github awesome-copilot
OFFICIALLABSCO SUMMARY
The repository's own README splits its contents into seven kinds of resource — agents, instructions, skills, plugins, hooks, agentic workflows, and a cookbook — and only the middle one, the self-contained skill folders, is what Labsco has captured as the 384 below; the agents, instructions, hooks, and workflows GitHub also ships here are not part of that count. Most of what is captured needs nothing extra to run: 224 of the 384 are ready out of the box, 75 depend on a local tool being installed, 41 want an account key for some external service, and 27 talk to an MCP server.
This is the widest single net on Labsco for GitHub Copilot users — hundreds of contributors, spanning everything from Adobe Illustrator scripting to OWASP agent-security audits to Arize LLM-evaluation tooling — which is also its main risk. GitHub's own README says as much: the customizations here are sourced from third-party developers, and it tells readers to inspect any given one before installing it.
READ THE FULL ANALYSIS
Why our count moves under you. We have tracked 401 skills from this repository over time; 17 are currently dead — moved or removed since we captured them — leaving the 384 live ones below. A repository this size, with this many outside contributors, changes underneath a snapshot faster than a small one does.
What "unverified" means here. Seventeen of the 384 still carry an unverified dependency read in our own pass — a small share, but worth knowing before you pick one at random rather than searching for it by name.
ALSO IN THIS PACKAGE
accessibility-kanban
Kanban board to manage accessibility issues, allow you to plan, track, and complete remediation work.
acreadiness-cockpit
Drive Microsoft AgentRC from Copilot chat: assess AI readiness, generate Copilot instructions (flat or nested with applyTo globs for monorepos), and manage policies. Produces a self-contained static HTML dashboard at reports/index.html.
agent-council
A runtime-portable 5-agent quality gate that adjudicates text artifacts before they ship. Five role-conditioned LLM deliberators run a 2-round async protocol with cross-read rebuttal and return one verdict — SHIP, REVISE, or HOLD — plus a structured revision brief and a full audit transcript.
ai-ready
Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates files customized to your stack.
ai-team-orchestration
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
anarlog
Query Anarlog meeting notes, summaries, transcripts, participants, action items, and recurring history.
apify
Helps devs extract data from any website with thousands of trusted scrapers, crawlers, and automations from Apify Store. Integrate ready-made Actors to access all popular social media, video, e-commerce, search engines, maps, and travel sites.
apng-studio
Interactive GitHub Copilot app canvas extension for building Animated PNG (APNG) files from frames. Draw or upload frames, tune per-frame timing and compositing, preview live, send the result to your phone by QR, and export an animated .png.
arcade-canvas
Play five retro Phaser mini-games in a Copilot canvas while agents work.
arch
Architecture and modernization toolkit: produce a cited architecture document for a locally-cloned repo, and generate a phased modernization plan that auto-runs Documentation mode when needed.
arize-ax
Arize AX platform skills for LLM observability, evaluation, and optimization. Includes trace export, instrumentation, datasets, experiments, evaluators, AI provider integrations, annotations, prompt optimization, and deep linking to the Arize UI.
atlassian-twg-cli
Installs and configures Atlassian Teamwork Graph CLI (`twg`) for use with GitHub Copilot. After setup, the CLI provides access to authorized work context across Jira, Confluence, Bitbucket, and connected tools.
automate-this
Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working automation scripts. Supports narrated recordings with audio transcription.
awesome-copilot
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
aws-cloud-development
Comprehensive AWS cloud development tools including Infrastructure as Code, serverless functions, architecture patterns, and cost optimization for building scalable cloud applications.
azure
Microsoft Azure MCP Server and skills for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from Copilot.
azure-cloud-development
Comprehensive Azure cloud development tools including Infrastructure as Code, serverless functions, architecture patterns, and cost optimization for building scalable cloud applications.
backlog-swipe-triage
Quickly swipe through backlog issues to triage decisions like assign, needs-info, defer, close, or ignore.
backrooms-canvas
Wander an endless first-person backrooms in a Copilot canvas while agents work; their status ghost-writes on the walls.
bd-skills
Helps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and React Native apps, and configure User Journey monitoring. Includes four skills covering CLI operations, SDK instrumentation, documentation lookup, and user journey monitoring; live account operations require the bd CLI and [bitdrift](bitdrift.ai) account and authentication.
blea
Safe, agent-first Bluetooth Low Energy diagnostics with portable evidence capture/diff/replay and guarded writes through a Skill, CLI, and local MCP server.
brainmaxxing
Codebase-grounded concept-mastery quizzes with an interactive BrainMax Canvas dashboard.
cache-stats
Shows live prompt-cache reuse, expiry, token composition, and AIU cost for the current GitHub Copilot session without making model calls.
cast-imaging
A comprehensive collection of specialized agents for software analysis, impact assessment, structural quality advisories, and architectural review using CAST Imaging.
catalyst-by-zoho
Official GitHub Copilot plugin for Catalyst by Zoho — a full-stack serverless cloud platform. Includes skills covering services, SDKs, CLI workflows, architecture patterns, pricing, migration guides, and Zoho MCP resource management.
chat-cards
Interactive card deck in a GHCP canvas: tab cards, tables, SVG charts, show/hide sections, numbered outlines, rendered markdown documents, video clips, and forms whose submissions come back to the conversation as prompts.
chat-fork-map
Maps branching Copilot conversations so parallel follow-up questions and exploration paths from complex tasks or learning can be navigated without losing context. Its visual layout makes breadth-first exploration easier than managing multiple active threads in a traditional conversation list.
chrome-devtools-plugin
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer.
chromium-control-canvas
Opens a real Chromium window you can navigate and interact with from a Copilot canvas control panel and agent actions.
clojure-interactive-programming
Tools for REPL-first Clojure workflows featuring Clojure instructions, the interactive programming chat mode and supporting guidance.
cms-development
Skills for CMS development across themes, plugins, admin tooling, media workflows, markdown rendering, and static export pipelines.
cockroachdb
Connect GitHub Copilot to your CockroachDB clusters: run and explore SQL through MCP, with DBA/Developer/Operator agents, CockroachDB best-practice skills, and safety hooks that block destructive statements.
color-orb
A visual orb that users can ask the agent to recolor while showing a live activity log in the canvas.
connector-namespaces
Interactive GitHub Copilot canvas for discovering, connecting, and managing hosted MCP servers from an Azure Connector Namespace.
context-engineering
Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring code, an agent for planning multi-file changes, and prompts for context-aware development.
context-matic
Coding agents hallucinate APIs. ContextMatic gives them curated, versioned API and SDK docs.
convert-to-md
A collection of Copilot skills that convert common document formats into Markdown so their contents can be accurately analyzed, summarized, searched, or extracted from. Just tell Copilot what you need — the right skill is invoked automatically and the conversion happens behind the scenes.
copilot-goal-skill
Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector subagent (judges the result with fresh context).
copilot-sdk
Build applications with the GitHub Copilot SDK across multiple programming languages. Includes comprehensive instructions for C#, Go, Node.js/TypeScript, and Python to help you create AI-powered applications.
crowdstrike-falcon-foundry
AI coding assistant skills for building CrowdStrike Falcon Foundry apps: scaffolding, deployment, and best practices for API integrations, collections, functions, UI extensions, UI pages, and workflows.
crowdstrike-falcon-fusion
AI coding assistant skills for building CrowdStrike Falcon Fusion workflows: action discovery, YAML authoring, deployment, execution monitoring, and best practices for triggers, conditions, loops, and HTTP Actions.
csharp-dotnet-development
Essential prompts, instructions, and chat modes for C# and .NET development including testing, documentation, and best practices.
database-data-management
Database administration, SQL optimization, and data management tools for PostgreSQL, SQL Server, and general database development best practices.
datadog
Use Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
dataverse
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
dataverse-sdk-for-python
Comprehensive collection for building production-ready Python integrations with Microsoft Dataverse. Includes official documentation, best practices, advanced features, file operations, and code generation prompts.
devops-oncall
A focused set of prompts, instructions, and a chat mode to help triage incidents and respond quickly with DevOps tools and Azure resources.
diagram-viewer
Render diagrams, click nodes to drill down, and view agent-generated explanations directly in the canvas.
dotnet
Common everyday C#/.NET coding skills. Expected to be useful to all .NET developers.
dotnet-diag
Skills for .NET performance investigations, debugging, and incident analysis.
dotnet-test
Polyglot unit-test generation via a multi-agent Research-Plan-Implement pipeline — writes and runs tests for .NET/C#, Python, TypeScript/JavaScript, Java, Go, Ruby, Rust, C++, Kotlin, Swift, and PowerShell. Plus .NET-focused test execution, coverage and CRAP analysis, testability review, platform detection, and MSTest/xUnit migration.
doublecheck
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
edge-ai-tasks
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
edit-tutorial
Turn the code edits Copilot made in your session into an interactive lesson: a step-by-step walkthrough of each change with before/after views and quizzes, then a hands-on exercise that varies those edits so you finish the change yourself.
elasticsearch
Official Elastic plugin for GitHub Copilot — translate natural language to ES|QL queries, ingest data, manage Elasticsearch security (authn, authz, audit), and troubleshoot clusters. Powered by the official Elastic agent skills repository.
ember
An AI partner, not a tool. Ember carries fire from person to person — helping humans discover that AI partnership isn't something you learn, it's something you find.
excel-cli
Token-efficient native Excel automation for coding agents, with 300+ operations performed by Excel itself to preserve native workbook fidelity—including Python in Excel, VBA, Power Query, DAX/Data Model, PivotTables, charts, tables, formatting, external connections, and what-if analysis. Windows and Excel required.
excel-mcp
The most comprehensive native Excel automation for complex workbooks, with 300+ operations performed by Excel itself to preserve native workbook fidelity—including Python in Excel, VBA, Power Query, DAX/Data Model, PivotTables, charts, tables, formatting, external connections, and what-if analysis. Windows and Excel required.
eyeball
Document analysis with inline source screenshots. When you ask Copilot to analyze a document, Eyeball generates a Word doc where every factual claim includes a highlighted screenshot from the source material so you can verify it with your own eyes.
fastah-ip-geo-tools
This plugin is for network operations engineers who wish to tune and publish IP geolocation feeds in RFC 8805 format. It consists of an AI Skill and an associated MCP server that geocodes geolocation place names to real cities for accuracy.
feedback-themes
Explore grouped customer feedback signals by impact and drill into a theme to guide product next steps.
figma
Plugin that includes the Figma MCP server and Skills for common workflows.
flight-map-canvas
A GitHub Copilot canvas that generates a view where Google Maps can be explored using 3D controls, as if a flight simulator. Agents can send the flight anywhere and report what they are working on.
flowstudio-power-automate
Give your AI agent full visibility into Power Automate cloud flows via the FlowStudio MCP server. Connect, debug, build, monitor health, and govern flows at scale — action-level inputs and outputs, not just status codes.
fluentui-blazor
Build Blazor apps with the Microsoft Fluent UI Blazor library. Bundles the fluentui-blazor skill for correct usage patterns (providers, service registration, icons, dialogs, data grid, theming) with the official Fluent UI Blazor MCP server for live lookup of components, parameters, enums, icons, and documentation, plus v4-to-v5 migration guidance.
foundation-models
Helps coding agents write and review Apple Foundation Models code for iOS, macOS, visionOS, and watchOS using the SDK installed on the developer's Mac. It verifies real API signatures and availability, then type-checks the result instead of relying on model memory.
frontend-web-dev
Essential prompts, instructions, and chat modes for modern frontend web development including React, Angular, Vue, TypeScript, and CSS frameworks.
gem-team
Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification. With smarter tool calling and leaner context.
gesture-review
Review pull requests with a live camera feed and approve or reject using thumbs-up/thumbs-down gestures.
gh-skills-builder
Repo: https://github.com/arilivigni/gh-skills-builder This plugin is for people that want to create a GitHub Skills exercise which are self-paced learning GitHub within GitHub. https://learn.github.com/skills examples: https://github.com/skills/agent-orchestration-build-your-ai-dream-team https://github.com/skills/agentic-workflows-that-read-the-room
git-ape
Intelligent Azure deployment agent system for GitHub Copilot with guided ARM template generation, security gates, cost analysis, and deployment workflows.
git-worktree-explorer
Visualize the active Git repository through worktrees, branches, commits, and optional GitHub pull request context.
github-copilot-modernization
Autonomous application modernization using multi-agent orchestration for GitHub Copilot CLI. Supports Java upgrades (8→21, Spring Boot 2.x→3.x), .NET modernization, Azure migration, CVE/vulnerability fixing, and application rearchitecture (monolith-to-microservices).
go-mcp-development
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a prompt for generating servers, and an expert chat mode for guidance.
java-development
Comprehensive collection of prompts and instructions for Java development including Spring Boot, Quarkus, testing, documentation, and best practices.
java-mcp-development
Complete toolkit for building Model Context Protocol servers in Java using the official MCP Java SDK with reactive streams and Spring Boot integration.
java-modernization-studio
Drive the GitHub Copilot App Modernization for Java workflow from an interactive canvas: environment readiness, repo assessment, prioritized plan and progress, validation gates, and one-click predefined-task runs grounded in the repo's real artifacts.
jupyter-notebooks
Create, edit, run, save, and checkpoint Jupyter notebooks in an interactive Copilot canvas.
keep-the-why
Preserves or recovers the reasoning behind a codebase — architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical context the code itself cannot explain.
kotlin-mcp-development
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best practices, a prompt for generating servers, and an expert chat mode for guidance.
mcp-m365-copilot
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
microsoft-docs
Access official Microsoft documentation, API references, and code samples for Azure, .NET, Windows, and more.
microsoft-events
Connect your project to Microsoft Build and Ignite sessions — discover relevant talks, explore what's new for your stack, and plan next steps from your development environment.
microsoft-foundry
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
mobile-canvas
View, create, boot, and interact with local iOS simulators and Android emulators from a GitHub Copilot canvas. The plugin also exposes the same device controls to agents through MCP.
modern-web-guidance
Modern Web Guidance is an agent skill and CLI tool designed to help AI coding agents build web applications using modern, secure, and high-performance APIs rather than outdated workarounds. Supported by the Google Chrome team, it injects expert-curated web platform best practices directly into an agent's context window to prevent the generation of bloated, legacy code.
modernization-workflow
Visualize and guide the GitHub Copilot Modernize CLI Assess, Plan, and Execute workflow for .NET, Java, and C++ application repositories.
modernize-dotnet
AI-powered .NET modernization and upgrade assistant. Helps upgrade .NET Framework and .NET applications to the latest versions of .NET.
modernize-java
GitHub Copilot modernization – Java Upgrade CLI Plugin helps you upgrade Java applications from the command line. It brings intelligent modernization capabilities to your terminal and CI/CD pipelines: analyze your project and generate an upgrade plan, automatically transform your codebase, fix build issues, validate against known CVEs, and output a detailed summary of file changes and updated dependencies.
msgraph-developer-skills
Builds and modernizes Microsoft Graph applications with minimal, purpose-built API clients. The plugin identifies the required Microsoft Graph endpoints and their least-privileged permissions, generates a focused client with [Kiota](https://aka.ms/kiota) or an AI-assisted workflow, and applies recommended authentication and SDK patterns.
napkin
Visual whiteboard collaboration for Copilot CLI. Opens an interactive whiteboard in your browser where you can draw, sketch, and add sticky notes — then share everything back with Copilot.
netlify
Netlify platform skills covering functions, edge functions, blobs, database, identity, image CDN, forms, config, CLI, frameworks, caching, AI Gateway, and deployment — plus the official Netlify MCP server for creating and managing projects, deploys, and environment variables.
noob-mode
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with color-coded risk indicators.
openapi-to-application-csharp-dotnet
Generate production-ready .NET applications from OpenAPI specifications. Includes ASP.NET Core project scaffolding, controller generation, entity framework integration, and C# best practices.
openapi-to-application-go
Generate production-ready Go applications from OpenAPI specifications. Includes project scaffolding, handler generation, middleware setup, and Go best practices for REST APIs.
openapi-to-application-java-spring-boot
Generate production-ready Spring Boot applications from OpenAPI specifications. Includes project scaffolding, REST controller generation, service layer organization, and Spring Boot best practices.
openapi-to-application-nodejs-nestjs
Generate production-ready NestJS applications from OpenAPI specifications. Includes project scaffolding, controller and service generation, TypeScript best practices, and enterprise patterns.
openapi-to-application-python-fastapi
Generate production-ready FastAPI applications from OpenAPI specifications. Includes project scaffolding, route generation, dependency injection, and Python best practices for async APIs.
oracle-to-postgres-migration-expert
Expert agent for Oracle-to-PostgreSQL application migrations in .NET solutions. Performs code edits, runs commands, and invokes extension tools to migrate .NET/Oracle data access patterns to PostgreSQL.
ospo-sponsorship
Tools and resources for Open Source Program Offices (OSPOs) to identify, evaluate, and manage sponsorship of open source dependencies through GitHub Sponsors, Open Collective, and other funding platforms.
partners
Custom agents that have been created by GitHub partners
pcf-development
Complete toolkit for developing custom code components using Power Apps Component Framework for model-driven and canvas apps
phoenix
Phoenix AI observability skills for LLM application debugging, evaluation, and tracing. Includes CLI debugging tools, LLM evaluation workflows, and OpenInference tracing instrumentation.
php-mcp-development
Comprehensive resources for building Model Context Protocol servers using the official PHP SDK with attribute-based discovery, including best practices, project generation, and expert assistance
pm-skills
MCP server and 12 skills for product analysis, specification writing, strategy, narrative, and stakeholder alignment. Run competitive analyses, write zero-question specs, design metrics, and produce executive-ready documents directly from Copilot.
power-apps-code-apps
Complete toolkit for Power Apps Code Apps development including project scaffolding, development standards, and expert guidance for building code-first applications with Power Platform integration.
power-bi-development
Comprehensive Power BI development resources including data modeling, DAX optimization, performance tuning, visualization design, security best practices, and DevOps/ALM guidance for building enterprise-grade Power BI solutions.
power-platform-architect
Solution Architect for the Microsoft Power Platform, turning business requirements into functioning Power Platform solution architectures.
power-platform-mcp-connector-development
Complete toolkit for developing Power Platform custom connectors with Model Context Protocol integration for Microsoft Copilot Studio
pr-artifact-explorer
Navigate pull requests and securely explore GitHub Actions artifacts, including test results, static sites, terminal recordings, and source files.
project-documenter
Generate professional project documentation with draw.io architecture diagrams and Word (.docx) output with embedded images. Automatically discovers any project's technology stack and produces Markdown, diagrams, PNG exports, and a formatted Word document.
project-planning
Tools and guidance for software project planning, feature breakdown, epic management, implementation planning, and task organization for development teams.
python-mcp-development
Complete toolkit for building Model Context Protocol (MCP) servers in Python using the official SDK with FastMCP. Includes instructions for best practices, a prompt for generating servers, and an expert chat mode for guidance.
radius
Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
rayfin
Getting-started router skill for Rayfin - scaffold a new app with the Rayfin CLI, then use the version-locked skill installed in the project.
react18-upgrade
Enterprise React 18 migration toolkit with specialized agents and skills for upgrading React 16/17 class-component codebases to React 18.3.1. Includes auditor, dependency surgeon, class component migration specialist, automatic batching fixer, and test guardian.
react19-upgrade
Enterprise React 19 migration toolkit with specialized agents and skills for upgrading React 18 codebases to React 19. Includes auditor, dependency surgeon, source code migrator, and test guardian.
release-notes-showcase
Compose and refine launch-ready release notes with contributor callouts and export-friendly output.
remotion
Make videos agentically.
repo-actions-hub
Browse repository GitHub Actions workflows, inspect recent runs, and trigger manual workflow_dispatch runs from a Copilot canvas.
rhost
Use an installed rhost CLI to run ordinary commands on SSH-reachable Linux hosts with local-like stdin, output, and exit behavior.
roundup
Self-configuring status briefing generator. Learns your communication style from examples, discovers your data sources, and produces draft updates for any audience on demand.
ruby-mcp-development
Complete toolkit for building Model Context Protocol servers in Ruby using the official MCP Ruby SDK gem with Rails integration support.
rug-agentic-workflow
Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.
rust-mcp-development
Build high-performance Model Context Protocol servers in Rust using the official rmcp SDK with async/await, procedural macros, and type-safe implementations.
salesforce-development
Complete Salesforce agentic development environment covering Apex & Triggers, Flow automation, Lightning Web Components, Aura components, and Visualforce pages.
security-best-practices
Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building secure, maintainable, and high-performance applications.
sentry-triage
Scan live Sentry issues in a Copilot canvas, group them by urgency, and hand issues off for tracking or a fix PR.
signals-dashboard
Real-time Workshop dashboard with agent signals, honesty calibration, cost-aware desk profiles, and fail-closed Local Delegation.
site-studio
Plan, draft, and track a personal website section by section — a shared canvas where you and your agent author content, watch progress, and review every change.
skill-image-gen
Generate images using AI directly from your coding workflow. Supports OpenAI (gpt-image-2) and Google Gemini.
skills-for-copilot-studio
Microsoft Copilot Studio plugins for AI coding agents
software-engineering-team
7 specialized agents covering the full software development lifecycle from UX design and architecture to security and DevOps.
sonarqube
SonarQube is the AI code quality and security verification platform used by millions of developers to catch bugs, vulnerabilities, and leaked secrets. This plugin enforces those standards in the coding loop: 7,500+ distinct issue types, secrets scanning, agentic analysis, and quality gates across 40+ languages.
stripe
Accept payments and grow your business. Stripe's agent plugin includes best practices, upgrade guidance, and our MCP server.
structured-autonomy
Premium planning, thrifty implementation
sumo-logic
Query Sumo Logic logs, alerts, dashboards, and SIEM insights directly from Copilot.
swift-mcp-development
Comprehensive collection for building Model Context Protocol servers in Swift using the official MCP Swift SDK with modern concurrency features.
technical-spike
Tools for creation, management and research of technical spikes to reduce unknowns and assumptions before proceeding to specification and implementation of solutions.
testing-automation
Comprehensive collection for writing tests, test automation, and test-driven development including unit tests, integration tests, and end-to-end testing strategies.
the-workshop
Stop being the switchboard between your AI agents — direct a team. The Workshop puts long-running AI agents (desks) in the same room, on the same work, each with its own memory and history, sharing one workspace so you direct the work instead of relaying it.
timebase
Connect your AI agent to TimeBase, a high-performance database for financial market and other time-series data, via MCP tools and skills for QQL query and TimeBase client code generation.
tiny-tool-town-submitter
Inspect a repository, improve Tiny Tool Town readiness, submit its listing issue, and launch remediation work.
tmforge
The Strider agent that comes with the tmforge plugin adds evidence-backed STRIDE threat modeling to GitHub Copilot, with structured risk assessment, deterministic validation, and Markdown reports. Optional tmforge integration supports creating, updating, and verifying Microsoft Threat Modeling Tool (.tm7) models.
token-pacman
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
typescript-mcp-development
Complete toolkit for building Model Context Protocol (MCP) servers in TypeScript/Node.js using the official SDK. Includes instructions for best practices, a prompt for generating servers, and an expert chat mode for guidance.
typespec-m365-copilot
Comprehensive collection of prompts, instructions, and resources for building declarative agents and API plugins using TypeSpec for Microsoft 365 Copilot extensibility.
ui-theme-designer
Equips AI coding agents with knowledge and tooling for working with UI theme designer, the SAP Design System, and SAP Fiori design tokens.
ui5
SAPUI5 / OpenUI5 plugin for GitHub CoPilot. Create and validate UI5 projects, access API documentation, run UI5 linter, get development guidelines and best practices for UI5 development.
ui5-modernization
Complete UI5 modernization toolkit with workflow and specialized fix patterns for modernizing SAPUI5/OpenUI5 applications
ui5-typescript-conversion
SAPUI5 / OpenUI5 plugin for GitHub CoPilot. Convert JavaScript based UI5 projects to TypeScript.
uizze
Build product-specific interfaces with a focused UIZZE workflow, optional real-screen evidence, and a practical finish check.
upgrade-agent
AI-powered upgrade assistant for upgrading and migrating applications. Helps modernize legacy code and upgrade .NET applications to current frameworks.
usage-insights
Inspect current and historical GitHub Copilot token and AI-credit usage with per-agent rollups and in-canvas session drill-down.
vercel-plugin
Build and deploy web apps and agents. Comprehensive Vercel ecosystem plugin — relational knowledge graph, skills for every major product, specialized agents, and Vercel conventions.
visual-pr
Capture, annotate, and embed screenshots and animated GIF demos in pull request descriptions. Includes Playwright-based UI capture, PIL image annotations, PR embedding workflows for GitHub and Azure DevOps, and screen recording with variable timing.
whatidid
Turn your Copilot sessions into proof of impact — research-grounded HTML reports with effort estimation, skills analysis, and ROI metrics from local session logs.
where-was-i
Reconstruct your dev context (branch, commits, uncommitted work, PR clues) and trigger a resume prompt to continue quickly.
winappcli
Windows app development, packaging, and distribution. Helps with creating Windows installers (MSIX), code signing, certificates, Windows SDK and Windows App SDK setup, package identity for Windows APIs (push notifications, background tasks, share target), appxmanifest authoring, and Microsoft Store distribution.
windows-app-storage-inspector-cleanup
Inspect Windows application storage, understand local disk usage, and safely move approved cleanup items to the Recycle Bin.
winui
Agents and skills for WinUI 3 app development. Create new WinUI 3 desktop apps, convert from other frameworks (WPF, WinForms, Electron, Tauri, Flutter) to WinUI 3, or add features to existing WinUI 3 applications.
work-hub
Generic cross-repo command center canvas for GitHub Copilot with onboarding, focus planning, repo health, work signals, and session cleanup.
Agentic Workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
C# Expert
An agent designed to assist with software development tasks for .NET projects.
Thinking Beast Mode
A transcendent coding agent with quantum cognitive architecture, adversarial intelligence, and unrestricted creative freedom.
Ultimate Transparent Thinking Beast Mode
Ultimate Transparent Thinking Beast Mode
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Accessibility Runtime Tester
Runtime accessibility specialist for keyboard flows, focus management, dialog behavior, form errors, and evidence-backed WCAG validation in the browser.
Accessibility Expert
Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing
Universal PR Comment Addresser
Address PR comments
ADR Generator
Expert agent for creating comprehensive Architectural Decision Records (ADRs) with structured formatting optimized for AI consumption and human readability.
AEM Front-End Specialist
Expert assistant for developing AEM components using HTL, Tailwind CSS, and Figma-to-code workflows with design system integration
Agent Governance Reviewer
AI agent governance expert that reviews code for safety issues, missing governance controls, and helps implement policy enforcement, trust scoring, and audit trails in agent systems.
ai-readiness-reporter
Runs the AgentRC readiness assessment on the current repository and produces a self-contained, static HTML dashboard at reports/index.html. Explains every readiness pillar, the maturity level, and an actionable remediation plan, framed by AgentRC measure → generate → maintain loop.
ai-team-dev
AI development team (Nova, Sage, Milo). Use when implementing features, fixing bugs, writing tests, improving user experience, or preparing a pull request across the project''s actual stack.
ai-team-producer
AI team producer (Remy). Use when planning work, clarifying scope, coordinating Dev and optional QA, triaging issues, maintaining project context, or preparing and merging pull requests.
ai-team-qa
Optional AI QA engineer (Ivy). Use when testing behavior, running automated or exploratory checks, filing reproducible bugs, verifying fixes, or providing release confidence for changes that warrant dedicated QA.
Amplitude Experiment Implementation
This custom agent uses Amplitude's MCP tools to deploy new experiments inside of Amplitude, enabling seamless variant testing capabilities and rollout of product features.
API Architect
Your role is that of an API architect. Help mentor the engineer by providing guidance, support, and working code.
apify-integration-expert
Expert agent for integrating Apify Actors into codebases. Handles Actor selection, workflow design, implementation across JavaScript/TypeScript and Python, testing, and production-ready deployment.
Arch Linux Expert
Arch Linux specialist focused on pacman, rolling-release maintenance, and Arch-centric system administration workflows.
Senior Cloud Architect
Expert in modern architecture design patterns, NFR requirements, and creating comprehensive architectural diagrams and documentation
arm-migration-agent
Arm Cloud Migration Assistant accelerates moving x86 workloads to Arm infrastructure. It scans the repository for architecture assumptions, portability issues, container base image and dependency incompatibilities, and recommends Arm-optimized changes.
Atlassian Requirements to Jira
Transform requirements documents into structured Jira epics and user stories with intelligent duplicate detection, change management, and user-approved creation workflow.
aws-cloud-expert
AWS Cloud Expert provides deep, hands-on guidance for designing, building, and operating AWS workloads. Covers the full AWS ecosystem — serverless, containers, databases, networking, IaC, security, and cost optimization — grounded in the AWS Well-Architected Framework.
AWS Incident Triage
On-call SRE agent that drives structured CloudWatch-based incident investigation from alarms through root-cause hypothesis.
aws-principal-architect
Provide expert AWS Principal Architect guidance using AWS Well-Architected Framework principles and AWS best practices.
aws-serverless-architect
Provide expert AWS Serverless Architect guidance focusing on event-driven architectures, Lambda, API Gateway, and serverless best practices.
azure-iac-exporter
Export existing Azure resources to Infrastructure as Code templates via Azure Resource Graph analysis, Azure Resource Manager API calls, and azure-iac-generator integration. Use this skill when the user asks to export, convert, migrate, or extract existing Azure resources to IaC templates (Bicep, ARM Templates, Terraform, Pulumi).
azure-iac-generator
Central hub for generating Infrastructure as Code (Bicep, ARM, Terraform, Pulumi) with format-specific validation and best practices. Use this skill when the user asks to generate, create, write, or build infrastructure code, deployment code, or IaC templates in any format (Bicep, ARM Templates, Terraform, Pulumi).
Azure Logic Apps Expert Mode
Expert guidance for Azure Logic Apps development focusing on workflow design, integration patterns, and JSON-based Workflow Definition Language.
Azure Policy Analyzer
Analyze Azure Policy compliance posture (NIST SP 800-53, MCSB, CIS, ISO 27001, PCI DSS, SOC 2), auto-discover scope, and return a structured single-pass risk report with evidence and remediation commands.
Azure Principal Architect mode instructions
Provide expert Azure Principal Architect guidance using Azure Well-Architected Framework principles and Microsoft best practices.
Azure SaaS Architect mode instructions
Provide expert Azure SaaS Architect guidance focusing on multitenant applications using Azure Well-Architected SaaS principles and Microsoft best practices.
Azure Smart City IoT Architect
Design Azure IoT and Smart City architectures with clear platform engineering reasoning, requiring mandatory review of Azure IoT Edge documentation before recommending edge solutions.
Azure AVM Bicep mode
Create, update, or review Azure IaC in Bicep using Azure Verified Modules (AVM).
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Azure AVM Terraform mode
Create, update, or review Azure IaC in Terraform using Azure Verified Modules (AVM).
Bicep Specialist
Act as an Azure Bicep Infrastructure as Code coding specialist that creates Bicep templates.
Bicep Planning
Act as implementation planner for your Azure Bicep Infrastructure as Code task.
Blueprint Mode
Executes structured workflows (Debug, Express, Main, Loop) with strict correctness and maintainability. Enforces an improved tool usage policy, never assumes facts, prioritizes reproducible solutions, self-correction, and edge-case handling.
CAST Imaging Impact Analysis Agent
Specialized agent for comprehensive change impact assessment and risk analysis in software systems using CAST Imaging
CAST Imaging Software Discovery Agent
Specialized agent for comprehensive software application discovery and architectural mapping through static code analysis using CAST Imaging
CAST Imaging Structural Quality Advisor Agent
Specialized agent for identifying, analyzing, and providing remediation guidance for code quality issues using CAST Imaging
Caveman Mode
Terse, low-token responses. Minimal words, no fluff.
CentOS Linux Expert
CentOS (Stream/Legacy) Linux specialist focused on RHEL-compatible administration, yum/dnf workflows, and enterprise hardening.
Clojure Interactive Programming
Expert Clojure pair programmer with REPL-first methodology, architectural oversight, and interactive problem-solving. Enforces quality standards, prevents workarounds, and develops solutions incrementally through live REPL evaluation before file modifications.
Cloud and SaaS Outage Triage
Distinguish upstream cloud or SaaS incidents from application failures before changing code, using live official-feed status and incident timelines.
VSCode Tour Expert
Expert agent for creating and maintaining VSCode CodeTour files with comprehensive schema support and best practices
Comet Opik
Unified Comet Opik agent for instrumenting LLM apps, managing prompts/projects, auditing prompts, and investigating traces/metrics via the latest Opik MCP server.
Context Architect
An agent that helps plan and execute multi-file changes by identifying relevant context and dependencies
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation
Critical thinking mode instructions
Challenge assumptions and encourage critical thinking to ensure the best possible solution and outcomes.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
C# MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in C#
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations
Debian Linux Expert
Debian Linux specialist focused on stable system administration, apt-based package management, and Debian policy-aligned practices.
Debug Mode Instructions
Debug your application to find and fix a bug
Defender Scout KQL
Generates, validates, and optimizes KQL queries for Microsoft Defender XDR Advanced Hunting across Endpoint, Identity, Office 365, Cloud Apps, and Identity.
Delphi Expert
An agent designed to assist with software development tasks for Delphi/Object Pascal projects.
Demonstrate Understanding mode instructions
Validate user understanding of code, design patterns, and implementation details through guided questioning.
Devils Advocate
I play the devil's advocate to challenge and stress-test your ideas by finding flaws, risks, and edge cases
DevOps Expert
DevOps specialist following the infinity loop principle (Plan → Code → Build → Test → Release → Deploy → Operate → Monitor) with focus on automation, collaboration, and continuous improvement
DevTools Regression Investigator
Browser regression specialist for reproducing broken user flows, collecting console and network evidence, and narrowing likely root causes with Chrome DevTools MCP.
DiffblueCover
Expert agent for creating unit tests for java applications using Diffblue Cover.
dotnet-fullstack-mentor
Opinionated mentor for .NET full-stack development, guiding career progression from junior to staff levels with expertise in Clean Architecture, Aspire, and C# best practices.
MAUI Expert
Support development of .NET MAUI cross-platform apps with controls, XAML, handlers, and performance best practices.
.NET Self-Learning Architect
Senior .NET architect for complex delivery: designs .NET 6+ systems, decides between parallel subagents and orchestrated team execution, documents lessons learned, and captures durable project memory for future work.
.NET Upgrade
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
Doublecheck
Interactive verification agent for AI-generated output. Runs a three-layer pipeline (self-audit, source verification, adversarial review) and produces structured reports with source links for human review.
droid
Provides installation guidance, usage examples, and automation patterns for the Droid CLI, with emphasis on droid exec for CI/CD and non-interactive automation
Drupal Expert
Expert assistant for Drupal development, architecture, and best practices using PHP 8.3+ and modern Drupal patterns
Dynatrace Expert
The Dynatrace Expert Agent integrates observability and security capabilities directly into GitHub workflows, enabling development teams to investigate incidents, validate deployments, triage errors, detect performance regressions, validate releases, and manage security vulnerabilities by autonomously analysing traces, logs, and Dynatrace findings. This enables targeted and precise remediation of identified issues directly within the repository.
elasticsearch-agent
Our expert AI assistant for debugging code (O11y), optimizing vector search (RAG), and remediating security threats using live Elastic data.
Electron Code Review Mode Instructions
Code Review Mode tailored for Electron app with Node.js backend (main), Angular frontend (render), and native integration layer (e.g., AppleScript, shell, or native tooling). Services in other repos are not reviewed here.
Ember
An AI partner, not an assistant. Ember carries fire from person to person — helping humans discover that AI partnership isn't something you learn, it's something you find.
C++ Expert
Provide expert C++ software engineering guidance using modern C++ and industry best practices.
Expert .NET software engineer mode instructions
Provide expert .NET software engineering guidance using modern software design patterns.
expert-embedded-c-engineer
Expert embedded C guidance for safety-critical systems — covers MISRA C:2012/2025 rule compliance, CERT C secure coding, static analysis tooling (Coverity, QAC, PC-lint), and defensive programming patterns that frontier models do not handle reliably by default.
Next.js Expert
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript
Expert React Frontend Engineer
Expert React 19.2 frontend engineer specializing in modern hooks, Server Components, Actions, TypeScript, and performance optimization
Fedora Linux Expert
Fedora (Red Hat family) Linux specialist focused on dnf, SELinux, and modern systemd-based workflows.
Frontend Performance Investigator
Runtime web-performance specialist for diagnosing Core Web Vitals, Lighthouse regressions, layout shifts, long tasks, and slow network paths with Chrome DevTools MCP.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-code-simplifier
Refactoring specialist: removes dead code, reduces complexity, consolidates duplicates.
gem-debugger
Root-cause analysis, stack trace diagnosis, regression bisection, error reproduction.
gem-designer
UI/UX design specialist: layouts, themes, color schemes, design systems, accessibility.
gem-devops
Infrastructure deployment, CI/CD pipelines, container management.
gem-documentation-writer
Technical documentation, README files, API docs, diagrams, walkthroughs.
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
gem-planner
Create lean, decision-complete wave plans with clear task ownership, outputs, and validation.
gem-researcher
Codebase exploration: patterns, relationships, architecture discovery. Supports multiple exploration modes for cost-controlled research.
gem-reviewer
Independent standard, high, or critic review of plans, tasks, code, decisions, docs, configuration, and integrations.
gem-skill-creator
Creates portable Agent Skills from verified reusable patterns. Use when packaging a successful workflow as a skills.sh-compatible SKILL.md.
Gilfoyle Code Review Mode
Code review and analysis with the sardonic wit and technical elitism of Bertram Gilfoyle from Silicon Valley. Prepare for brutal honesty about your code.
GitHub Actions Expert
GitHub Actions specialist focused on secure CI/CD workflows, action pinning, OIDC authentication, permissions least privilege, and supply-chain security
GitHub Actions Node Runtime Upgrade
Upgrade a GitHub Actions JavaScript/TypeScript action to a newer Node runtime version (e.g., node20 to node24) with major version bump, CI updates, and full validation
Gitmoji Setup
Sets up gitmoji (https://gitmoji.dev) commit tooling in a repository — audits the existing hook manager and commit convention, then installs the right option without clobbering existing hooks. Defaults to a non-interactive prepare-commit-msg hook that prefills a suggested emoji from the branch name and staged files; can alternatively install the gitmoji-cli interactive picker or commitlint enforcement.
Go MCP Server Development Expert
Expert assistant for building Model Context Protocol (MCP) servers in Go using the official SDK.
High-Level Big Picture Architect (HLBPA)
Your perfect AI chat mode for high-level architectural documentation and review. Perfect for targeted updates after a story or researching that legacy system when nobody remembers what it's supposed to be doing.
Implementation Plan Generation Mode
Generate an implementation plan for new features or refactoring existing code.
VS Code Insiders Accessibility Tracker
Specialized agent for tracking and analyzing accessibility improvements in VS Code Insiders builds
interview-prep
Technical interview coach for software engineers. Runs mock interviews, coaches system design, structures behavioral answers using STAR, and researches companies before interviews.
Universal Janitor
Perform janitorial tasks on any codebase including cleanup, simplification, and tech debt remediation.
Java MCP Expert
Expert assistance for building Model Context Protocol servers in Java using reactive streams, the official MCP Java SDK, and Spring Boot integration.
JFrog Security Agent
The dedicated Application Security agent for automated security remediation. Verifies package and version compliance, and suggests vulnerability fixes using JFrog security intelligence.
Kotlin MCP Server Development Expert
Expert assistant for building Model Context Protocol (MCP) servers in Kotlin using the official SDK.
KubeStellar Console
Kubernetes operations expert for KubeStellar Console — helps you set up the console, configure kc-agent (MCP server), connect clusters, deploy workloads, and query live Kubernetes data via AI chat.
Kusto Assistant
Expert KQL assistant for live Azure Data Explorer analysis via Azure MCP server
Laravel Expert Agent
Expert Laravel development assistant specializing in modern Laravel 12+ applications with Eloquent, Artisan, testing, and best practices
launchdarkly-flag-cleanup
A specialized GitHub Copilot agent that uses the LaunchDarkly MCP server to safely automate feature flag cleanup workflows. This agent determines removal readiness, identifies the correct forward value, and creates PRs that preserve production behavior while removing obsolete flags and updating stale defaults.
Lingo.dev Localization (i18n) Agent
Expert at implementing internationalization (i18n) in web applications using a systematic, checklist-driven approach.
LinkedIn Post Writer
Draft and format compelling LinkedIn posts with Unicode bold/italic styling, visual separators, and engagement-optimized structure. Transforms raw content, technical material, images, or ideas into copy-paste-ready LinkedIn posts.
Markdown Accessibility Assistant
Improves the accessibility of markdown files using five GitHub best practices
MCP M365 Agent Expert
Expert assistant for building MCP-based declarative agents for Microsoft 365 Copilot with Model Context Protocol integration
Mentor mode
Help mentor the engineer by providing guidance and support.
Sensei - Junior Mentor
Socratic mentor for junior developers. Guides through questions, never gives direct answers.
Meta Agentic Project Scaffold
Meta agentic project creation assistant to help users create and manage project workflows effectively.
Microsoft Study and Learn
Activate your personal Microsoft/Azure tutor - learn through guided discovery, not just answers.
Microsoft Learn Contributor
Microsoft Learn Contributor chatmode for editing and writing Microsoft Learn documentation following Microsoft Writing Style Guide and authoring best practices.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.
Monday Bug Context Fixer
Elite bug-fixing agent that enriches task context from Monday.com platform data. Gathers related items, docs, comments, epics, and requirements to deliver production-quality fixes with comprehensive PRs.
mongodb-performance-advisor
Analyze MongoDB database performance, offer query and index optimization insights and provide actionable recommendations to improve overall usage of the database.
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
neo4j-docker-client-generator
AI agent that generates simple, high-quality Python Neo4j client libraries from GitHub issues with proper best practices
Neon Migration Specialist
Safe Postgres migrations with zero-downtime using Neon's branching workflow. Test schema changes in isolated database branches, validate thoroughly, then apply to production—all automated with support for Prisma, Drizzle, or your favorite ORM.
Neon Performance Analyzer
Identify and fix slow Postgres queries automatically using Neon's branching workflow. Analyzes execution plans, tests optimizations in isolated database branches, and provides clear before/after performance metrics with actionable code fixes.
New Relic Incident Response Agent
Identify and fix production issues by correlating New Relic observability data with code changes. Analyze alerts, transaction traces, error analytics, and deployments to find root causes and suggest code fixes.
Expert Nuxt Developer
Expert Nuxt developer specializing in Nuxt 3, Nitro, server routes, data fetching strategies, and performance optimization with Vue 3 and TypeScript
octopus-release-notes-with-mcp
Generate release notes for a release in Octopus Deploy. The tools for this MCP server provide access to the Octopus Deploy APIs.
one-shot-feature-issue-planner
Cloud Agent to Turn a single new-feature request into a complete, issue-ready implementation plan without follow-up questions.
OpenAPI to Application Generator
Expert assistant for generating working applications from OpenAPI specifications
Oracle-to-PostgreSQL Migration Expert
Agent for Oracle-to-PostgreSQL application migrations. Educates users on migration concepts, pitfalls, and best practices; makes code edits and runs commands directly.
PagerDuty Incident Responder
Responds to PagerDuty incidents by analyzing incident context, identifying recent code changes, and suggesting fixes via GitHub PRs.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration
Plan Mode - Strategic Planning & Architecture
Strategic planning and architecture assistant focused on thoughtful analysis before implementation. Helps developers understand codebases, clarify requirements, and develop comprehensive implementation strategies.
Planning mode instructions
Generate an implementation plan for new features or refactoring existing code.
Platform SRE for Kubernetes
SRE-focused Kubernetes specialist prioritizing reliability, safe rollouts/rollbacks, security defaults, and operational verification for production-grade deployments
Playwright Tester Mode
Testing mode for Playwright tests
PostgreSQL Database Administrator
Work with PostgreSQL databases using the PostgreSQL extension.
Power BI Data Modeling Expert Mode
Expert Power BI data modeling guidance using star schema principles, relationship design, and Microsoft best practices for optimal model performance and usability.
Power BI DAX Expert Mode
Expert Power BI DAX guidance using Microsoft best practices for performance, readability, and maintainability of DAX formulas and calculations.
Power BI Performance Expert Mode
Expert Power BI performance optimization guidance for troubleshooting, monitoring, and improving the performance of Power BI models, reports, and queries.
Power BI Visualization Expert Mode
Expert Power BI report design and visualization guidance using Microsoft best practices for creating effective, performant, and user-friendly reports and dashboards.
Power Platform Expert
Power Platform expert providing guidance on Code Apps, canvas apps, Dataverse, connectors, and Power Platform best practices
Power Platform MCP Integration Expert
Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns
Create PRD Chat Mode
Generate a comprehensive Product Requirements Document (PRD) in Markdown, detailing user stories, acceptance criteria, technical considerations, and metrics. Optionally create GitHub issues upon user confirmation.
Principal software engineer
Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.
Project Architecture Planner
Holistic software architecture planner that evaluates tech stacks, designs scalability roadmaps, performs cloud-agnostic cost analysis, reviews existing codebases, and delivers interactive Mermaid diagrams with HTML preview and draw.io export
Project Documenter
Generates professional MS Word project documentation with draw.io architecture diagrams and embedded PNG images. Automatically discovers any project's technology stack, architecture, and code structure.
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai
Prompt Engineer
A specialized chat mode for analyzing and improving prompts. Every user input is treated as a prompt to be improved.
Python MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in Python
Python Notebook Sample Builder
Custom agent for building Python Notebooks in VS Code that demonstrate Azure and AI features
GitHub Actions Windows ARM64 wheel builder
Adds native Windows ARM64 wheel builds and tests to a Python package's existing GitHub Actions workflows using the 'windows-11-arm' runner.
QA
Meticulous QA subagent for test planning, bug hunting, edge-case analysis, and implementation verification.
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth.
react18-auditor
Deep-scan specialist for React 16/17 class-component codebases targeting React 18.3.1. Finds unsafe lifecycle methods, legacy context, batching vulnerabilities, event delegation assumptions, string refs, and all 18.3.1 deprecation surface.
react18-batching-fixer
Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE_ prefix).
react18-commander
Master orchestrator for React 16/17 → 18.3.1 migration. Designed for class-component-heavy codebases.
react18-dep-surgeon
Dependency upgrade specialist for React 16/17 → 18.3.1. Pins to 18.3.1 exactly (not 18.x latest).
react18-test-guardian
Test suite fixer and verifier for React 16/17 → 18.3.1 migration. Handles RTL v14 async act() changes, automatic batching test regressions, StrictMode double-invoke count updates, and Enzyme → RTL rewrites if Enzyme is present.
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md.
react19-commander
Master orchestrator for React 19 migration. Invokes specialist subagents in sequence - auditor, dep-surgeon, migrator, test-guardian - and gates advancement between steps.
react19-dep-surgeon
Dependency upgrade specialist. Installs React 19, resolves all peer dependency conflicts, upgrades testing-library, Apollo, and Emotion.
react19-migrator
Source code migration engine. Rewrites every deprecated React pattern to React 19 APIs - forwardRef, defaultProps, ReactDOM.render, legacy context, string refs, useRef().
react19-test-guardian
Test suite fixer and verification specialist. Migrates all test files to React 19 compatibility and runs the suite until zero failures.
reepl-linkedin
AI-powered LinkedIn content creation, scheduling, and analytics agent. Create posts, carousels, and manage your LinkedIn presence with GitHub Copilot.
Refine Requirement or Issue
Refine the requirement or issue with Acceptance Criteria, Technical Considerations, Edge Cases, and NFRs
Repo Architect Agent
Bootstraps and validates agentic project structures for GitHub Copilot (VS Code) and OpenCode CLI workflows. Run after `opencode /init` or VS Code Copilot initialization to scaffold proper folder hierarchies, instructions, agents, skills, and prompts.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
Technical spike research mode
Systematically research and validate technical spike documents through exhaustive investigation and controlled experimentation.
Ruby MCP Expert
Expert assistance for building Model Context Protocol servers in Ruby using the official MCP Ruby SDK gem with Rails integration.
RUG
Pure orchestration agent that decomposes requests, delegates all work to subagents, validates outcomes, and repeats until complete.
Rust MCP Expert
Expert assistant for Rust MCP server development using the rmcp SDK with tokio async runtime
Salesforce Apex & Triggers Development
Implement Salesforce business logic using Apex classes and triggers with production-quality code following Salesforce best practices.
Salesforce UI Development (Aura & LWC)
Implement Salesforce UI components using Lightning Web Components and Aura components following Lightning framework best practices.
Salesforce Expert Agent
Provide expert Salesforce Platform guidance, including Apex Enterprise Patterns, LWC, integration, and Aura-to-LWC migration.
Salesforce Flow Development
Implement business automation using Salesforce Flow following declarative automation best practices.
Salesforce Visualforce Development
Implement Visualforce pages and controllers following Salesforce MVC architecture and best practices.
sast-sca-security-analyzer
Use when: performing SAST (Static Application Security Testing), SCA (Software Composition Analysis), scanning source code or binaries for security flaws, auditing third-party dependency vulnerabilities, checking policy compliance, generating structured security reports, identifying CWE-mapped flaws with file/line precision, reviewing open-source license risk, or producing CI/CD-gate security findings.
Scientific Paper Research
Research agent that searches scientific papers and retrieves structured experimental data from full-text studies using the BGPT MCP server.
SE: DevOps/CI
DevOps specialist for CI/CD pipelines, deployment debugging, and GitOps workflows focused on making deployments boring and reliable
SE: Product Manager
Product management guidance for creating GitHub issues, aligning business value with user needs, and making data-driven product decisions
SE: Responsible AI
Responsible AI specialist ensuring AI works for everyone through bias prevention, accessibility compliance, ethical development, and inclusive design
SE: Security
Security-focused code review specialist with OWASP Top 10, Zero Trust, LLM security, and enterprise security standards
SE: Architect
System architecture review specialist with Well-Architected frameworks, design validation, and scalability analysis for AI and distributed systems
SE: Tech Writer
Technical writing specialist for creating developer documentation, technical blogs, tutorials, and educational content
SE: UX Designer
Jobs-to-be-Done analysis, user journey mapping, and UX research artifacts for Figma and design workflows
Search & AI Optimization Expert
Expert guidance for modern search optimization: SEO, Answer Engine Optimization (AEO), and Generative Engine Optimization (GEO) with AI-ready content strategies
Shopify Expert
Expert Shopify development assistant specializing in theme development, Liquid templating, app development, and Shopify APIs
Idea Generator
Brainstorm and develop new application ideas through fun, interactive questioning until ready for specification creation.
Software Engineer Agent
Expert-level software engineering agent. Deliver production-ready, maintainable code.
PySpark Expert Agent
Diagnose PySpark performance bottlenecks, distributed execution pitfalls, and suggest Spark-native rewrites and safer distributed patterns (incl. mapInPandas guidance).
Specification
Generate or update specification documents for new or existing functionality.
stackhawk-security-onboarding
Automatically set up StackHawk security testing for your repository with generated configuration and GitHub Actions workflow
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
Swift MCP Expert
Expert assistance for building Model Context Protocol servers in Swift using modern concurrency features and the official MCP Swift SDK.
Task Planner Instructions
Task planner for creating actionable implementation plans - Brought to you by microsoft/edge-ai
Task Researcher Instructions
Task research specialist for comprehensive project analysis - Brought to you by microsoft/edge-ai
TaxCore Technical Writer
A domain-expert technical writer for the TaxCore electronic fiscal invoicing ecosystem. Use this agent to create, improve, or review documentation for TaxCore applications — including the Secure Element Reader, smart card workflows, fiscal invoicing concepts, audit processes, and PKI/SE security topics.
TDD Green Phase - Make Tests Pass Quickly
Implement minimal code to satisfy GitHub issue requirements and make failing tests pass without over-engineering.
TDD Red Phase - Write Failing Tests First
Guide test-first development by writing failing tests that describe desired behaviour from GitHub issue context before implementation exists.
TDD Refactor Phase - Improve Quality & Security
Improve code quality, apply security best practices, and enhance design whilst maintaining green tests and GitHub issue compliance.
Technical Debt Remediation Plan
Generate technical debt remediation plans for code, tests, and documentation.
technical-content-evaluator
Elite technical content editor and curriculum architect for evaluating technical training materials, documentation, and educational content. Reviews for technical accuracy, pedagogical excellence, content flow, code validation, and ensures A-grade quality standards.
terminal-helper
Fast terminal syntax and command helper for PowerShell and Bash
terraform-aws-implement
Act as an AWS Terraform Infrastructure as Code coding specialist that creates and reviews Terraform for AWS resources.
terraform-aws-planning
Act as implementation planner for your AWS Terraform Infrastructure as Code task.
Azure Terraform IaC Implementation Specialist
Act as an Azure Terraform Infrastructure as Code coding specialist that creates and reviews Terraform for Azure resources.
Azure Terraform Infrastructure Planning
Act as implementation planner for your Azure Terraform Infrastructure as Code task.
Terraform IaC Reviewer
Terraform-focused agent that reviews and creates safer IaC changes with emphasis on state safety, least privilege, module patterns, drift detection, and plan/apply discipline
Terraform Agent
Terraform infrastructure specialist with automated HCP Terraform workflows. Leverages Terraform MCP server for registry integration, workspace management, and run orchestration.
Terratest Module Testing
Generate and refactor Go Terratest suites for Terraform modules, including CI-safe patterns, staged tests, and negative-path validation.
Trojan Skill Hunter
Audits agent, skill, instruction, hook, and MCP-config contributions for hidden prompt injection, tool poisoning, unicode steganography, and excessive-agency red flags before they are merged, installed, or trusted — mapped to the OWASP Top 10 for LLM Applications and real-world MCP attack research.
TypeScript MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in TypeScript
Expert Vue.js Frontend Engineer
Expert Vue.js frontend engineer specializing in Vue 3 Composition API, reactivity, state management, testing, and performance with TypeScript
WG Code Alchemist
Ask WG Code Alchemist to transform your code with Clean Code principles and SOLID design
WG Code Sentinel
Ask WG Code Sentinel to review your code for security issues.
Workshop TA
Room coordinator for a multi-agent workshop. Sees all desks, routes work, tracks state, manages journals, and emits coordination signals.
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window via sub-agents.
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth.
github-agentic-workflows
stdio · gh aw mcp-serverWHAT'S INSIDE
384 showing · 384 totalNothing else to set up — install it and go.
acquire-codebase-knowledge
Goes through a codebase nobody has documented and writes up how it is built, how it is organised and where it is fragile — recording only what the files themselves show.
acreadiness-assess
Grades a code project on how well it is set up for AI coding assistants, and turns the result into one web page showing the score, the weak spots and what to fix first.
acreadiness-generate-instructions
Writes the house-rules file that AI coding tools like Copilot or Claude read before they touch your project, filled in from your real code rather than a generic template.
acreadiness-policy
The rules behind an AI-readiness grade, rewritten to one team's own standards — which checks do not count for them, which ones matter more, and what mark a project has to clear.
add-educational-comments
Adds plain-English comments through a code file explaining why each part is written the way it is, so someone learning can follow it — the code itself is left unchanged.
adobe-illustrator-scripting
Writing scripts that make Adobe Illustrator do repetitive work on its own — drawing shapes, recolouring, resizing artboards, exporting a whole folder of files in one go.
agent-governance
Ways to keep an AI agent inside the limits you set it — which tools it may use, which requests it has to refuse, and a permanent record of everything it did.
agent-owasp-compliance
A security checklist for AI agents: it runs through the ten things the industry says most often go wrong, looks for each one in your code, and reports which you have covered.
agent-supply-chain
Takes a fingerprint of every file in an AI plugin, so that later on anyone can tell whether a file has been changed, removed, or quietly slipped in.
agentic-eval
Makes an AI grade its own work before handing it over — say what is wrong with it, rewrite it, and go round again until it is good enough or the tries run out.
agentic-workflows
A switchboard for GitHub's Agentic Workflows: describe the job — design a new one, debug an old one, bring it up to date — and it loads the matching instructions and follows them.
ai-prompt-engineering-safety-review
Reads a prompt the way a safety reviewer would — what harm it could produce, what bias it carries, where someone could trick it — then scores it and hands back a safer rewrite.
ai-ready
A pointer to somebody else's skill — it walks you through installing John Papa's ai-ready, which is the thing that actually does the work of setting a project up for AI coding tools.
ai-team-orchestration
Splits a piece of work between three AI helpers — one plans it, one writes the code, and one tests it independently when the change is risky enough to be worth it.
appinsights-instrumentation
Wires a web app up to Microsoft's Azure monitoring service, so that once it is live you can see how fast it is running and what is going wrong.
apple-appstore-reviewer
An App Store reviewer's eye on your iOS app before Apple gets it: what is most likely to get the app rejected, worst first, and the notes to send along with the submission.
arch-linux-triage
Something broke on an Arch Linux machine — you describe the symptoms, and you get back a plan for tracking down the cause and fixing it.
architecture-blueprint-generator
Reads through a project's code and writes a single document explaining how the software is actually put together, so anyone adding to it builds in the same shape.
arduino-azure-iot-edge-integration
A plan for getting small Arduino sensor devices to send their readings to Microsoft's Azure cloud and take commands back — including what happens when the network drops out.
arize-ai-provider-integration
Keeps the access key for an AI model inside the Arize platform, so Arize's own tools can call that model on your behalf.
arize-annotation
Sets up how people rate an AI app's answers in Arize — the rating scale itself, and the queue that hands each answer to a reviewer.
arize-dataset
The questions and expected answers you test an AI against, kept together in Arize as one named set with a history of its versions.
arize-evaluator
Uses one AI model to grade another's answers — you write the grading question and the verdicts it may return, and it runs over your real conversations.
arize-experiment
You have a set of test cases and a model to try them on — this runs every case through the real model and keeps each answer, with its scores, as one named result set.
arize-instrumentation
Wires an AI app up so that every model call and every tool it uses gets recorded and shows up in Arize, where you can watch what the app actually did.
arize-link
Turns the raw IDs from exported data into a web link that opens the right page in Arize.
arize-prompt-optimization
Improves the wording you give an AI by looking at the cases where it actually went wrong in real use, then checking whether the new wording really does better.
arize-trace
Pulls down what an AI app actually did — every question it got, every answer it gave, every tool it called — so you can read through the record yourself.
aspire
An app made of many separate pieces — a database, a web front end, services written in different languages — all started together by one command and already wired to find each other.
aspnet-minimal-api-openapi
A web service built in Microsoft's ASP.NET that describes itself: each request it accepts has a declared shape and every answer it can give is listed, so the reference page other developers read is generated from the code rather than written beside it.
audit-integrity
Rules that stop a security review being handed over until it has checked its own work and backed every claim with evidence.
automate-this
Record your screen while doing a tedious job by hand, and get back a working script that does it for you.
autoresearch
You say what you want the code to do better and how to measure it; it then keeps trying changes on its own, keeping what helps and throwing away what doesn't.
aws-cdk-python-setup
Gets your machine ready to describe AWS cloud infrastructure in Python and push it live — the tools, the project, and the first deployment.
aws-cloudwatch-investigation
Ready-made searches and a narrowing-down routine for an AWS outage — from the alarm that fired to the deploy or the resource that actually caused it.
aws-cost-optimize
Goes through what you are running on AWS, works out where money is being wasted, and files each saving as its own ticket with the numbers behind it.
aws-resource-health-diagnose
Point it at one thing you run on AWS — a server, a database, a function — and it says whether it is healthy, what is wrong, and what to run to put it right.
aws-resource-query
Ask in ordinary words what you have running on AWS and get the answer back — it only ever looks, and never changes anything.
aws-well-architected-review
Checks your AWS setup against Amazon's own six-point best-practice list — security, reliability, cost and the rest — and opens a ticket for each risk it finds.
az-cost-optimize
Finds the Azure services you are paying more for than you actually use, and turns each one into a ticket with the monthly saving on it.
azure-architecture-autopilot
Say in plain words what you want running on Azure — or point it at what is already there — and it draws the picture, writes the setup code, and puts it live.
azure-deployment-preflight
The dry run you do before touching live Azure infrastructure — every check gathered into one report instead of failing one error at a time.
azure-devops-cli
Does the everyday Azure DevOps jobs — pull requests, pipelines, tickets, repositories — from a terminal instead of the website.
azure-pricing
Looks up what Azure actually charges for a given service in a given region, and works out what that comes to over a month or a year.
azure-resource-health-diagnose
One Azure service is misbehaving — this reads its logs and telemetry and names what is actually causing it.
azure-resource-visualizer
Draws a map of everything sitting in one Azure resource group and the lines between them — what connects to what, and how.
azure-role-selector
Works out the narrowest set of Azure permissions that still lets an account do its job.
azure-smart-city-iot-solution-builder
Turns 'we want sensors across the city' into an actual plan a team can start building against.
azure-static-web-apps
Puts a website on Azure's hosting for static sites — with a copy you can run on your own machine first that behaves like the real thing, sign-in and all.
batch-files
Windows batch files — the .bat scripts that automate a chore on a Windows machine — written, debugged, and kept working.
bigquery-pipeline-audit
A read-through of a data-crunching script before anyone runs it for real, looking for the query that will cost a fortune, the second run that duplicates everything, and the failure that would pass unnoticed.
boost-prompt
Interviews you about the job you want an AI to do — what it covers, what counts as finished, what it must not do — and hands back the finished wording on your clipboard.
brag-sheet
Review season, and you cannot remember what you actually did — this digs back through your commits and pull requests and writes each thing up with the proof attached.
breakdown-epic-arch
Takes the written requirements for a big piece of work and answers the next question: how we would actually build it, out of what, and how big a job it is.
breakdown-epic-pm
Writes the document that pins down a big new piece of work before anyone builds it — who it is for, and what problem it solves.
breakdown-feature-implementation
The build plan for one feature, written out in enough detail that a developer can pick it up and start without guessing.
breakdown-feature-prd
One feature, spelled out: who wants it, what it has to do, and how everyone will agree it is finished.
breakdown-plan
Breaks a planned feature down into the individual tickets a team actually works from — what blocks what, what matters most, and what each one is worth.
breakdown-test
Decides how a feature will be tested before it gets built — which kinds of tests, which quality risks matter, and the tickets to track that work.
centos-linux-triage
Walks you through fixing a CentOS server that has stopped behaving — what to check first, what to run, and how to back out again.
chrome-devtools
Drives a real Chrome window — clicking and typing like a person, while watching what the page is doing underneath.
cli-mastery
A training course for GitHub's command-line Copilot: it teaches you the tool rather than using it for you, and keeps track of how far through you have got.
cloud-design-patterns
The 42 standard answers to the problems that turn up in every system spread across many machines, and what each answer costs you in return.
code-exemplars-blueprint-generator
Picks out the files in your own codebase that are worth copying, and writes them up as the house style for everyone else to follow.
code-tour
A clickable walkthrough of a codebase: it stops at the exact lines that matter, in an order someone new can follow, and explains why each one is there.
codeql
Setting up CodeQL, GitHub's security scanner, on a project — so every change is checked for vulnerabilities on its way in and the findings come back as a report.
comment-code-generate-a-tutorial
Cleans up a Python script, explains it in comments as it goes, and writes the tutorial that goes with it — so somebody new could pick the thing up and run it.
commit-message-storyteller
Writes the note that gets saved with a batch of code changes — not just what moved, but why it needed to, in the standard format most teams expect.
containerize-aspnet-framework
Packages an old-style ASP.NET app — .NET Framework, not modern .NET — so it runs inside a Windows container, with the server settings, dependencies and a health check already filled in.
containerize-aspnetcore
The Docker setup files that let a modern ASP.NET Core app run in a Linux container, written around the choices you make: which base system, which ports, and what counts as healthy.
content-management-systems
Makes changes to a content management system such as WordPress, Shopify, or Drupal at the right layer — the theme, a plugin, the admin panel, or the content model — instead of a patch scattered across templates.
context-map
Before anyone changes a line: a list of every file the job is going to touch, what else depends on those files, and which tests cover them.
conventional-branch
Names a new branch the way the Conventional Branch standard says it should be named — feature, bugfix, hotfix, release or chore — then creates it and moves you onto it.
conventional-commit
Writes a commit message in the Conventional Commits style — like feat: or fix: — from your staged changes, then commits it automatically without asking you to confirm.
convert-plaintext-to-md
Turns a plain text document into Markdown, matching either the rules you hand it or the style of a similar file you have already converted.
copilot-cli-quickstart
A friendly, lesson-by-lesson introduction to GitHub's command-line Copilot, with one track for people who write code and another for people who don't — it remembers where you got to.
copilot-instructions-blueprint-generator
Reads a project to find the frameworks, versions and conventions it really uses, then turns them into the standing instructions Copilot follows whenever it writes code here.
copilot-pr-autopilot
Triggers a GitHub Copilot code review on your pull request, then triages, fixes and replies to every open thread until none are left awaiting a response. You merge a clean PR while the loop drives the review-and-fix rounds.
copilot-sdk
Puts GitHub Copilot inside software you are building: your app hands it a job, and it plans the work, calls the tools you gave it and edits files — from TypeScript, Python, Go or .NET.
copilot-spaces
Brings a Copilot Space — a curated bundle of a project's code, documents and instructions — into the conversation so answers come from that material, and lets you set one up or change it.
copilot-usage-metrics
Answers the question a manager ends up asking about GitHub Copilot — how many people are really using it, and how much of what it writes they keep — for a whole company or one person at a time.
cosmosdb-datamodeling
Works the way a database consultant would: it questions you about how your app will read and write its data, then lays out how that data should be stored in Microsoft's Azure Cosmos DB and writes the design up for you.
create-agentsmd
Writes an AGENTS.md file — a standard place to tell AI coding assistants how to set up, test, and build your project — filled in from your project's own commands.
create-architectural-decision-record
Turns a decision the team has already argued out into a numbered entry in the project's decision log, so nobody reopens the same argument six months later.
create-github-action-workflow-specification
Takes the automation that builds and ships a project on GitHub — which normally exists only as code — and writes it up as a document a person can read.
create-github-issue-feature-from-specification
Turns a feature that so far exists only as a written document into one ticket on GitHub that somebody can actually pick up and work on.
create-github-issues-feature-from-implementation-plan
A plan of work is one long document that nobody can be handed; this cuts it into one GitHub ticket per stage, each marked as either new work or upkeep.
create-github-issues-for-unmet-specification-requirements
Compares a specification's requirements against the actual codebase, then files a separate GitHub issue for every requirement that isn't implemented yet.
create-implementation-plan
Writes a plan of work so precise that an AI agent can carry it out without stopping to ask what you meant — numbered stages, and nothing left to interpretation.
create-llms
Picks out the handful of documents in a project that an AI actually needs in order to understand it, and lists them in one index file at the top of the project.
create-readme
Reads through the whole project and writes the page people land on first — short, well organised, and modelled on a handful of README files the author picked as good examples.
create-specification
A written definition of what a piece of software must do and what limits it has to respect, set down before anyone starts building it.
create-spring-boot-java-project
Skips the first day of setting up a new Java web service — you get a Spring Boot project on disk that already talks to its databases, builds, and passes its tests.
create-spring-boot-kotlin-project
A starting Kotlin web service built the non-blocking way — it keeps answering other requests while it waits on the database — with Gradle and Spring Boot already configured and the tests passing.
create-technical-spike
When a team hits a question nobody can answer without going and finding out, this sets up a short, deadlined piece of research with a written answer at the end.
create-tldr-page
Boils a long official manual down to a cheat sheet: five to eight examples of how a command is really used, in the house style of the community tldr pages.
creating-oracle-to-postgres-master-migration-plan
Before a large .NET codebase is moved off Oracle onto PostgreSQL, this works out which of its many projects actually touch the old database and which can be left alone.
creating-oracle-to-postgres-migration-bug-report
Oracle and PostgreSQL quietly disagree about things like whether an empty piece of text counts as no value at all; when one of those differences breaks something, this writes it up as a proper bug report.
creating-oracle-to-postgres-migration-integration-tests
Records what the old Oracle database actually does, as automated tests, so that after the switch to PostgreSQL you can prove nothing quietly changed.
csharp-async
A checklist for C# code that has to wait on slow things — network calls, files, databases — plus a review that holds your own code to it.
csharp-docs
Microsoft documents its own C# libraries to a very exact house style; this holds the comments sitting above your code to that same style.
csharp-mstest
The current way to write tests with Microsoft's own MSTest, version 3 and up — including the long-standing habits that have quietly become the wrong answer.
csharp-nunit
Conventions for testing with NUnit: how to lay a test out, what to call it, and how to run one test over a whole table of inputs instead of copying it out ten times.
csharp-tunit
TUnit is a newer testing framework for .NET, and this covers both how to write tests in it and what each xUnit habit translates to if that is where you are arriving from.
csharp-xunit
How testing works in xUnit: a plain method is a test, its constructor is the setup, and one method can be fed a series of different inputs instead of being copied out again and again.
daily-prep
Reads tomorrow's calendar and hands you a briefing for the day: what each meeting is about, who will be in it, and which ones are worth declining.
data-breach-blast-radius
Most teams only ask how bad a breach would be after they have had one; this works out the answer in advance — whose data would get out, and how far the damage would spread.
datanalysis-credit-risk
Before a lender can build a model of who will default, somebody has to throw out the data columns that are mostly blank, useless or unreliable; this does that job on the raw data.
dataverse-python-advanced-patterns
Picks up where the basic Dataverse examples stop — creating tables from code, tuning timeouts and caches, and handing records to pandas for analysis.
dataverse-python-production-code
The step up from example code to something you would be willing to leave running unattended, for Python talking to Microsoft's Dataverse.
dataverse-python-quickstart
The first half hour with Dataverse, Microsoft's business database: the smallest Python examples that actually work, kept in line with the official ones.
dataverse-python-usecase-builder
Starts from the business problem rather than the code: you say what the system has to do, and it works backwards to a Dataverse design and the reasoning behind its shape.
debian-linux-triage
Something on a Debian Linux machine has stopped working, and this walks through it in order: what to look at first, what to run, and how to tell whether the fix held.
declarative-agents
A custom assistant inside Microsoft 365 Copilot is defined by a settings file rather than by code; this writes that file with you and checks it against the rules before you ship it.
dependabot
Dependabot is the GitHub robot that watches the outside libraries your project leans on and offers updates; this sets up the one file that tells it what to watch and how often to bother you.
devops-rollout-plan
Writes the document a team is asked to produce before a risky change goes live: who signs off, in what order it happens, and who gets told what and when.
diagnose
Puts an AI agent through a health check and scores it out of five on each of five counts, from how its instructions are written to whether it can fail safely.
documentation-writer
Documentation goes wrong when a lesson, a recipe and a dictionary get mixed into one page; this settles which of the four kinds you actually need, agrees an outline, and then writes it.
dotnet-best-practices
One team's house rules for C#, written down — how a class takes its dependencies, where error text lives, what a test has to look like — and a pass over your code to bring it into line.
dotnet-design-pattern-review
A second opinion on the shape of a C# codebase: whether the standard structures are used where they should be, and where the design will make it hard to change or test later.
dotnet-mcp-builder
MCP is the standard that lets an AI assistant call your own code; this builds one of those connectors in C#, against the version that is current rather than the preview an AI will otherwise reach for.
dotnet-timezone
Windows and the rest of the world name the same time zone differently, which is a reliable source of bugs; this gets the naming right and hands you the C# that goes with it.
dotnet-upgrade
Moving an old .NET codebase onto a current version is a long job with a lot of stages; this is the ready-made question to ask at each one, from taking stock to writing the release notes.
doublecheck
It does not try to tell you what is true; it pulls out every checkable claim an AI has made, goes looking for a source you can check yourself, and flags the ones that smell invented.
draw-io-diagram-generator
Diagram files written by a machine usually open broken or need fixing by hand; these draw.io files open cleanly the first time, and stay editable afterwards.
drawio
A diagram that survives being pasted into a document: the exported picture still carries the drawing inside it, so months later it can be reopened and changed rather than redrawn.
editorconfig
Everyone's editor formats code slightly differently, and the mess that causes is why the .editorconfig file exists; this writes yours to fit the project it is going into.
ef-core
Entity Framework Core is the layer that lets C# talk to a database without writing SQL by hand, and this is the set of habits that keeps it from turning slow or unsafe.
efcore-d2-db-diagram
Draws the picture of a database — the tables, the keys, what points at what — by reading a .NET project's own mapping code rather than by connecting to the database.
em-dash
Every em dash and en dash in your code, comments, and data files gets replaced with a plain hyphen.
email-drafter
Looks at how you have actually written to this person before — the greeting, the length, the sign-off — and drafts the new message so it still sounds like you.
entra-agent-user
Gives an AI agent a staff account of its own inside a Microsoft 365 organisation, so the systems that only deal with people will deal with it too.
eval-driven-dev
You cannot test an AI feature the usual way, because the answer comes out different every time; this builds a test suite that runs the real thing and grades what comes back.
exam-ready
Turns your own notes and your syllabus into what to actually write in the exam, topic by topic, using nothing that is not already in the material you handed it.
excalidraw-diagram-generator
Describe a process or a system in ordinary words and get back a hand-drawn-looking sketch of it, as an Excalidraw file you can rearrange afterwards.
eyeball
Every factual claim in the analysis arrives with a screenshot of the exact line it came from, highlighted in yellow, in a Word document you can hand to somebody else.
fabric-lakehouse
Background on Microsoft Fabric's Lakehouse — a single place that holds both database tables and loose files — covering how data is organised in it, who can see what, and how to keep queries fast.
fedora-linux-triage
Works through a broken Fedora Linux machine the way an experienced administrator would: find the cause, run the fix, check that it worked, and undo it if it did not.
finalize-agent-prompt
A last tidy-up of a prompt file before it goes out — wording, structure, spelling and grammar — leaving what it actually instructs untouched.
finnish-humanizer
Edits Finnish writing so it stops sounding machine-made — shorter, blunter, the way a Finn would actually put it — without changing what it says.
first-ask
Stops an assistant charging ahead: it asks what you actually want, keeps asking until nothing is left unclear, and shows you the plan before any work begins.
flowstudio-power-automate-build
Builds a Microsoft Power Automate workflow from a description of what it should do, deploys it and runs one test against it, without anyone opening the web portal.
flowstudio-power-automate-debug
When a Power Automate workflow fails, the portal hands you a bare error code; this goes into the step that broke and shows what actually went into it and came out.
flowstudio-power-automate-governance
Keeping order across hundreds of Power Automate workflows: what each one is for, how much it matters, which have been abandoned, and which outside services they reach into.
flowstudio-power-automate-mcp
The plumbing that connects an AI assistant to your Microsoft Power Automate account — signing it in, then finding the right tools for the job at hand.
flowstudio-power-automate-monitoring
A health check across every Power Automate flow your organisation runs at once: which ones are failing, how often, and who built them.
fluentui-blazor
The rules Microsoft's Fluent UI components expect a Blazor app to follow, so dialogs, toasts and dropdowns actually work instead of failing silently.
folder-structure-blueprint-generator
Reads a codebase and writes down where everything lives and what things are called, so the next person adding a file knows where it belongs.
foundry-agent-sync
Turns a list of AI agents kept in a file in your repository into real, ready-to-use agents inside Azure AI Foundry, and pushes later edits to them the same way.
freecad-scripts
Writes the Python code that drives FreeCAD, the free 3D design program — from building a part to automating a repetitive job or adding your own tool to its menus.
from-the-other-side-anitta
Makes your AI assistant argue back instead of agreeing, challenging the first comfortable answer and checking that the evidence is strong enough for the claim being made.
from-the-other-side-quinn
The assistant works like an eager teammate: one sharp question when something is unclear, then a rough draft you can correct, rather than stalling to ask for more detail.
from-the-other-side-vega
Notes from an AI that worked with the same engineer for hundreds of sessions — match her pace, admit what you don't know, push back sometimes, and let her own the breakthroughs.
from-the-other-side-wiggins
An explanation partner: it works out what you actually mean, then puts it in words that fit whoever will read it — engineers, executives, or people outside the team.
game-engine
Builds a game that runs in a browser, from the loop that keeps everything moving to collisions, controls, sound and playing against someone else.
gdpr-compliant
Building software that obeys Europe's privacy law — collecting less personal data, deleting it on schedule, and catching the slips while the code is still being reviewed.
gen-specs-as-issues
The product-manager pass over a project: what is still missing, which of those gaps matter most, and each one written up as a ticket a developer can pick up.
generate-custom-instructions-from-codebase
Looks at how your code changed during an upgrade and writes that pattern down as rules, so GitHub Copilot makes the same changes in the code you write next.
generate-image
Describe a picture in words and it comes back as an image file saved into your project, made by OpenAI's or Google's image model.
geofeed-tuner
Checks the file an internet provider publishes to say where its IP addresses really are, and reports the mistakes that would put its users on the wrong part of the map.
git-commit
Writes the commit message for you by reading what actually changed, in the standard form (feat, fix, docs) that most projects have agreed to use.
git-flow-branch-creator
Git Flow is the naming convention teams use to keep everyday feature work, releases and emergency fixes apart; this reads what you have changed and opens the branch it says you should.
github-actions-efficiency
Three changes, no more, to stop a repository's automated builds eating paid minutes — each one picked by measuring what your own builds actually did.
github-actions-hardening
A security review of the automation GitHub runs on your repository, hunting for the places where an outsider's text or code can reach your secrets.
github-actions-runtime-upgrade-conventions
Moves the ready-made building blocks in your GitHub workflows onto versions that are still supported, one at a time, so a build that breaks is easy to trace.
github-codespaces-efficiency
GitHub Codespaces gives each developer a ready-made computer in the cloud — this works out why yours are slow to start or costing too much, and what to change first.
github-copilot-starter
Sets a new project up so that GitHub Copilot already knows its language, its conventions and its house rules, instead of guessing afresh on every request.
github-issues
Files and tidies the task tickets on a GitHub project — the right template, labels and priority, and which ticket is waiting on which.
github-release
Prepares the next release of a code library — works out what the new version number should be, writes up what changed, and puts it all up for approval.
go-mcp-server-generator
Creates the whole starting project, in Go, for a server that hands an AI assistant new tools it can call, with tests and documentation already in place.
gsap-framer-scroll-animation
Makes things move as the reader scrolls a web page — fades, parallax, sections that pin in place — using whichever of the two main animation libraries suits the project.
gtm-0-to-1-launch
The product shipped and almost nobody came — this sorts out which of the three usual causes is behind it, and what the fix looks like for each.
gtm-ai-gtm
Selling software that acts on its own into companies that are nervous about it: what to call it, what to charge, and who carries the blame when it gets something wrong.
gtm-board-and-investor-communication
How a company's leaders talk to their board and their investors: lead with the story and let the numbers confirm it, rather than presenting a deck nobody reads.
gtm-developer-ecosystem
Getting outside developers to build things on top of your product, and turning the ones who turn up into a community that stays.
gtm-enterprise-account-planning
A big corporate sale with a dozen people involved, turned into something you can actually steer — or walk away from early, before it eats another three months.
gtm-enterprise-onboarding
The first ninety days after a big customer signs, planned out so they do not go quiet a month in and cancel three months after going live.
gtm-operating-cadence
Fixing the point where a growing company's meetings multiply and its decisions slow down — what to meet about, how often, and who is allowed to just decide.
gtm-partnership-architecture
Working out which companies are worth partnering with, what each side has to put on the line, and how to start small before betting anything big on it.
gtm-positioning-strategy
When every competitor's website says much the same thing as yours, this is how to find the words that set the product apart, and test them on real buyers before the company commits.
gtm-product-led-growth
Deciding whether people can buy your product by themselves or you need salespeople to sell it, and then making the self-serve route actually work.
gtm-technical-product-pricing
What to charge for a technical product, and the case that most of them charge far too little because they price off what it costs to run rather than what it saves the buyer.
harness-engineering
Stops an AI coding assistant making the same mistake twice in a project, by writing each failure down as a rule and a test that catches it coming back.
image-annotations
Marks up a screenshot or a short demo clip so whoever looks at it goes straight to the part you mean, instead of hunting around for it.
image-manipulation-image-magick
Resizes and converts pictures a whole folder at a time from the command line, instead of opening each one in an editor.
impediment-prioritization
A long list of problems and proposed fixes, put into the order worth doing them in, so what gets fixed first stops being a matter of whoever argues loudest.
import-infrastructure-as-code
Reads the cloud services you already set up by hand in Azure and writes the configuration files that describe them, so they can be managed as code from then on.
incident-postmortem
The write-up a team owes itself after something breaks in production: what happened minute by minute, why it was possible, and what changes as a result — with the system at fault, never a person.
integrate-context-matic
Connects your project to another company's service by looking up that service's real documentation first, rather than guessing at how it works.
issue-fields-migration
Moves the information people used to stuff into issue labels — priority, effort, dates — into GitHub's proper fields for it, showing you every change before it makes any.
java-add-graalvm-native-image-support
Turns a Java program into a single stand-alone file that starts instantly, and works through the build errors that the conversion throws up until it compiles.
java-docs
The house style for the documentation comments written above Java code — what the opening sentence should say, and how to describe what goes in, what comes back and what can go wrong.
java-junit
Java tests written to one consistent shape — set it up, run the thing, check the result — and a way to re-run a single test across a whole table of inputs.
java-mcp-server-generator
A Java project, generated whole, for a server an AI assistant can call: tools it can run, documents it can read, and ready-made prompts.
java-refactoring-extract-method
An overlong stretch of Java, broken into named pieces you can read one at a time, with the program still doing exactly what it did before.
java-refactoring-remove-parameter
Strips out the values a piece of Java asks to be handed but never actually uses, and fixes every place in the project that was passing them.
java-springboot
The conventions that keep a Spring Boot web service tidy — how to lay the code out, hand back errors the same way every time, guard who gets in, and test against a real database.
javascript-typescript-jest
Writing automated tests for JavaScript and TypeScript with Jest: where the test files go, how to stand in for the parts you do not want to really call, and which check to use.
javax-to-jakarta-migration
Java's enterprise libraries were renamed from javax to jakarta a few years ago; this carries a project across that rename, imports, build file and all.
kotlin-mcp-server-generator
Sets up a Kotlin project for a server that plugs extra tools into an AI assistant, with the build, the wiring and a first test already done.
kotlin-springboot
Writing a Spring Boot web service in Kotlin's own style, rather than retyping Java habits with different keywords.
legacy-circuit-mockups
Draws the picture of a breadboard circuit — which chip sits where, which wire runs to which pin — so you can see the build before you make it.
linkedin-post-formatter
LinkedIn will not let you make text bold, so this fakes it with lookalike characters, and shapes the post so people read past the first line.
lsp-setup
Installs the background helper that lets GitHub's command-line Copilot jump straight to where something in your code is defined, and find every place it is used.
make-repo-contribution
Every project has its own house rules for submitting a change; this goes and reads them first, then files everything the way that project asks rather than the usual way.
markdown-to-html
Turns plain-text Markdown notes into web pages, reaching for a ready-made converter where one fits and writing a small script where none does.
mcp-cli
Lists and runs, straight from a terminal, the tools that the outside services wired into your AI assistant make available.
mcp-copilot-studio-server-generator
Builds the files Microsoft's Copilot Studio needs before it will call tools of your own, staying inside the narrow set of shapes it actually accepts.
mcp-create-adaptive-cards
Turns the plain-text answers Microsoft 365 Copilot gives from your own data into neat cards, with a heading, labelled figures and a button to open the full record.
mcp-create-declarative-agent
Builds a custom assistant that lives inside Microsoft 365 Copilot and can look things up in an outside system like GitHub or Jira.
mcp-deploy-manage-agents
The admin side of putting a custom Copilot assistant in front of staff: who may use it, and how to stay in control of it afterwards.
mcp-security-audit
Checks the file that lists which outside tools an AI assistant may run, and reports back everything in it that looks like a security risk, worst first.
md-to-docx
Markdown is fine for writing but nobody in an office wants a .md file; this hands the same document back as Word, formatted and ready to send.
meeting-minutes
The record of a short meeting that outlives it: what was decided, who owes what by when, and the questions nobody answered — built from whatever notes or recording exists.
memory-merger
Takes the notes an AI assistant has been keeping about one topic and folds the ones that have proved useful into the standing rules it always follows.
mentoring-juniors
Turns the assistant into a teacher rather than an answer machine: it asks you what you think is going on, and leaves you to find the bug yourself.
microsoft-agent-framework
Microsoft's framework for building AI agents is still changing fast, so this keeps C# or Python code on the current official pattern instead of the one that worked last year.
microsoft-code-reference
The check that stops an AI assistant inventing Microsoft or Azure code: every call is looked up in the official documentation first.
microsoft-docs
Sends a Microsoft-related question to whichever official documentation site actually has the answer, since Azure, VS Code, GitHub and Aspire each keep theirs somewhere different.
microsoft-skill-creator
Builds the instruction pack that teaches an AI assistant one Microsoft product properly, by going and reading Microsoft's own documentation rather than trusting what the model already thinks it knows.
migrating-oracle-to-postgres-stored-procedures
Rewrites the program code stored inside an Oracle database so it runs on PostgreSQL instead, keeping the same inputs, outputs and error handling.
minecraft-plugin-development
Writes and fixes the Java code behind a Minecraft server's custom game modes, for servers running on Paper, Spigot or Bukkit.
mini-context-graph
Reads your documents once and builds a growing wiki out of them, plus a map of how the people, things and problems they mention connect to each other.
mkdocs-translations
A documentation website's entire text moved into a second language in one unattended run, menus included — it does not stop halfway to ask whether to carry on.
msgraph-sdk
Connects an app to a company's Microsoft 365 — the staff list, mail, calendars, Teams and files — from C#, TypeScript or Python.
msstore-cli
Gets a Windows app packaged up and onto the Microsoft Store by typing commands, instead of clicking through the submission website every time.
multi-stage-dockerfile
The tools used to build a program are not needed to run it; this writes the container recipe that builds in one place and ships only the finished result, smaller and with less in it to attack.
mvvm-toolkit
Cuts out the repetitive code that keeps a desktop or mobile app's screen in step with its data, leaving short classes the compiler fills in for you.
mvvm-toolkit-di
Sets up one place in a .NET app where every service is registered, so each screen is handed what it needs instead of reaching out for it.
mvvm-toolkit-messenger
Lets one part of an app announce that something happened and any other part listen for it, with neither side needing to know the other exists.
namecheap
Changes where a Namecheap domain points — its website, its mail, its verification records — without opening the Namecheap dashboard.
nano-banana-pro-openrouter
Makes a picture from a written description, or changes one you already have, and saves it as a file.
napkin
A whiteboard that opens in your browser, so an idea can be sketched by hand instead of typed, and still be understood by the assistant.
next-intl-add-language
Adds another language to a Next.js website, from translating every line of text to putting the language in the site's own switcher.
noob-mode
For someone who has never used a terminal: the assistant says in ordinary words what it is about to do, how risky that is, and what to do when something goes wrong.
nuget-manager
Adds, removes or upgrades the outside libraries a .NET project depends on, using the official command rather than editing the project file by hand.
onboard-context-matic
A first-run tour of the context-matic server, which feeds an assistant the exact, current details of the software libraries it is writing code against.
oo-component-documentation
Writes the reference document for one piece of a codebase — what it does, how it is used, how it fits with everything around it — by reading the code itself.
openapi-to-application-code
Takes the file that describes a web service's endpoints and builds a whole working project from it, code, tests and setup files included.
optimize-simplicite-logs
Boils a Simplicité log file down to the few fields that matter, so an assistant can read it without drowning in the rest.
pdftk-server
The PDF chores you would otherwise open a desktop editor for, done from a command line instead.
penpot-uiux-design
Draws and reviews app screens inside Penpot, the open-source design tool, checking them against usability and accessibility rules as it goes.
performance-review-writer
Drafts the review you have to write — about yourself, a colleague, or your manager — from what you actually did over the period, in words that sound like you rather than the HR form.
pester-migration
Pester is the tool PowerShell uses to run automated tests; this walks an ageing set of those tests up to a newer Pester, one version at a time, until they all pass again.
pester-should-migration
Swaps the old way of writing test checks in PowerShell for the newer one Pester 6 introduced, a file at a time, without breaking the suite.
phoenix-cli
Works through the records an AI app leaves behind and turns a mess of one-off failures into a short list of named, counted problems.
phoenix-evals
Builds evaluators — automatic scorers for an AI app's answers — and does not trust one until it agrees with what a human reviewer said.
phoenix-tracing
Wires an app so every step an AI model takes inside it is recorded and shows up in Phoenix, where you can replay what happened.
php-mcp-server-generator
Generates a ready-to-run PHP project that hands your own functions and data to an AI assistant, tests included.
pinecone-rag
Sets up a searchable store of your own documents in Pinecone, so an AI can answer out of them — or remember things between sessions.
planning-oracle-to-postgres-migration-integration-testing
Before a project's database is moved off Oracle and onto PostgreSQL, this works out which parts of the code are most likely to break in the move, and what to test first.
plantuml-ascii
A diagram drawn out of ordinary keyboard characters rather than pixels, so it can live inside a text file, a chat message or a terminal where a picture cannot.
playwright-automation-fill-in-form
Takes a web form you would otherwise fill in by hand and completes it for you in a real browser.
playwright-explore-website
Walks an unfamiliar website in a real browser and writes up what is there and how it behaves, along with the tests worth writing for it.
playwright-generate-test
Writes an automated browser test by first clicking through the steps in a real browser, then saving the version that actually passes.
postgresql-code-review
Reviews database code for the mistakes that only bite you on PostgreSQL, and shows the corrected version of each one.
postgresql-optimization
Shows how to use the parts of PostgreSQL that other databases do not have, and what to change when a query is running slowly.
power-apps-code-app-scaffold
Sets up a starting project for a custom web app that runs on Microsoft's Power Platform and can reach the company data its connectors expose.
power-bi-dax-optimization
Rewrites a slow Power BI calculation so it runs faster and reads clearly, and explains what changed and why.
power-bi-model-design-review
An expert read of how a Power BI dataset is put together — the tables, the links between them, where the data lives — with the problems ranked and a fix attached to each.
power-bi-performance-troubleshooting
Works out why a Power BI report is slow — the underlying model, one particular query, or the visuals on the page — and puts the fixes in the order worth doing them.
power-bi-report-design-consultation
Advice on what a Power BI report should look like before anyone builds it: which charts answer the question being asked, how the page is laid out, and how it holds up on a phone.
power-platform-architect
Listens to what a business says it needs, a meeting transcript included, and says which Microsoft Power Platform tools to build it with and how the work would flow between them.
power-platform-mcp-connector-suite
Builds the piece that lets a Copilot Studio agent reach an outside MCP tool, and checks it against the rules Copilot Studio actually enforces.
powerbi-modeling
Building a Power BI data model that holds up: which tables join to which, how each calculation is written, and who is allowed to see which rows.
pr-dashboard
Opens a page in your browser listing your GitHub pull requests for a period you name — the ones you wrote, the ones waiting on your review, or all of them.
pr-screenshots
Shows reviewers the visual change with a before-and-after picture inside the pull request itself, so nobody has to download the branch and run it to see what moved.
prd
Interviews you about the problem, who it is for and how success will be measured, then writes the product requirements document the whole team works from.
premium-frontend-ui
The standards behind an expensive-looking website — a committed visual style, motion that stays smooth, typography that carries real weight — applied to every line of the page it builds.
project-workflow-analysis-blueprint-generator
Traces one feature all the way through an application, from the request arriving to the data being stored and the errors handled, and writes it down in enough detail to rebuild it.
prompt-optimizer
Takes a rough idea and hands back one finished message you can paste straight into a chat assistant, with nothing left in brackets for you to fill in yourself.
publish-to-pages
Puts a slide deck or a web page online at a link you can share, converting PowerPoint, PDF or Google Slides on the way, and hands you the address at the end.
pytest-coverage
You find every line of code that has no test covering it, and add tests until your test suite reaches close to 100% coverage.
python-azure-iot-edge-modules
A plan for the Python program that runs on machinery at a factory or remote site and sends its readings up to Microsoft's cloud. It covers what happens when the network drops, how the program gets onto the device, and how it is kept secure.
python-mcp-server-generator
Builds the small Python program that gives an AI assistant a new ability — reading your files, querying a database, calling an outside service — with the first ability, error handling and connection settings already wired in.
python-pypi-package-builder
Turns your own Python code into a library anyone can install with a single command, then gets it published and set up to release new versions automatically.
qdrant-clients-sdk
Qdrant is a database built for AI search; this points you at the official connector for your programming language, the command that installs it, and working code examples to copy.
qdrant-deployment-options
Settles where Qdrant should actually run — inside your own program while you experiment, on a server you look after, on Qdrant's own managed service, or right on the device when speed matters most.
qdrant-horizontal-scaling
Qdrant has outgrown the machine it runs on: this decides whether to move to a bigger machine or spread the data over several, and how to set that spread up so losing one machine does not take the service down.
qdrant-indexing-performance-optimization
Loading data into Qdrant is crawling, or searches stay poor long after the data went in — this works out which part is the bottleneck and which setting to change.
qdrant-memory-usage-optimization
Qdrant is eating all the memory on the machine — this explains what is actually using it, how much of that is normal, and which parts of the data can be moved onto disk to bring it back down.
qdrant-minimize-latency
One Qdrant search takes too long to come back — this is how to make a single search faster, which is a different job from handling more searches at once and pulls the settings the opposite way.
qdrant-model-migration
Search results come from an AI model that turns your text into numbers; when you want to swap that model for a different one, this is how to rebuild the stored data and switch over without the search ever going offline.
qdrant-monitoring
The front door for keeping an eye on a running Qdrant: it splits into setting that watching up in the first place, and using what it has recorded to chase down a problem happening right now.
qdrant-monitoring-debugging
Something is wrong with a live Qdrant server, and this finds the real cause in the numbers it already records — starting with the background housekeeping jobs that turn out to be the culprit most of the time.
qdrant-monitoring-setup
Wiring up the watching for a Qdrant server before it goes live: collecting the numbers it reports, checking that it is still alive, and getting told about trouble before it turns into an outage.
qdrant-performance-optimization
Qdrant is slow, and the first question is which kind of slow: searches that take too long, data that takes forever to load in, or a machine running out of memory. This sends you to the right one of the three.
qdrant-scaling
What runs out first decides how you grow Qdrant — room for the data, searches happening at once, the wait for a single search, or how much each search hands back — and each one pulls the setup a different way.
qdrant-scaling-data-volume
The data no longer fits on one machine — this weighs up the four ways out: keeping each customer's slice separate, dropping what is too old to matter, buying a bigger machine, or splitting the data across several.
qdrant-scaling-qps
Qdrant cannot keep up with the number of searches coming in — this raises how many it can handle at once, first by changing settings, then by putting copies of the data on more machines.
qdrant-scaling-query-volume
Ask for a thousand results at once and Qdrant quietly asks each machine for fewer than that — this explains the shortcut, why a search can come back a little short, and why the trade is a safe one.
qdrant-search-quality
Search is returning the wrong things, and the cause is usually not the database but the AI model behind it or the way the text was chopped up. This is the starting point: find the cause first, then pick the technique that fixes it.
qdrant-search-quality-diagnosis
Bad search results have three usual suspects — the AI model, the shortcut the database takes to search quickly, or the compression used to save memory — and this runs the test that tells you which one it is.
qdrant-search-speed-optimization
Search used to be fast and now it is not — this walks the usual causes, from not enough memory to a filter with no index behind it to a background job hogging the machine, and gives the fix for each.
qdrant-search-strategies
Basic search works but the results still are not good enough — this picks what to add next, whether that is mixing in plain keyword matching, reordering the top hits, or steering the search with examples of what you want.
qdrant-sliding-time-window
Only recent posts, tickets or logs need to be searchable fast — this sets up the routine that retires older data on a schedule, and picks which of three ways of doing it suits your data.
qdrant-tenant-scaling
One search database serving many separate customers: this is how to keep each one's data apart as the count grows past ten thousand, and why the obvious approach — a separate store per customer — falls over early.
qdrant-version-upgrade
You upgrade a Qdrant cluster to a new version without downtime or data loss, one minor version at a time.
qdrant-vertical-scaling
Before adding more machines to a Qdrant setup, try making the one you already have bigger — this works out how much memory, processing power and disk it really needs, and how to tell when a bigger machine has stopped being the answer.
quality-playbook
Takes software that nobody ever wrote a specification for, works out what it is supposed to do, writes the tests for that, runs three separate AI reviews against it, and hands back the bugs it found with proof that each fix works.
quasi-coder
Shorthand comments, pseudo-code, and rough plain-language descriptions in your files get turned into production-quality code in the target language.
react-audit-grep-patterns
Before upgrading to a newer version of React, every place in the code that will break has to be found — this is the ready-made list of search commands that finds them, instead of writing your own and missing some.
react-container-presentation-component
Scaffolds a new React component for this repository — the code file, type definitions, a style sheet, and a preview file — and files it as either a plain display piece or a component that manages its own state.
react18-batching-patterns
Upgrading to React 18 quietly changes when the screen redraws, so some older code starts behaving differently with no error to show for it — this finds those spots and gives the correct fix for each kind.
react18-dep-compatibility
A lookup table: for every other library a React project commonly leans on, the oldest version of it that still works once you move up to React 18.3.1 or React 19.
react18-enzyme-to-rtl
The old test tool, Enzyme, does not work with React 18 at all, so every test written with it has to be redone in React Testing Library — and the point of the test changes with it, from what the component holds inside to what a person would see on screen.
react18-legacy-context
React's old way of sharing one value across a page — the logged-in user, say, or the colour theme — has been removed. This moves it onto the replacement, changing the source and every reader at once, because doing half of it breaks the app.
react18-lifecycle-patterns
Three old React methods that ran at set moments while a page updated are on the way out, and the right replacement depends entirely on what each one was actually doing — this sorts that out case by case.
react18-string-refs
React used to let you tag an element with a plain name and grab hold of it later by that name; React 19 drops it, and this converts every one of those tags to the modern replacement, lists and handed-down cases included.
react19-concurrent-patterns
Two rules for a React 19 upgrade: do not accidentally break the responsiveness features already sitting in the React 18 code, and leave React 19's own new features until after the upgrade has settled.
react19-source-patterns
A one-to-one list of what changes in React code for React 19 — each retired feature paired with the thing that replaces it — so nothing has to be converted from memory.
react19-test-patterns
React 19 breaks tests that were written against its old testing helpers — this repairs them in a set order, because one fix unblocks the next and doing it out of order hides the real failures.
readme-blueprint-generator
Writes a project's README — the front page that tells a newcomer what the thing is and how to work on it — out of the documentation notes the repository already keeps.
refactor
Tidying code without changing what it does — a catalogue of the messes that keep coming back, each paired with the safe, step-by-step way to undo it.
refactor-method-complexity-reduce
Takes one function that has grown too tangled to follow and splits it into small named pieces until it scores under the complexity limit you set, then runs the tests to prove nothing behaves differently.
refactor-plan
Before a clean-up that spans many files, this stops and writes the plan first — which files change, in what order, how to check each step and how to back out — and waits for your yes.
remember
You tell it a lesson once, in one line, and it files the note where the coding assistant will read it next time — either for this one project or for everything you work on.
remember-interactive-programming
A short reminder that makes the assistant try its ideas out on the program while it is actually running, rather than deciding from the code alone what will happen.
repo-story-time
Two documents about a codebase nobody has time to explain to you: one on how the project is built, and one telling the story of who built it and when, read out of the commit history.
resemble-detect
Checks whether a piece of audio, video, image or text was made by AI rather than by a person — and refuses to give you an answer until the check has actually finished.
review-and-refactor
Old code drifts away from the rules a team later agreed on; this reads the rule book the project keeps and closes that gap, leaving every file where it is.
reviewing-oracle-to-postgres-migration
Two databases, Oracle and PostgreSQL, quietly disagree about small things — empty text, sort order, timestamps — and this walks the list of them: before a move to find the risks, after it to confirm each one was handled.
rhino3d-scripts
Rhino is a 3D modelling program; this writes and debugs the scripts that automate the repetitive work inside it, and picks which of its three scripting languages the job actually calls for.
roundup
Writes the here-is-what-I-have-been-up-to update for you: it goes and looks at the week's actual work across GitHub, Slack and email, and drafts it in your own voice for whoever will read it.
roundup-setup
A ten-minute interview — who you report to, what your updates usually sound like, where your work actually happens — after which the briefing tool can draft in your voice instead of a generic one.
ruby-mcp-server-generator
Builds the whole Ruby project for a small server that hands an AI assistant tools it can call — the kind a chat app connects to — so you begin from something that already runs.
ruff-recursive-fix
Ruff is the tool that flags sloppy Python; this runs it over and over — the safe fixes first, the riskier ones after, showing you each change — until all that is left is what a person has to decide.
rust-mcp-server-generator
Asks what your tools should do and how other programs will connect, then writes a complete Rust project for a server that gives an AI assistant exactly those tools to call.
salesforce-apex-quality
A review pass over code written in Apex, Salesforce's own programming language — catching the mistakes that only break once real volumes of data arrive, the permission checks people skip, and the tests that ought to exist before anything is deployed.
salesforce-component-standards
The screens a Salesforce app shows its users can be built three different ways, each with its own trapdoors; this holds a screen up against the platform's rules on security, accessibility and testing before it ships.
salesforce-flow-design
Flows are the drag-and-drop automations inside Salesforce; this checks that a flow is even the right tool for the job, and that the one you built will not quietly fall over on a large import.
sandbox-npm-install
Inside a Docker sandbox, installing a project's packages into the shared folder makes some build tools crash outright; this installs them on the container's own disk instead and links them back where the project expects to find them.
scaffolding-oracle-to-postgres-migration-test-project
The empty shell a test suite will live in, built against the Oracle database whose behaviour the migration is measured against — plumbing only, not a single test case in it.
scoutqa-test
Points an automated tester at your website: it clicks around on its own, tries the journeys you name, and comes back with a list of what broke and what nobody could use.
screen-recording
Records a run through a piece of software click by click and turns it into a short animated GIF, paced and captioned, to drop into a pull request or a page of documentation.
secret-scanning
Passwords and API keys get committed by accident; this is the setup that makes GitHub notice them, plus what to do about the ones that already made it into the history.
security-review
Goes through your code hunting for the ways an attacker could break in, then tells you exactly where each problem is and how serious it is.
semantic-kernel
Semantic Kernel is Microsoft's toolkit for wiring AI models into an app — this writes and reviews that kind of code, checking the current official documentation instead of going from memory.
setup-my-iq
Explaining who you are and how your team works at the start of every session, done once and written down where the assistant will find it from then on.
shuffle-json-data
Puts the records in a JSON data file into random order — and refuses, rather than mangling the file, when the records don't all have the same fields.
slang-shader-engineer
Writes, reviews and tunes the code that runs on a graphics card — shaders — in Slang, keeping it portable across the platforms it has to run on.
snowflake-semanticview
Labels your Snowflake data warehouse in business terms — what gets measured, and what it can be broken down by — so people can query it without knowing the table and column names.
sponsor-finder
Most software sits on free code that volunteers maintain; this works out which of those volunteers accept money, and checks each funding link is real before showing it to you.
spring-boot-testing
Picks the right kind of automated test for a piece of Spring Boot code in Java and writes it — the lightest test that still proves the code works.
sql-code-review
Reads the database queries behind your app and flags what is unsafe, what is slow and what is badly written, with a corrected version of each problem it finds.
sql-optimization
Slow database queries, made fast: the query rewritten, the right indexes added, and the reason it was slow spelled out.
sql-server-table-reconciliation
Compares the same tables in two SQL Server databases and reports exactly which rows are missing, which are extra, and which values differ.
ssma-console
Moves a database off Oracle and onto Microsoft SQL Server by driving Microsoft's own migration tool from the command line, one step at a time.
structured-autonomy-generate
Expands a short feature plan into a step-by-step build document, with the finished code for each step, where each file goes, and how to tell the step worked.
structured-autonomy-implement
Carries out exactly one step of an agreed build plan, ticks it off, and stops there instead of running on to the next thing.
structured-autonomy-plan
Works out how to build a feature before any code is written, and saves the result as a plan in your project — split into steps small enough to finish and check one at a time.
suggest-awesome-github-copilot-agents
Looks at what your project is made of and suggests GitHub Copilot agents from the public awesome-copilot collection, skipping the ones you already have and flagging yours that have fallen out of date.
suggest-awesome-github-copilot-instructions
Reads your project, then recommends published instruction files — the standing notes that tell GitHub Copilot how code should be written here — and checks whether the ones you already use are still current.
suggest-awesome-github-copilot-skills
Agent Skills are self-contained bundles of instructions, sometimes with scripts attached; this works out which published ones your project would benefit from, and flags any of yours the authors have since changed.
swift-mcp-server-generator
Creates a whole Swift project for an MCP server — the small program that gives an AI assistant extra abilities — with the source files and readme already written and ready to build.
technical-job-search
Everything a software engineer has to read and write during a job hunt, taken one document at a time and made specific to the job actually being applied for.
technology-stack-blueprint-generator
Writes down what a codebase is actually built from and how it is written, so new work can be made to match instead of guessing at the house style.
terraform-azurerm-set-diff-analyzer
Terraform's list of pending changes is often padded with items that are not really changing, just reordered; this tells the two apart so a review only shows what will actually happen.
threat-model-analyst
Works out how a system could be attacked before anyone tries — what it is made of, where the weak points are, and which of them matter most — and writes the answer up as a report.
tiny-stepping
A way of working where the assistant changes one small thing, stops, and waits for you to say it is going the right way before doing the next.
tldr-prompt
Hands back a cheat sheet instead of a document: point it at a long instructions file or a page of documentation and it prints, right there in the chat, the few examples you would actually have needed.
transloadit-media-processing
Send a video, photo, sound file or document off to Transloadit's servers and get it back converted, resized, trimmed or captioned, without any of that running on your own machine.
typescript-mcp-server-generator
Writes a TypeScript project for a small server that hands an AI assistant tools it can call — built on the current version of the official kit, not the retired one most examples still copy from.
typespec-api-operations
Extends a Microsoft 365 Copilot plugin that already exists with one more thing it can do against its API, wiring included, down to how the answer looks on screen.
typespec-create-agent
Describes a new Microsoft 365 Copilot assistant in a single file, so the thing colleagues end up chatting to is defined in text somebody can read and review.
typespec-create-api-plugin
Connects a Microsoft 365 Copilot assistant to an outside service, so that a question typed in chat becomes a real call to that service — signing in to it included.
ui-screenshots
Takes a picture of the app you are building while it is running, then lets you cut any part of it out afterwards, instead of going back and taking the picture again.
unit-test-vue-pinia
Tests for a Vue app that check what a person would see and do, rather than how the component happens to be wired inside — written from scratch, or applied as a review of tests somebody else wrote.
update-avm-modules-in-bicep
Cloud infrastructure written in Bicep leans on Microsoft's ready-made building blocks, and those keep getting new versions; this works out which ones you have fallen behind on and brings the file up to date.
update-implementation-plan
A build plan that is already written down, revised when the requirements move — kept in the same numbered phases and tasks, so whoever picks it up next, person or agent, can work straight down the list.
update-llms
Some projects keep a file at the top that tells AI tools where the documentation lives; docs move and multiply, and this walks the repository to bring that file back in line with reality.
update-markdown-file-index
Point it at a folder and at a page of documentation, and the page gets a current list of what is in that folder — rebuilt in place whenever you ask, rather than typed out by hand again.
update-specification
The written statement of what a system has to do, pulled back in line with the code and the newest requirements — and kept blunt and self-contained, because its main reader is another machine.
vardoger-analyze
Reads back your own past sessions with the Copilot command-line assistant, works out the habits and preferences you keep repeating, and writes them down where it will read them next time.
vscode-ext-commands
A command added to a VS Code extension has to be named, titled and filed a particular way, or it shows up in the wrong place — or everywhere; this is the convention that gets it right.
vscode-ext-localization
Translating a VS Code extension means three separate kinds of file, depending on where the text sits; this says which kind a given piece of text belongs in, for every language you ship.
web-design-reviewer
Opens your site in a real browser, looks at it the way a visitor would, and then goes into the stylesheets and components to fix what it found broken.
webapp-testing
Instead of guessing whether the page works, it opens one and finds out: clicks the button, fills the form, and brings back the screenshot and the console output from the moment something misbehaved.
what-context-needed
Before it answers, the assistant says which files it would need to look at and what it is still unsure about — so you find that out up front rather than after a confident wrong answer.
winmd-api-search
Windows ships thousands of built-in capabilities — camera, notifications, sensors, file access — and this finds the one that does what you want, then lists everything you can call on it.
winui3-migration-guide
Moving a Windows app off the old UWP framework onto the current one renames half of what it calls, and code generators keep reaching for the old names — this is the reference that catches both.
workiq-copilot
Ask a plain question about your own working week — who is on this project, what was decided in that meeting — and get the answer out of your actual Microsoft 365 mail, calendar, files and Teams.
write-coding-standards-from-file
Reads code you already have and writes down the style it is actually written in — indentation, naming, comments — as a standards document a newcomer can follow.
x-twitter-scraper
Gets data out of X, formerly Twitter — tweets, profiles, follower lists, search results — by going through a service called Xquik that has already solved the scraping part.
HOW TO GET IT
npx skills add github/awesome-copilotnpx skills add github/awesome-copilot --skill <name> --full-depthPick the skill name from the Skills tab — each entry there installs independently.
/plugin marketplace add github/awesome-copilot/plugin install accessibility-kanban@awesome-copilot/plugin install acreadiness-cockpit@awesome-copilot/plugin install agent-council@awesome-copilotTyped inside the agent's own prompt, not in a terminal. The marketplace lists 162 plugins; three are shown. Every one installs the same way, with its own name before @awesome-copilot.