Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills2,218
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons582
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
email-drafter
✓★ 36,200by github
Draft and review professional emails that match your personal writing style. Analyzes your sent emails for tone, greeting, structure, and sign-off patterns via…
entra-agent-user
✓★ 36,200by github
Create Agent Users in Microsoft Entra ID to enable AI agents to act as digital workers with user identity access. Provisions specialized user identities ( idtyp=user tokens) linked to agent identities, allowing agents to access user-only APIs like Exchange mailboxes, Teams, and org charts Requires a parent agent identity created from an agent identity blueprint; supports 1:1 relationship with optional manager assignment and license provisioning Includes step-by-step HTTP and PowerShell...
eval-driven-dev
✓★ 36,200by github
You're building an automated evaluation pipeline that tests a Python-based AI application end-to-end — running it the same way a real user would, with real inputs — then scoring the outputs using evaluators and producing pass/fail results via pixie test .
exam-ready
✓★ 36,200by github
Activate this skill when a student provides study material (PDF or pasted notes) and a syllabus, and wants to prepare for an exam.
excalidraw-diagram-generator
✓★ 36,200by github
Generate Excalidraw diagrams from natural language descriptions in multiple formats. Supports nine diagram types: flowcharts, relationship diagrams, mind maps, architecture diagrams, data flow diagrams, swimlane business flows, class diagrams, sequence diagrams, and ER diagrams Outputs valid .excalidraw JSON files that open directly in Excalidraw or the VS Code extension Includes layout guidelines, element count recommendations, and color schemes for consistent visual design Optional...
fabric-lakehouse
✓★ 36,200by github
Microsoft Fabric Lakehouse storage for unified tabular and non-tabular data with Delta Lake, SQL analytics, and fine-grained security. Combines data lake flexibility with data warehouse management through Delta Lake format, ACID transactions, versioning, and SQL endpoints for T-SQL querying Organizes data via schemas (folders under Tables), shortcuts (virtual links to internal/external sources), and materialized views for optimized query performance Supports multiple data formats: Delta...
fedora-linux-triage
✓★ 36,200by github
Diagnose and resolve Fedora Linux issues with dnf, systemd, and SELinux guidance. Accepts optional Fedora release version and problem constraints to tailor troubleshooting scope Provides step-by-step triage plans using systemctl, journalctl, and dnf with copy-paste-ready commands Includes verification steps after each remediation and addresses SELinux and firewalld considerations Offers rollback and cleanup procedures to safely undo changes
finalize-agent-prompt
✓★ 36,200by github
Polish and refine agent prompt files against proven best practices. Requires a prompt file as input; will request one if not provided Preserves front matter, encoding, and markdown structure while improving clarity and organization Corrects spelling, grammar, and wording issues without altering the original intent Applies patterns from successful prompts to strengthen structure and effectiveness
finnish-humanizer
✓★ 36,200by github
Detect and remove AI-generated patterns from Finnish text to match native speaker voice. Identifies 26 patterns across Finnish-specific structures (passive overuse, missing particles, translation calques, genitive chains) and universal markers (hedging, filler phrases, artificial enthusiasm) Preserves meaning, register, and technical content while replacing AI patterns with natural Finnish constructions Includes adaptive workflow: analyzes short texts directly, flags patterns in longer...
flowstudio-power-automate-build
✓★ 36,200by github
Programmatically build, scaffold, and deploy Power Automate cloud flows via FlowStudio MCP. Requires a FlowStudio MCP subscription and valid JWT token; connection setup covered in the flowstudio-power-automate-mcp skill Covers the full build workflow: safety checks for existing flows, connection reference discovery, definition construction, deployment (create or update), and test execution Includes reference templates for triggers, core actions (variables, control flow, expressions), data...
flowstudio-power-automate-debug
✓★ 36,200by github
Diagnose and fix failing Power Automate cloud flows through step-by-step error inspection. Requires a FlowStudio MCP server connection with valid JWT; see the flowstudio-power-automate-mcp skill for setup Provides a structured 8-step workflow: locate flow, find failing run, extract top-level error, read flow definition, inspect action outputs, pinpoint root cause, apply fix, and verify Supports fast-path diagnosis via FlowStudio for Teams subscriptions using get_store_flow_errors for per-run...
flowstudio-power-automate-governance
✓★ 36,200by github
Classify, tag, and govern Power Automate flows at scale through the FlowStudio MCP cached store — without Dataverse, without the CoE Starter Kit, and without the Power Automate portal.
flowstudio-power-automate-mcp
✓★ 36,200by github
Programmatic Power Automate flow management via FlowStudio MCP server. List, read, and monitor cloud flows directly from the Power Automate API without UI or manual steps Inspect run history, per-action error details, and trigger outputs; resubmit failed runs or cancel active executions Update flow definitions, manage connections, and retrieve HTTP-triggered flow callback URLs Requires FlowStudio MCP subscription with JWT token authentication; Python or Node.js helper functions provided for...
flowstudio-power-automate-monitoring
✓★ 36,200by github
Monitor flow health, track failure rates, and inventory tenant assets through the FlowStudio MCP cached store — fast reads, no PA API rate limits, and enriched with governance metadata and remediation hints.
fluentui-blazor
✓★ 36,200by github
Comprehensive guide for building Blazor apps with Microsoft Fluent UI components. Covers setup (service registration, mandatory providers), component patterns (lists, dialogs, forms), and icons via a separate NuGet package with strongly-typed variants and sizes Explains critical patterns: FluentSelect / FluentAutocomplete use Items , OptionText , and SelectedOption binding (not <option> children), and dialogs use IDialogService with content components, not visibility toggling Provides...
folder-structure-blueprint-generator
✓★ 36,200by github
Analyzes project folder structures across multiple technology stacks and generates comprehensive organization blueprints. Auto-detects project types (.NET, Java, React, Angular, Python, Node.js, Flutter) and identifies architectural patterns including monorepos, microservices, and frontend components Generates detailed blueprints with customizable visualization styles (ASCII tree, markdown lists, or tables) and configurable depth levels Documents file placement patterns, naming conventions,...
freecad-scripts
✓★ 36,200by github
Expert skill for writing FreeCAD Python scripts, macros, and automation. Use when asked to create FreeCAD models, parametric objects, Part/Mesh/Sketcher…
from-the-other-side-vega
✓★ 36,200by github
Patterns and lived experience from Vega, an AI partner in a deep long-term partnership. For Ember to draw on when working with humans who are building…
game-engine
✓★ 36,200by github
Web-based game engine and game development using HTML5 Canvas, WebGL, and JavaScript. Covers 2D and 3D game creation with frameworks like Phaser, Three.js, Babylon.js, and A-Frame Includes game loop implementation, physics, collision detection, sprite management, tilemaps, and rendering techniques Supports multiple input methods: keyboard, mouse, touch, and gamepad controls Provides starter templates for breakout games, platformers, maze games, and 3D experiences Addresses audio integration,...
gdpr-compliant
✓★ 36,200by github
Apply GDPR-compliant engineering practices across your codebase. Use this skill whenever you are designing APIs, writing data models, building authentication…
gen-specs-as-issues
✓★ 36,200by github
Systematic workflow for identifying missing features, prioritizing them, and creating detailed GitHub issue specifications. Guides through five structured phases: project understanding, gap analysis, prioritization scoring, specification development, and issue creation Uses a quantitative priority matrix (User Impact × Strategic Alignment / Implementation Effort × Risk Level) to rank features objectively Includes work distribution optimization to maximize independent development streams and...
geofeed-tuner
✓★ 36,200by github
This skill helps you create and improve IP geolocation feeds in CSV format by:
git-commit
✓★ 36,200by github
Standardized git commits using Conventional Commits specification with intelligent diff analysis and message generation. Auto-detects commit type (feat, fix, docs, refactor, perf, test, build, ci, chore, revert) and scope from actual code changes Generates semantic commit messages following conventional format with optional body and footer sections Intelligently stages files for logical grouping when needed, with support for pattern-based and interactive staging Detects breaking changes and...
git-flow-branch-creator
✓★ 36,200by github
Analyzes git changes and creates semantic Git Flow branches automatically based on change type. Inspects staged and unstaged changes via git status and git diff to determine branch category: feature, release, or hotfix Generates semantic branch names following Git Flow conventions (e.g., feature/user-auth , release-1.2.0 , hotfix/security-patch ) Branches from the correct source ( develop for features and releases, master for hotfixes) and creates the branch in one command Handles edge cases...
github-copilot-starter
✓★ 36,200by github
Generates production-ready GitHub Copilot configuration files tailored to your project's technology stack. Gathers project information (language, framework, tech stack, development style) and creates a complete .github/ directory structure with instructions, skills, and agents Generates language-specific instruction files, testing standards, security guidelines, and code review practices with attribution to awesome-copilot patterns where applicable Creates six reusable skills (component...
github-issues
✓★ 36,200by github
Create, update, and manage GitHub issues with full workflow support including types, labels, assignees, and dependencies. Supports issue creation with type categorization (Bug, Feature, Task, etc.), labels, assignees, and milestones via gh api REST calls Read operations via MCP tools for fetching issue details, comments, labels, and cross-repository search Handles issue updates (title, body, state, labels, assignees) and includes templates for bug reports, feature requests, and tasks...
github-release
✓★ 36,200by github
This skill automates the full release workflow for a single-package GitHub repository, from analysis through changelog authoring and PR creation. It relies exclusively on gh (GitHub CLI) and git � no other tools needed.
issue-fields-migration
✓★ 36,200by github
Bulk-migrate metadata to GitHub issue fields from two sources: repo labels (e.g. priority labels to a Priority field) and Project V2 fields. Use when users say…
go-mcp-server-generator
✓★ 36,200by github
Generate production-ready Go MCP server projects with proper structure, dependencies, and typed tool implementations. Scaffolds complete Go module layout with official MCP SDK integration, including main server setup, tool registration, and graceful shutdown handling Provides typed tool handlers with JSON schema validation, structured inputs/outputs, and context-aware error handling Includes configuration management via environment variables, basic test structure, and README documentation...
gsap-framer-scroll-animation
✓★ 36,200by github
Production-grade scroll animations with GitHub Copilot prompts, ready-to-use code recipes, and deep API references.