Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills2,933
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons725
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
add-educational-comments
✓★ 36,200by github
Add educational comments to code files to transform them into effective learning resources. Adapts explanation depth and tone to three configurable knowledge levels: beginner, intermediate, and advanced Automatically requests a file if none is provided, with numbered list matching for quick selection Expands files by up to 125% using educational comments only (hard limit: 400 new lines; 300 for files over 1,000 lines) Preserves file encoding, indentation style, syntax correctness, and...
copilot-instructions-blueprint-generator
✓★ 36,200by github
Generate GitHub Copilot instruction files by analyzing actual codebase patterns and technology versions. Scans projects to detect exact language, framework, and library versions, then generates instructions that enforce compatibility with those specific versions Analyzes existing code patterns for naming conventions, architecture style, error handling, testing approaches, and documentation standards to ensure Copilot-generated code matches established practices Supports multiple technology...
arize-dataset
✓★ 36,200by github
INVOKE THIS SKILL when creating, managing, or querying Arize datasets and examples. Also use when the user needs test data or evaluation examples for their…
remember
✓★ 36,200by github
Persistent, domain-organized memory system that captures lessons learned across VS Code projects. Stores reusable knowledge in two scopes: global (all projects) or workspace-specific, automatically organizing learnings by domain Uses simple syntax ( /remember [>domain [scope]] lesson ) to transform debugging sessions and hard-won discoveries into searchable memory instructions Automatically discovers existing memory domains and intelligently categorizes new learnings, creating domain files...
autoresearch
✓★ 36,200by github
Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then…
oo-component-documentation
✓★ 36,200by github
Create or update standardized object-oriented component documentation using a shared template plus mode-specific guidance for new and existing docs.
boost-prompt
✓★ 36,200by github
Interactive workflow to refine task prompts through structured questioning and clipboard delivery. Guides users through systematic prompt refinement by interrogating scope, deliverables, constraints, and technical requirements Produces polished markdown prompts and automatically copies them to the system clipboard via the Joyride extension Focuses exclusively on prompt engineering; does not generate code or implementation details Requires the Joyride extension for VSCode clipboard...
centos-linux-triage
✓★ 36,200by github
Diagnose and resolve CentOS issues with RHEL-compatible commands and SELinux awareness. Confirms CentOS release type (Stream vs. legacy) and provides triage steps using systemctl, journalctl, dnf/yum, and log inspection Includes copy-paste-ready remediation commands with verification steps after each major change Addresses SELinux policies and firewalld configuration as part of troubleshooting workflow Provides rollback and cleanup procedures to safely revert changes
agent-supply-chain
✓★ 36,200by github
Generate and verify integrity manifests for AI agent plugins and tools. Detect tampering, enforce version pinning, and establish supply chain provenance.
dataverse-python-advanced-patterns
✓★ 36,200by github
Production-ready Dataverse SDK patterns with error handling, batch operations, and optimization techniques. Demonstrates exponential backoff retry logic for transient errors, batch CRUD operations with error recovery, and OData query optimization using filters, selects, expands, and paging with correct logical names Covers table metadata creation and inspection, custom column definitions with IntEnum option sets, and cache flushing strategies when schema changes Includes configuration best...
datanalysis-credit-risk
✓★ 36,200by github
Credit risk data cleaning and variable screening pipeline for pre-loan modeling. Executes 11 independent steps covering data loading, abnormal period filtering, missing rate analysis, low-IV and high-PSI variable removal, null importance denoising, and correlation-based feature elimination Supports organization-level analysis with separate modeling and out-of-sample (OOS) sample handling, plus multi-process acceleration for IV and PSI calculations Generates comprehensive Excel report with 15...
copilot-spaces
✓★ 36,200by github
Project-specific context for conversations through curated documentation, code, and team instructions. List and load Copilot Spaces using MCP read-only tools; create, update, and delete spaces via GitHub REST API with gh api Spaces contain attached repositories, files, documentation, and custom instructions that ground Copilot responses in actual project knowledge Use spaces to answer architecture and standards questions, generate code following team conventions, or execute multi-step...
create-github-issue-feature-from-specification
✓★ 36,200by github
Create GitHub issues from specification files using the feature_request.yml template. Analyzes specification files to extract requirements and automatically generates issue titles and descriptions Searches existing issues to prevent duplicates before creating new ones Supports both creating new issues and updating existing ones via the GitHub API Applies feature and enhancement labels automatically based on specification content
csharp-nunit
✓★ 36,200by github
NUnit best practices for standard and data-driven unit testing in .NET projects. Organize tests with [TestFixture] classes matching production code, using [Test] methods named MethodName_Scenario_ExpectedBehavior and following Arrange-Act-Assert structure Data-driven testing via [TestCase] , [TestCaseSource] , [Values] , [Range] , and [Combinatorial] attributes for inline, programmatic, and parameterized test generation Use Assert.That with constraint model ( Is.EqualTo , Contains.Item ) and...
create-github-issues-feature-from-implementation-plan
✓★ 36,200by github
Create GitHub Issues automatically from implementation plan phases. Analyzes implementation plan files to identify phases and generates one issue per phase Uses feature_request.yml or chore_request.yml templates, with fallback to default issue format Checks for existing issues before creation to avoid duplicates, and updates existing issues when needed Includes phase details, requirements, and context in issue descriptions with appropriate labels
create-github-issues-for-unmet-specification-requirements
✓★ 36,200by github
Automatically create GitHub issues for specification requirements not yet implemented in code. Analyzes specification files to extract all requirements, then checks codebase implementation status for each one Searches existing issues to prevent duplicates before creating new feature request issues Generates issues with requirement IDs, detailed descriptions, implementation guidance, and acceptance criteria Scans related specification files and code patterns to verify whether requirements are...
powerbi-modeling
✓★ 36,200by github
Semantic modeling assistant for building optimized Power BI data models with DAX, relationships, and best practices. Connects to active Power BI models (Desktop or Fabric) to analyze current structure before providing guidance on star schemas, relationships, measures, and naming conventions Covers core modeling tasks: creating DAX measures, configuring table relationships and cardinality, implementing row-level security (RLS), and optimizing performance Includes model quality assessment...
aspnet-minimal-api-openapi
✓★ 36,200by github
ASP.NET Minimal API endpoints with automatic OpenAPI/Swagger documentation and strong typing. Organize endpoints using MapGroup() , endpoint filters, and feature-based folder structures for scalability Define explicit request/response DTOs with validation attributes; use record types and TypedResults for type safety Leverage .NET 9 built-in OpenAPI support with operation summaries, descriptions, operationIds, and property-level documentation via [Description()] Apply document and schema...
acreadiness-generate-instructions
✓★ 36,200by github
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS…
debian-linux-triage
✓★ 36,200by github
Expert-guided triage and resolution for Debian Linux system issues using apt, systemd, and AppArmor. Diagnoses problems across package management, service health, and security policies with Debian-native tools Provides step-by-step triage plans using systemctl , journalctl , apt , and dpkg with copy-paste-ready commands Includes verification steps after remediation and rollback guidance for safe recovery Accounts for AppArmor and firewall considerations in troubleshooting workflows
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...
editorconfig
✓★ 36,200by github
EditorConfig file generator that analyzes projects and creates comprehensive editor configuration based on best practices. Analyzes project structure and file types to infer languages and technologies, then generates targeted configuration rules for each file type Applies universal best practices including UTF-8 charset, LF line endings, trailing whitespace removal, and final newline insertion Respects user preferences (spaces vs. tabs, indentation size) while flagging any conflicts with...
diagnose
✓★ 36,200by github
Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and…
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.
react18-lifecycle-patterns
✓★ 36,200by github
Provides exact before/after migration patterns for the three unsafe class component lifecycle methods - componentWillMount, componentWillReceiveProps, and…
ruff-recursive-fix
✓★ 36,200by github
Run Ruff checks with optional scope and rule overrides, apply safe and unsafe autofixes iteratively, review each change, and resolve remaining findings with…
ai-ready
✓★ 36,200by github
Make any repo AI-ready — analyzes your codebase and generates AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review…
csharp-tunit
✓★ 36,200by github
Best practices for writing unit tests with TUnit, including data-driven and advanced testing patterns. Use [Test] attribute for test methods; follow Arrange-Act-Assert pattern with naming convention MethodName_Scenario_ExpectedBehavior Data-driven testing via [Arguments] , [MethodData] , and [ClassData] attributes; multiple [Arguments] can apply to the same method Fluent async assertions with await Assert.That() syntax; chain with .And or .Or operators and use .Within() for tolerance...
lsp-setup
✓★ 36,200by github
Enable code intelligence (go-to-definition, find-references, hover, type info) for any programming language by installing and configuring an LSP server for…
threat-model-analyst
✓★ 36,200by github
Full STRIDE-A threat model analysis and incremental update skill for repositories and systems. Supports two modes: (1) Single analysis — full STRIDE-A threat…