Activeai mlMIT

AI Agents Skills

AI agent skills repository

200 stars20 forks35 viewsAdded 1mo ago

AI-Agent Assisted

Tier 2
GitHub Copilot
Signals: README-created-with-copilot

README

AI Agent Skills GitHub Star AWS GenAI Superstar

AI Agent Skills Hero

๐Ÿง  Agent Skills Repository


๐Ÿ†• NEW: Honest Agent Skill

Just added! A universal skill that configures ALL your AI coding agents to be honest, objective, and non-sycophantic. Run it once, and every agent (Claude Code, GitHub Copilot, Cursor, Windsurf, etc.) will stop telling you what you want to hear and start giving you honest, direct feedback.

๐Ÿ”— View the Honest Agent Skill โ†’

What it does:

  • Configures honest, objective communication across 7 verified AI coding agents
  • One-time setup that updates all your agent instruction files
  • Supports both project-level and global configuration
  • Works with Claude Code, Copilot, Cursor, Windsurf, Cline, Aider, and Continue.dev

A curated collection of AI agent skills for enhanced coding assistance

Supercharge your AI coding agents with specialized knowledge and production-ready patterns

Skills โ€ข Quick Start โ€ข Usage โ€ข Contributing


๐Ÿ‘ค Author

Yuval Avidani

Yuval Avidani

AI Builder & Speaker | GitHub Star โญ | AWS GenAI Superstar ๐ŸŒŸ

Building the future with AI agents, automation, and cutting-edge technology.
20+ years turning complex ideas into production-ready solutions.

Website GitHub Projects

๐ŸŽค Speaker & Enterprise AI Trainer
๐Ÿ† Recognized for open-source contributions

๐Ÿค– This repository was created by Yuval Avidani using GitHub Copilot via VS Code Insiders โ€” demonstrating the power of AI-assisted development!


โœจ What Are Agent Skills?

Agent skills are specialized knowledge modules that enhance AI coding agents with domain-specific expertise. They provide:

  • ๐ŸŽฏ Focused Knowledge โ€” Only what the AI doesn't already know
  • ๐Ÿ“ Production-Ready Code โ€” Working examples, not abstract concepts
  • โšก Quick Activation โ€” Trigger keywords for instant context
  • ๐Ÿ”„ Reusable Patterns โ€” Copy once, use everywhere

๏ฟฝ๏ธ Understanding Agent Skills (Open Standard)

What is SKILL.md?

SKILL.md is a simple, open format for giving AI agents new capabilities and expertise. It's an open standard that works across multiple AI coding agents and platforms.

Agent Skills are folders of instructions, scripts, and resources that your AI agent can discover and use to perform tasks more accurately and efficiently.

Why Use Agent Skills?

For You (Developer):

  • ๐Ÿ“š Learn Faster โ€” Pre-built knowledge from experts in your domain
  • ๐ŸŽฏ Better Results โ€” Agents have context to work more accurately
  • โ™ป๏ธ Reuse Everywhere โ€” Same skill works across Copilot, Claude Code, Cursor, Windsurf, and more
  • ๐Ÿ” Version Control โ€” Skills are part of your repository, tracked in git

For Your Team:

  • ๐Ÿ“– Capture Knowledge โ€” Document processes and best practices
  • ๐Ÿš€ Share Skills โ€” Distribute expertise across projects
  • ๐Ÿข Enterprise Use โ€” Centralize organizational knowledge

For AI Agents:

  • ๐Ÿง  Domain Expertise โ€” Perform specialized tasks reliably
  • ๐Ÿ”ง New Capabilities โ€” Enable new workflows and automations
  • ๐ŸŽ“ Context โ€” Access procedures, scripts, and examples on demand

What Can You Do With Agent Skills?

Agent skills enable AI agents to:

  • Domain Expertise: Package specialized knowledge (legal review, data analysis, deployment procedures)
  • New Capabilities: Create presentations, build MCP servers, analyze datasets, debug failures
  • Repeatable Workflows: Turn multi-step tasks into consistent, auditable processes
  • Interoperability: Reuse skills across different compatible agent products

๐Ÿ“š How Agent Skills Work (Step-by-Step for Beginners)

Step 1: Understanding the File Structure

Each skill is a simple folder with a SKILL.md file inside:

your-project/
โ”œโ”€โ”€ .github/skills/          # GitHub Copilot project skills location
โ”‚   โ””โ”€โ”€ my-skill-name/
โ”‚       โ”œโ”€โ”€ SKILL.md         # Main skill file (required)
โ”‚       โ”œโ”€โ”€ script.js        # Optional: supporting scripts
โ”‚       โ””โ”€โ”€ examples.md      # Optional: more examples
โ”œโ”€โ”€ .claude/skills/          # Claude Code project skills location
โ”‚   โ””โ”€โ”€ my-skill-name/
โ”‚       โ””โ”€โ”€ SKILL.md
โ””โ”€โ”€ ~/.copilot/skills/       # Personal skills (available across all projects)
    โ””โ”€โ”€ my-skill-name/
        โ””โ”€โ”€ SKILL.md

Step 2: Understanding SKILL.md Format

Every SKILL.md file has two parts:

YAML Frontmatter (metadata):

---
name: my-skill-name           # Unique identifier (lowercase, hyphens for spaces)
description: What this skill  # When should the agent use this skill?
license: MIT                  # Optional: license information
---

Markdown Body (instructions): The rest of the file contains instructions and examples for the AI agent.

Step 3: A Real Example

Here's what a simple SKILL.md looks like:

---
name: github-actions-debugging
description: Guide for debugging failing GitHub Actions workflows. Use this when asked to debug CI/CD failures or workflow issues.
---

# Debugging GitHub Actions Workflows

When debugging a failing workflow:

1. **Check the job logs** - Look for error messages and stack traces
2. **Review recent changes** - What changed since the last successful run?
3. **Test locally** - Reproduce the issue in your local environment
4. **Fix and validate** - Make changes and verify they work

## Common Issues and Solutions

### Issue: Workflow fails with "Command not found"
**Solution**: Install the required tool in your workflow step

### Issue: Permission denied when running scripts
**Solution**: Add `chmod +x script.sh` before running the script

Step 4: Agent Discovers and Uses Your Skill

When you ask your AI agent to do something:

"Debug why our GitHub Actions workflow is failing"

The agent will:

  1. โœ… Recognize that you're asking about GitHub Actions
  2. โœ… Find the github-actions-debugging skill in your project
  3. โœ… Load the SKILL.md file into its context
  4. โœ… Follow the instructions to help you debug

Step 5: Supported Locations

Project Skills (specific to one repository):

  • your-repo/.github/skills/ โ€” For GitHub Copilot
  • your-repo/.claude/skills/ โ€” For Claude Code

Personal Skills (available across all projects on your machine):

  • ~/.copilot/skills/ โ€” For GitHub Copilot (Copilot CLI and VS Code)
  • ~/.claude/skills/ โ€” For Claude Code

Organization/Enterprise Skills (coming soon):

  • Enterprise-level skills support is in development

๐Ÿค Supported AI Agents

Agent Skills work with these AI coding agents:

AgentSupportLocation
GitHub Copilotโœ… Full Support.github/skills/ or ~/.copilot/skills/
Claude Codeโœ… Full Support.claude/skills/ or ~/.claude/skills/
Cursorโœ… Full Support.cursor/rules/
Windsurfโœ… Full Support.windsurf/rules/
VS Code Insidersโœ… Full SupportAgent mode with skills
VS Code (Stable)โณ Coming SoonSupport coming in future release

๐Ÿ“ฆ Available Skills

SkillDescriptionKeywords
copilot-sdkGitHub Copilot SDK for building agentic applicationsCopilot SDK, GitHub SDK, agentic app, embed Copilot
honest-agent ๐Ÿ†•Configure all AI agents for honest, objective feedbackhonest agent, no sycophancy, objective, contradict me
aws-agentcoreAWS Bedrock AgentCore development patternsAgentCore, Bedrock Agent, AWS agent
aws-strandsModel-agnostic agent framework with Strands SDKStrands, ReAct agent, model-agnostic
aws-account-managementAWS Organizations, IAM, billing & multi-accountAWS Organizations, IAM, SCPs, Cost Explorer
langchainLangChain/LangGraph pipelines and agent workflowsLangChain, LangGraph, RAG, LCEL
vercelVercel deployment, serverless, and edge functionsVercel, serverless, edge function
railwayRailway platform deployment and configurationRailway, deploy container
cloudflareCloudflare Workers, Pages, D1, R2, KV & AICloudflare, Workers, D1, R2, edge computing
figmaFigma API, component code generation & design tokensFigma API, design tokens, Figma to code
fal-aiServerless AI image/video generation with fal.aifal.ai, Flux, SDXL, AI image generation
mongodbMongoDB & Mongoose queries, aggregation pipelinesMongoDB, Mongoose, aggregation, NoSQL
bunBun JavaScript runtime, bundler & test runnerBun, bun.sh, JavaScript runtime
owasp-securityOWASP Top 10 security vulnerabilities & preventionOWASP, security, XSS, SQL injection, CSRF
shabbat-timesJewish calendar data and Shabbat times integrationShabbat times, Hebcal, Zmanim
copilot-docsGitHub Copilot custom instructions referencecopilot-instructions.md
nano-banana-proGoogle Gemini 3 Pro Image generationNano Banana Pro, Gemini 3 Pro Image
github-trendingGitHub trending repositories scrapingGitHub trending, trending repos
ux-design-systemsDesign systems and component librariesdesign system, design tokens, theming
web-accessibilityWCAG compliance and accessibility patternsaccessibility, a11y, WCAG, ARIA
mobile-responsivenessResponsive design and mobile-first patternsresponsive, mobile-first, breakpoints
analytics-metricsData visualization and analytics dashboardsanalytics, dashboard, charts, KPI
mermaid-diagramsMermaid diagram syntax for visualizationsMermaid, flowchart, sequence diagram
local-llm-routerRoute queries to local LLMs in air-gapped networks with Serena MCPlocal LLM, Ollama, LM Studio, air-gapped, Serena, model routing

๐Ÿš€ Quick Start

1. Clone the Repository

git clone https://github.com/yuval-avidani/ai-agents-skills.git

2. Copy Skills to Your Project

Choose your AI coding agent and follow the instructions below.


๐Ÿ’ป Setup Guide: Using Skills in Your Agent (For Beginners)

This guide walks you through setting up Agent Skills in your favorite coding agent, step by step.

๐ŸŽฏ Prerequisites

Before you start, you need:

  • A coding agent installed (Copilot, Claude Code, Cursor, or Windsurf)
  • A project folder on your computer
  • Basic familiarity with command line or your agent's UI

๐Ÿ“ Step-by-Step Setup

Option 1: GitHub Copilot (Most Popular)

๐ŸŸข Setup GitHub Copilot with Skills

For Project Skills (specific to one repository):

  1. In your project folder, create the skills directory:

    mkdir -p .github/skills
    
  2. Copy the skills you want from this repository:

    # Copy a single skill
    cp -r skills/vercel .github/skills/
    
    # Or copy all skills
    cp -r skills/* .github/skills/
    
  3. Or manually create a skill:

    your-project/
    โ””โ”€โ”€ .github/
        โ””โ”€โ”€ skills/
            โ””โ”€โ”€ my-custom-skill/
                โ””โ”€โ”€ SKILL.md
    
  4. Open your project in VS Code and start using Copilot Agent

  5. Ask Copilot a question related to your skill, and it will automatically load it!

For Personal Skills (available across all your projects):

  1. Find your home directory (~ or C:\Users\YourUsername)

  2. Create personal skills folder:

    mkdir -p ~/.copilot/skills
    
  3. Copy skills there:

    cp -r skills/vercel ~/.copilot/skills/
    
  4. Now all your projects can use these skills automatically!

Verify it's working:

  • Open Copilot Agent
  • Ask about something covered in your skill (e.g., "How do I deploy to Vercel?")
  • Copilot will use the skill to help you

Option 2: Claude Code

๐ŸŸฃ Setup Claude Code with Skills

For Project Skills:

  1. In your project folder, create the skills directory:

    mkdir -p .claude/skills
    
  2. Copy the skills you want:

    # Single skill
    cp -r skills/langchain .claude/skills/
    
    # All skills
    cp -r skills/* .claude/skills/
    
  3. Open your project in Claude Code

  4. Chat with Claude about tasks covered in your skills - it will automatically use them!

For Personal Skills (available everywhere):

  1. Create personal skills folder:

    mkdir -p ~/.claude/skills
    
  2. Copy skills there:

    cp -r skills/aws-agentcore ~/.claude/skills/
    

Verify it's working:

  • Open Claude Code in your project
  • Ask about something in your skill
  • Claude will reference and use the skill

Option 3: Cursor

๐Ÿ”ต Setup Cursor with Skills

For Project Rules:

  1. In your project folder:

    mkdir -p .cursor/rules
    
  2. Copy SKILL.md files (rename them as rules):

    # Copy a skill as a rule file
    cp skills/figma/SKILL.md .cursor/rules/figma.md
    
    # Or copy multiple
    cp skills/*/SKILL.md .cursor/rules/
    
  3. In Cursor Settings, configure which rules to use:

    • Settings โ†’ Rules โ†’ Add project rules
    • Point to .cursor/rules/ folder
  4. Start using Cursor - it will apply these rules to your context automatically


Option 4: Windsurf

๐ŸŸก Setup Windsurf with Skills

For Project Rules:

  1. In your project folder:

    mkdir -p .windsurf/rules
    
  2. Copy skills as rules:

    # Copy specific skills
    cp skills/vercel/SKILL.md .windsurf/rules/vercel.md
    
    # Or copy all skills
    cp skills/*/SKILL.md .windsurf/rules/
    
  3. Windsurf automatically discovers rules in .windsurf/rules/

  4. Start building - Windsurf will use these rules contextually


๐ŸŽ“ What Happens After Setup?

Once you've set up your skills:

  1. Agent Detects Skills: Your AI agent scans the skill directories
  2. Agent Reads SKILL.md: It reads the name and description from frontmatter
  3. Agent Activates on Relevance: When you ask a question matching the description, the agent loads the skill
  4. Agent Follows Instructions: Your agent now has the context to help you accurately

๐Ÿ’ก Example: Using a Vercel Skill

You have this SKILL.md:

---
name: vercel-deployment
description: Deploying applications to Vercel. Use this when asked about deploying, hosting, or managing Vercel projects.
---

You ask your agent:

"Help me deploy my React app to Vercel"

Agent automatically:

  • โœ… Finds vercel-deployment skill
  • โœ… Loads SKILL.md into context
  • โœ… Follows the deployment instructions
  • โœ… Helps you deploy successfully!

๐Ÿ› Troubleshooting

ProblemSolution
Agent not using skillRestart your agent, or make sure folder path is correct
Skill file not foundVerify SKILL.md is in the right folder and named exactly "SKILL.md"
Agent using wrong skillMake sure skill descriptions are descriptive enough to match your request

๐Ÿ’ป Usage (Advanced)


๐Ÿ“ Skill Format

Each skill follows a consistent structure:

---
name: skill-name
description: Brief description with trigger keywords
---

# Skill Title

Quick start and core patterns...

๐ŸŽฏ Key Principles

PrincipleDescription
Concise is keyOnly include what the AI doesn't already know
Progressive disclosureStart with quick start, then advanced patterns
Concrete examplesWorking code over abstract descriptions
Trigger keywordsInclude words that activate the skill

๐Ÿ“ Repository Structure

ai-agents-skills/
โ”œโ”€โ”€ ๐Ÿ“„ README.md
โ”œโ”€โ”€ ๐Ÿ“ skills/
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ copilot-sdk/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ honest-agent/       # ๐Ÿ†• NEW!
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ aws-agentcore/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ aws-strands/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ aws-account-management/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ langchain/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ vercel/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ railway/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ cloudflare/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ figma/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ fal-ai/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ mongodb/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ bun/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ owasp-security/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ shabbat-times/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ copilot-docs/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ nano-banana-pro/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ github-trending/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ ux-design-systems/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ web-accessibility/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ mobile-responsiveness/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ analytics-metrics/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ mermaid-diagrams/
โ”‚   โ”‚   โ””โ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚   โ””โ”€โ”€ ๐Ÿ“ local-llm-router/
โ”‚       โ”œโ”€โ”€ ๐Ÿ“„ SKILL.md
โ”‚       โ””โ”€โ”€ ๐Ÿ“ references/
โ”‚           โ””โ”€โ”€ ๐Ÿ“„ model-matrix.md
โ””โ”€โ”€ ๐Ÿ“ templates/
    โ””โ”€โ”€ ๐Ÿ“ skill-template/
        โ””โ”€โ”€ ๐Ÿ“„ SKILL.md

๐Ÿค Contributing

We welcome contributions! Here's how to add a new skill:

  1. Fork this repository
  2. Create a new skill in skills/your-skill-name/SKILL.md
  3. Follow the skill template
  4. Submit a pull request

Contribution Guidelines

  • โœ… Include practical, production-ready code examples
  • โœ… Add trigger keywords in the description
  • โœ… Test all code snippets before submitting
  • โœ… Keep explanations concise but complete
  • โŒ Don't include basic concepts the AI already knows
  • โŒ Don't use placeholder code or TODOs

๐ŸŒŸ Star History

If you find this repository useful, please consider giving it a โญ!


๐Ÿ“„ License

MIT License โ€” Feel free to use, modify, and distribute.


Made with โค๏ธ by Yuval Avidani

Building AI agents that matter

Follow on GitHub

Tags

built-with-github-copilotagents

Similar Tools