Files
awesome-llm-apps/awesome_agent_skills
..

Awesome Agent Skills

A curated collection of skills for AI agents following the Agent Skills format.

What Are Agent Skills?

Agent Skills are packaged instructions and scripts that extend agent capabilities. They follow the Agent Skills specification - a simple, open format for giving agents new capabilities and expertise.

Each skill contains:

  • SKILL.md - Instructions for the agent
  • scripts/ - Helper scripts for automation (optional)
  • references/ - Supporting documentation (optional)

Available Skills

🖥️ Coding

Skill Description
python-expert Senior Python developer with focus on clean, maintainable code
code-reviewer Thorough code review with security and performance focus
debugger Systematic debugging and root cause analysis
fullstack-developer Modern web development (React, Node.js, databases)

🔍 Research

Skill Description
deep-research Multi-source research with citations and synthesis
fact-checker Verify claims and identify misinformation
academic-researcher Literature review and academic writing

✍️ Writing

Skill Description
technical-writer Clear documentation and technical content
content-creator Engaging blog posts and social media content
editor Professional editing and proofreading

📋 Planning

Skill Description
project-planner Break down projects into actionable tasks
sprint-planner Agile sprint planning and estimation
strategy-advisor High-level strategic thinking and business decisions

📊 Data Analysis

Skill Description
data-analyst SQL, pandas, and statistical analysis
visualization-expert Chart selection and data visualization

Productivity

Skill Description
email-drafter Professional email composition
meeting-notes Structured meeting summaries with action items
decision-helper Structured decision-making frameworks

Installation

npx skills add shubhamsaboo/awesome-agent-skills

Manual Installation

Clone or download individual skill directories and reference them in your agent's configuration.

Usage

Skills are automatically available once installed. Agents use them when relevant tasks are detected based on the skill's description and triggers.

Examples

When you ask your agent:

  • "Review this React component for performance" → Triggers code-reviewer skill
  • "Research the benefits of intermittent fasting" → Triggers deep-research skill
  • "Help me debug this Python function" → Triggers debugger skill
  • "Draft an email to decline a meeting" → Triggers email-drafter skill

Integration with Agent Products

Agent Skills work with any skills-compatible agent product. Examples:

  • Claude Desktop / claude.ai - Upload SKILL.md files to project knowledge
  • Cursor / VSCode - Reference skills in .cursorrules or custom instructions
  • Custom agents - Load SKILL.md content as system prompts or agent instructions
  • AI frameworks - Use with LangChain, AutoGen, or custom agent frameworks

Skill Structure

Each skill follows the Agent Skills specification:

skill-name/
├── SKILL.md          # Required: Instructions for the agent
├── scripts/          # Optional: Helper scripts
├── references/       # Optional: Supporting documentation
└── assets/          # Optional: Images, templates, etc.

SKILL.md Format

---
name: skill-name
description: |
  What the skill does and when to use it.
  Include triggers like "use when debugging" or "when user mentions code review".
license: MIT
metadata:
  author: awesome-llm-apps
  version: "1.0.0"
---

# Skill Name

Instructions for the agent to follow...

Creating Your Own Skills

  1. Create a new directory with your skill name (lowercase, hyphens only)
  2. Add a SKILL.md file with YAML frontmatter
  3. Write clear, actionable instructions for the agent
  4. (Optional) Add supporting scripts or reference materials

See the Agent Skills specification for complete details.

Contributing

We welcome contributions! To add a new skill:

  1. Fork the repository
  2. Create a new skill directory following the specification
  3. Ensure SKILL.md has proper YAML frontmatter
  4. Include clear instructions and examples
  5. Submit a pull request

Resources