awesome-llm-apps/awesome_agent_skills/README.md

Awesome Agent Skills

A curated collection of production-ready skills for AI agents and LLM applications.

What Are Agent Skills?

Agent Skills are specialized prompts that transform a general-purpose AI into a domain expert. Each skill provides:

• 🎯 Focused expertise — Deep knowledge in a specific area
• 📋 Consistent output — Reliable, structured responses
• ⚡ Quick integration — Add capabilities in minutes
• 🔄 Reusable patterns — Works across projects

Skills Collection

🖥️ 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

How to Use

1. Direct Prompting

Copy the skill content and paste it into your AI conversation as a system message.

2. OpenAI / Anthropic API

from openai import OpenAI

client = OpenAI()

# Load skill from file
with open('awesome_agent_skills/coding/python_expert.md', 'r') as f:
    skill_content = f.read()

response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": skill_content},
        {"role": "user", "content": "Write a function to merge two sorted lists"}
    ]
)

3. LangChain

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

# Load skill
with open('awesome_agent_skills/research/deep_research.md', 'r') as f:
    system_prompt = f.read()

prompt = ChatPromptTemplate.from_messages([
    ("system", system_prompt),
    ("user", "{input}")
])

chain = prompt | ChatOpenAI(model="gpt-4")
result = chain.invoke({"input": "Research the current state of quantum computing"})

4. AI Coding Assistants

Add skills to your project configuration:

Cursor (.cursorrules):

Include the content from awesome_agent_skills/coding/python_expert.md

Claude Projects: Upload skill files to your project knowledge base.

Skill Format

Each skill follows this structure:

---
name: skill-name
description: Brief description of what the skill does.
---

# Skill Name

## When to use this skill
[Scenarios where this skill is helpful]

## How to Use this Skill
[Integration instructions with code examples]

### Parameters
[Input parameters the skill expects]

### Returns
[What output the skill provides]

## Example
[Input/output example]

Contributing

We welcome contributions! To add a new skill:

1. Fork the repository
2. Create a new skill file in the appropriate category folder
3. Follow the skill format template above
4. Include practical examples
5. Submit a pull request

License

MIT