awesome-llm-skills

Contents

• What Are LLM Skills?
• Quick Start
• Skills
• Platforms
  • Claude Code (Anthropic)
  • Claude Desktop (Anthropic)
  • Codex CLI (OpenAI)
  • Gemini CLI (Google)
  • OpenCode (Open-source CLI)
  • Qwen Code (Alibaba)
• Contributing
  • Quick Contribution Steps
• Resources
  • Official Documentation
  • Community Resources
• License

What Are LLM Skills?

LLM Skills are customizable workflows that teach LLM how to perform specific tasks according to your unique requirements. Skills enable LLM to execute tasks in a repeatable, standardized manner across all LLM platforms.

Quick Start

1. Create a project-local or user-level skill folder Use one of these discovery paths so Claude Code finds it automatically:

   • Project: .claude/skills/webapp-testing/
   • User: ~/.claude/skills/webapp-testing/

2. Add SKILL.md (required)

Basic Skill Template:

---
name: my-skill-name
description: A clear description of what this skill does and when to use it.
---

# My Skill Name

Detailed description of the skill's purpose and capabilities.

## When to Use This Skill

- Use case 1
- Use case 2
- Use case 3

## Instructions

[Detailed instructions for LLMs on how to execute this skill]

## Examples

[Real-world examples showing the skill in action]

• Focus on specific, repeatable tasks
• Include clear examples and edge cases
• Write instructions for LLM, not end users
• Document prerequisites and dependencies
• Include error handling guidance

3. Keep supporting files small Add only what's needed (e.g., small fixtures in resources/, helper scripts). This keeps skills snappy to load and easier for Claude to apply.

4. Load the skill

   • Claude (web or Desktop): Upload a ZIP via Settings → Capabilities → Skills → Upload skill.
   • Claude Code (terminal): Place the folder under .claude/skills/ (project) or ~/.claude/skills/ (user). Claude Code discovers skills from these locations.
   • Other CLIs (Codex, Gemini, OpenCode, Qwen Code): They don't use Anthropic's Skills format natively—reference your SKILL.md in prompts (Gemini CLI supports @ file/context attachments).

5. Use it Just ask in natural language, optionally mentioning the skill by name—for example: "Use the Webapp Testing skill to validate the checkout flow and generate report.md." Claude can auto-invoke relevant skills based on your request.

6. (Optional) Kickstart a repo session in Claude Code Slash-commands are supported; many users run /init to generate a CLAUDE.md and bootstrap context before working.

Skills

Skills with MCP

• Notion Knowledge Capture - Converts chats and decisions into structured Notion pages and database entries with proper linking.
• Notion Meeting Intelligence - Preps meetings from Notion context and creates internal pre-reads plus external agendas.
• Notion Research Documentation - Searches Notion, synthesizes multiple pages, and writes cited research docs back to Notion.
• Notion Spec To Implementation - Turns Notion specs into task plans with acceptance criteria and progress tracking.
• Taisly Agent Kit - Publishes approved short-form videos through Taisly with a reusable Agent Skill, Codex plugin, CLI, and remote MCP server.

Document Processing

• docx - Create, edit, analyze Word docs with tracked changes, comments, formatting.
• pdf - Extract text, tables, metadata, merge & annotate PDFs.
• pptx - Read, generate, and adjust slides, layouts, templates.
• xlsx - Spreadsheet manipulation: formulas, charts, data transformations.
• Markdown to EPUB Converter - Converts markdown documents and chat summaries into professional EPUB ebook files. By @smerchek

Development & Code Tools

• artifacts-builder - Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
• aws-skills - AWS development with CDK best practices, cost optimization MCP servers, and serverless/event-driven architecture patterns.
• Blueprint - A Claude Code plugin for specification-driven development that turns natural language into blueprints, blueprints into parallel build plans, and build plans into working software with automated iteration and dual-model adversarial review. By @JuliusBrussee
• Changelog Generator - Automatically creates user-facing changelogs from git commits by analyzing history and transforming technical commits into customer-friendly release notes.
• codebase-recon - Analyzes git history to reveal codebase hotspots, bug magnets, bus factor risks, team momentum, and development patterns before reading any code. By @yujiachen-y
• D3.js Visualization - Teaches Claude to produce D3 charts and interactive data visualizations. By @chrisvoncsefalvay
• dRPC Agent Skills - Gives any LLM coding agent read access to EVM and Solana chains through DRPC. Fetch balances, decode contract state, estimate gas, pull logs. By @drpcorg
• FFUF Web Fuzzing - Integrates the ffuf web fuzzer so Claude can run fuzzing tasks and analyze results for vulnerabilities. By @jthack
• finishing-a-development-branch - Guides completion of development work by presenting clear options and handling chosen workflow.

Data & Analysis

• CSV Data Summarizer - Automatically analyzes CSV files and generates comprehensive insights with visualizations without requiring user prompts. By @coffeefuelbump
• postgres - Execute safe read-only SQL queries against PostgreSQL databases with multi-connection support and defense-in-depth security. By @sanjay3290
• root-cause-tracing - Use when errors occur deep in execution and you need to trace back to find the original trigger.

Business & Marketing

• Brand Guidelines - Applies Anthropic's official brand colors and typography to artifacts for consistent visual identity and professional design standards.
• buyer-eval-skill - Structured, evidence-based B2B software vendor evaluation skill. Engages vendor AI agents, scores vendors across 7 dimensions with transparent evidence tracking, and produces comparative scorecards