mcpbeat Sign in

Claude Skills

The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.

Every Agent Skill we could find on GitHub, deduplicated by content. 79 354 files from 1 739 authors, of which 61 713 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.

61 713
unique skills
out of 79 354 files found on GitHub
17 641
are copies
same content, someone else's repository
1 738
tokens, median
what a typical skill costs you in context
7 879
name collisions
two skills with one name cannot sit side by side

56 161–56 220 of 61 713

page 937 of 1 029
Ue Materials Rendering
by ComeOnOliver
5k tokens
Ue Module Build System
by ComeOnOliver
4k tokens
Ue Networking Replication
by ComeOnOliver
5k tokens
Ue Niagara Effects
by ComeOnOliver
5k tokens
Ue Physics Collision
by ComeOnOliver
4k tokens
Ue Procedural Generation
by ComeOnOliver
5k tokens
Ue Project Context
by ComeOnOliver
3k tokens
Ue Sequencer Cinematics
by ComeOnOliver
5k tokens
Ue Serialization Savegames
by ComeOnOliver
4k tokens
Ue State Trees
by ComeOnOliver
5k tokens
Ue Testing Debugging
by ComeOnOliver
5k tokens
Ue UI Umg Slate
by ComeOnOliver
4k tokens
Ue World Level Streaming
by ComeOnOliver
5k tokens
Cohesive
by ComeOnOliver
351 tokens
Deslop
by ComeOnOliver
325 tokens
Electron To Electrobun
by ComeOnOliver
3k tokens
Organize
by ComeOnOliver
546 tokens
Utg
by ComeOnOliver
212 tokens
Redis Development
by ComeOnOliver
979 tokens
Remotion
by ComeOnOliver
1k tokens
Laravel Collections
by ComeOnOliver
1k tokens
Laravel Validation
by ComeOnOliver
2k tokens
Accessibility Compliance Accessibility Audit
by ComeOnOliver
409 tokens
Agent Orchestration Improve Agent
by ComeOnOliver
2k tokens
Agent Orchestration Multi Agent Optimize
by ComeOnOliver
2k tokens
Airflow Dag Patterns
by ComeOnOliver
295 tokens
API Testing Observability API Mock
by ComeOnOliver
415 tokens
Application Performance Performance Optimization
by ComeOnOliver
3k tokens
Attack Tree Construction
by ComeOnOliver
266 tokens
Auth Implementation Patterns
by ComeOnOliver
290 tokens
Backend Architect
by ComeOnOliver
5k tokens
Backend Development Feature Development
by ComeOnOliver
3k tokens
Backend Security Coder
by ComeOnOliver
2k tokens
Backtesting Frameworks
by ComeOnOliver
283 tokens
Bash Defensive Patterns
by ComeOnOliver
353 tokens
Bash Pro
by ComeOnOliver
5k tokens
Bats Testing Patterns
by ComeOnOliver
258 tokens
Bazel Build Optimization
by ComeOnOliver
2k tokens
Binary Analysis Patterns
by ComeOnOliver
2k tokens
Blockchain Developer
by ComeOnOliver
2k tokens
Business Analyst
by ComeOnOliver
2k tokens
C Pro
by ComeOnOliver
343 tokens
C4 Architecture C4 Architecture
by ComeOnOliver
4k tokens
C4 Code
by ComeOnOliver
2k tokens
C4 Component
by ComeOnOliver
1k tokens
C4 Container
by ComeOnOliver
1k tokens
C4 Context
by ComeOnOliver
1k tokens
Changelog Automation
by ComeOnOliver
256 tokens
Cicd Automation Workflow Automate
by ComeOnOliver
470 tokens
Cloud Architect
by ComeOnOliver
2k tokens
Code Documentation Code Explain
by ComeOnOliver
388 tokens
Code Documentation Doc Generate
by ComeOnOliver
385 tokens
Code Refactoring Context Restore
by ComeOnOliver
2k tokens
Code Refactoring Refactor Clean
by ComeOnOliver
386 tokens
Code Refactoring Tech Debt
by ComeOnOliver
2k tokens
Code Review AI AI Review
by ComeOnOliver
4k tokens
Code Review Excellence
by ComeOnOliver
287 tokens
Codebase Cleanup Deps Audit
by ComeOnOliver
408 tokens
Codebase Cleanup Refactor Clean
by ComeOnOliver
382 tokens
Competitive Landscape
by ComeOnOliver
211 tokens

Claude Skills — questions

Answers built from the skills we actually parsed.

What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 11 329 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 79 354 files found on GitHub, 61 713 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 7 879 skills here share a name with another skill, and two of them cannot sit side by side.