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. 79 404 files from 1 741 authors, of which 61 763 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.

61 763
unique skills
out of 79 404 files found on GitHub
17 641
are copies
same content, someone else's repository
1 737
tokens, median
what a typical skill costs you in context
7 882
name collisions
two skills with one name cannot sit side by side

8 821–8 880 of 61 763

page 148 of 1 030
Muapi Selfie With Celebrities
by SamurAIGPT

Generate a realistic behind-the-scenes selfie of the user with a celebrity or main actor from a specific movie, followed by an option to generate a cinematic long-take video connecting multiple selfies.

949 tokens
Muapi Storyboard
by SamurAIGPT

Generate N keyframes for a short story or scene sequence (image only, no video).

606 tokens
Muapi URL To Design
by SamurAIGPT

Analyze a website URL and generate a redesigned, improved UI — recreate the visual design with modern aesthetics, better hierarchy, and fresh brand direction.

883 tokens
Muapi Workflow
by SamurAIGPT

Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.

2k tokens scripts
Trace Claude Code
by parcadei

| Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.

2k tokens
Agent Orchestration
by parcadei

Agent Orchestration Rules

413 tokens
Agentic Workflow
by parcadei

Agentic Workflow Pattern

980 tokens
Agentica Claude Proxy
by parcadei

Guide for integrating Agentica SDK with Claude Code CLI proxy

1k tokens
Agentica Infrastructure
by parcadei

Reference guide for Agentica multi-agent infrastructure APIs

7k tokens
Agentica Prompts
by parcadei

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

2k tokens
Agentica SDK
by parcadei

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

3k tokens
Agentica Server
by parcadei

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

1k tokens
Agentica Spawn
by parcadei

Spawn Agentica multi-agent patterns

511 tokens
Async Repl Protocol
by parcadei

Async REPL Protocol

153 tokens
Leann Search
by parcadei

Semantic search across codebase using LEANN vector index

458 tokens
Router First Architecture
by parcadei

Router-First Architecture

401 tokens
Search Hierarchy
by parcadei

Search Tool Hierarchy

579 tokens
Search Tools
by parcadei

Search Tool Hierarchy

488 tokens
Ast Grep Find
by parcadei

AST-based code search and refactoring via ast-grep MCP

676 tokens
Async Repl Protocol
by parcadei

Async REPL Protocol

158 tokens
Background Agent Pings
by parcadei

Background Agent Pings

331 tokens
Braintrust Analyze
by parcadei

Analyze Claude Code sessions via Braintrust

2k tokens
Braintrust Tracing
by parcadei

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

3k tokens
Build
by parcadei

Workflow orchestrator that chains existing skills for feature development

5k tokens
CLI Reference
by parcadei

Claude Code CLI commands, flags, headless mode, and automation patterns

2k tokens
Complete Skill
by parcadei

A complete skill for E2E testing

61 tokens
Completion Check
by parcadei

Completion Check: Verify Infrastructure Is Wired

740 tokens
Compound Learnings
by parcadei

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

2k tokens
Create Handoff
by parcadei

Create handoff document for transferring work to another session

2k tokens
Dead Code
by parcadei

Find unused functions and dead code in the codebase

423 tokens
Debug Hooks
by parcadei

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

863 tokens
Discovery Interview
by parcadei

Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.

4k tokens
Environment Triage
by parcadei

Environment Triage

271 tokens
Explicit Identity
by parcadei

Explicit Identity Across Boundaries

322 tokens
Explore
by parcadei

Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)

3k tokens
Firecrawl Scrape
by parcadei

Scrape web pages and extract content via Firecrawl MCP

253 tokens
Fix
by parcadei

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

4k tokens
Git Commits
by parcadei

Git Commit Rules

256 tokens
Github Search
by parcadei

Search GitHub code, repositories, issues, and PRs via MCP

265 tokens
Graceful Degradation
by parcadei

Graceful Degradation with Helpful Messages

553 tokens
Help
by parcadei

Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available

3k tokens
Hook Developer
by parcadei

Complete Claude Code hooks reference - input/output schemas, registration, testing patterns

4k tokens
Hooks
by parcadei

Hook Development Rules

344 tokens
Idempotent Redundancy
by parcadei

Idempotent Redundancy

207 tokens
Implement Plan
by parcadei

Implement technical plans from thoughts/shared/plans with verification

5k tokens
Implement Plan Micro
by parcadei

Implement technical plans from thoughts/shared/plans with verification

1k tokens
Implement Task
by parcadei

Implementation agent that executes a single task and creates handoff on completion

2k tokens
Index At Creation
by parcadei

Index at Creation Time

200 tokens
LLM Tuning Patterns
by parcadei

LLM Tuning Patterns

480 tokens
Loogle Search
by parcadei

Search Mathlib for lemmas by type signature pattern

503 tokens
Math Help
by parcadei

Guide to the math cognitive stack - what tools exist and when to use each

3k tokens
Math Router
by parcadei

Deterministic router for math cognitive stack - maps user intent to exact CLI commands

496 tokens
Fields
by parcadei

Problem-solving strategies for fields in abstract algebra

695 tokens
Groups
by parcadei

Problem-solving strategies for groups in abstract algebra

958 tokens
Rings
by parcadei

Problem-solving strategies for rings in abstract algebra

944 tokens
Categories Functors
by parcadei

Problem-solving strategies for categories functors in category theory

472 tokens
Limits Colimits
by parcadei

Problem-solving strategies for limits colimits in category theory

472 tokens
Natural Transformations
by parcadei

Problem-solving strategies for natural transformations in category theory

466 tokens
Analytic Functions
by parcadei

Problem-solving strategies for analytic functions in complex analysis

914 tokens
Contour Integrals
by parcadei

Problem-solving strategies for contour integrals in complex analysis

904 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 79 404 files found on GitHub, 61 763 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: 7 882 skills here share a name with another skill, and two of them cannot sit side by side.