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. 79 566 files from 1 758 authors, of which 61 913 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.

61 913
unique skills
out of 79 566 files found on GitHub
17 653
are copies
same content, someone else's repository
1 739
tokens, median
what a typical skill costs you in context
7 886
name collisions
two skills with one name cannot sit side by side

16 861–16 920 of 61 913

page 282 of 1 032
Feature Flag Patterns
by vibeeval

Gradual rollout strategies, kill switches, A/B testing integration, flag lifecycle management, and technical debt prevention.

2k tokens
Fix
by vibeeval

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

4k tokens
Form Validation
by vibeeval

React Hook Form + Zod integration, multi-step forms, optimistic validation, server-side error mapping, and file upload patterns.

3k tokens
Firecrawl Scrape
by vibeeval

Scrape web pages and extract content via Firecrawl MCP

264 tokens
Fp Check
by vibeeval

Systematic false positive verification for security findings. Provides structured methodology to confirm or dismiss scanner results, manual audit findings, and automated alerts. Adapted from Trail of Bits. Use when triaging security scan results or verifying audit findings.

2k tokens
Frontend Dev
by vibeeval

| Full-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art. Builds complete, visually striking web pages with real media, advanced motion, and compelling copy. generating media assets (image/video/audio/music), writing conversion copy, creating generative art, or implementing cinematic scroll animations.

1420k tokens scripts
Frontend Patterns
by vibeeval

React, Next.js, TypeScript frontend patterns - component design, state management, performance

1k tokens
Gate Check
by vibeeval

Phase transition validation with artifact checklists, PASS/FAIL/CONDITIONAL gates for workflows

768 tokens
GCP Patterns
by vibeeval

Cloud Run deployment, BigQuery optimization, Pub/Sub patterns, IAM best practices

1k tokens
Git Commits
by vibeeval

Git Commit Rules

268 tokens
Gdpr Compliance
by vibeeval

GDPR compliance - data subject rights, lawful basis, DPIA, privacy by design, breach notification, consent management, cross-border transfers, PII masking

4k tokens
Github Actions Integration
by vibeeval

Claude Code Action entegrasyonu - PR review ve issue-to-fix workflow kurulumu

2k tokens
Github MCP
by vibeeval

GitHub MCP Server ile GitHub API erisimi. Repo, issue, PR, code search, release yonetimi.

2k tokens
Github Search
by vibeeval

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

276 tokens
Golang Patterns
by vibeeval

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

4k tokens
Golang Testing
by vibeeval

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.

4k tokens
Graceful Degradation
by vibeeval

Graceful Degradation with Helpful Messages

575 tokens
Graphql Patterns
by vibeeval

Schema design, resolver patterns, DataLoader, N+1 prevention, and subscription patterns for GraphQL APIs.

1k tokens
Growth Engineering
by vibeeval

Growth engineering - PLG, referral, viral loops, onboarding optimization.

5k tokens
Grpc Patterns
by vibeeval

Protobuf schema design, streaming patterns, interceptor chains, deadline propagation, and error handling for gRPC services.

2k tokens
Harvest Adaptive
by vibeeval

Adaptive content summarization - auto-detect content type and produce relevant summary

613 tokens
Harvest Competitive
by vibeeval

Competitive intelligence - extract features, pricing, tech stack from competitor sites

527 tokens
Harvest Deep Crawl
by vibeeval

Multi-page deep crawling - documentation sites, wikis, knowledge bases

632 tokens
Harvest Monitor
by vibeeval

Web change monitoring - track changes on pages, detect updates, changelog diffs

464 tokens
Harvest Single
by vibeeval

Single page smart extraction - articles, docs, blog posts to clean markdown

392 tokens
Harvest Structured
by vibeeval

Structured data extraction - tables, pricing, products, API endpoints with schema

566 tokens
Help
by vibeeval

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

3k tokens
Hipaa Compliance
by vibeeval

HIPAA compliance - PHI protection, technical/administrative/physical safeguards, minimum necessary standard, BAA requirements, de-identification, access logging

4k tokens
Hook Developer
by vibeeval

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

4k tokens
Hizir
by vibeeval

Hızır'ın kullanım kılavuzu. Tüm komutlar, agent'lar, workflow'lar, sistemler burada. /hizir yaz, her şeyi gör.

2k tokens
Hooks
by vibeeval

Hook Development Rules

361 tokens
Idempotent Redundancy
by vibeeval

Idempotent Redundancy

214 tokens
Implement Plan Micro
by vibeeval

Implement technical plans from thoughts/shared/plans with verification

1k tokens
Implement Plan
by vibeeval

Implement technical plans from thoughts/shared/plans with verification

3k tokens
Implement Task
by vibeeval

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

2k tokens
Incident Response Patterns
by vibeeval

Incident severity classification, runbook templates, root cause analysis, and post-incident review

719 tokens
Index At Creation
by vibeeval

Index at Creation Time

207 tokens
Insecure Defaults
by vibeeval

Detect fail-open configurations, hardcoded secrets, weak authentication defaults, permissive CORS, disabled security features, and other insecure-by-default patterns. Adapted from Trail of Bits. Use during security review or when auditing configuration and initialization code.

2k tokens
Iterative Retrieval
by vibeeval

Pattern for progressively refining context retrieval to solve the subagent context problem

2k tokens
Java Coding Standards
by vibeeval

Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.

917 tokens
Jpa Patterns
by vibeeval

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.

1k tokens
Knowledge Graph
by vibeeval

Knowledge graph integration for token-efficient codebase understanding. Uses codebase-memory MCP for AST indexing, dependency graphs, and smart context selection. 6-71x token savings vs raw file reading.

743 tokens
Kafka Patterns
by vibeeval

Topic design, partition strategies, consumer group patterns, exactly-once processing, and dead letter queue handling.

2k tokens
Kotlin Patterns
by vibeeval

Coroutine patterns, Flow operators, Jetpack Compose state management, Ktor routing, and Kotlin Multiplatform shared code.

2k tokens
Knowledge Management
by vibeeval

Proje bilgisini 4 katmanli yapida organize et. Aktif projeler, sorumluluk alanlari, referans kaynaklar ve arsiv. Progressive summarization ile bilgiyi katman katman ozumse. Second brain pattern'i ile codebase bilgisini yapilandir.

2k tokens
Kubernetes Patterns
by vibeeval

Pod design patterns, sidecar containers, init containers, config management, rolling updates, and resource limits.

2k tokens
Kvkk Compliance
by vibeeval

KVKK and GDPR compliance patterns - consent management, right to erasure, breach notification, audit logging, cookie consent, and data classification.

3k tokens
Layered Recall
by vibeeval

Progressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs only > summary > full. 10-50x token savings through fetch-on-confirmation pattern.

1k tokens
Learn
by vibeeval

Hizlica kural/ogrenim kaydet. CLAUDE.md'ye ve memory'ye yazar. Kullanim: /learn <kural>

502 tokens
LLM Tuning Patterns
by vibeeval

LLM Tuning Patterns

498 tokens
Load Testing Patterns
by vibeeval

k6 script templates, load profiles, response time thresholds, SLO validation, and performance testing strategies.

2k tokens
Loogle Search
by vibeeval

Search Mathlib for lemmas by type signature pattern using Loogle.

528 tokens
Math Help
by vibeeval

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

3k tokens
Marketing Analytics
by vibeeval

Marketing analytics - UTM, attribution, CAC, ROAS, conversion tracking.

5k tokens
Math
by vibeeval

Unified math capabilities - computation, solving, and explanation. I route to the right tool.

2k tokens
Math Router
by vibeeval

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

513 tokens
Math
by vibeeval

Multi-layer cognitive stack for machine-verified mathematical problem solving across 14 sub-disciplines.

37k tokens
Fields
by vibeeval

Problem-solving strategies for fields in abstract algebra

712 tokens
Rings
by vibeeval

Problem-solving strategies for rings in abstract algebra

961 tokens
Categories Functors
by vibeeval

Problem-solving strategies for categories functors in category theory

488 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: 11 350 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 79 566 files found on GitHub, 61 913 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: 7 886 skills here share a name with another skill, and two of them cannot sit side by side.