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

57 841–57 900 of 61 713

page 965 of 1 029

Sort Most copied

快照管理

Azure CLI 操作

PostgreSQL 数据库管理

Elasticsearch 集群管理

Redis 数据库管理

SQL 优化与调优

Google Cloud CLI 操作

MongoDB 数据库管理

MySQL 数据库管理与运维

Ansible 自动化运维

Git 高级操作

CI/CD 流水线配置

Docker Compose 编排

Terraform 基础设施即代码

Docker 容器操作与管理

监控与告警

Dockerfile 编写最佳实践

Docker 镜像管理

Docker 容器网络

Kubernetes ConfigMap 与 Secret

2k tokens

Deployment

by chaterm

Kubernetes Deployment 管理

kubectl 基础操作与常用命令

Helm 包管理

Kubernetes Pod 管理与调试

Kubernetes Service 与 Ingress

Kubernetes 故障排查

Linux file and directory operations

1k tokens

Network Tools

by chaterm

Linux network tools and diagnostics

1k tokens

Process Management

by chaterm

Linux process management and control

Bash Shell 脚本编写

Linux system administration and monitoring

511 tokens

User Permissions

by chaterm

Linux user and permission management

DNS 配置与排查

负载均衡配置

流量分析与抓包

代理服务器配置

TCP/IP 网络诊断与排查

VPN 配置与管理

OpenClaw 运维与故障修复

OpenClaw 配置管理

OpenClaw 安装与部署

OpenClaw 问题排查与诊断

性能基准测试

性能问题排查

性能分析

防火墙配置

安全审计

系统调优

系统加固

SSL/TLS 证书

Apache HTTP Server 配置

定时任务管理

日志分析与处理

SSH 管理与安全

Systemd 服务管理

Nginx configuration and optimization

1k tokens

Secscan

by atgreen

In-session, token-efficient LLM security scan of a repo (SAST triage). A lightweight, native Claude Code pipeline — survey → threat-model → deep-dive → adversarial-verify → report — using Read/Grep/Glob (and optional subagents), no external tooling. Use when asked to "security scan", "find vulnerabilities", "SAST", "audit this code for security", or "secscan".

23k tokens

Research Craft

by nik1t7n

> problems, designing ML/AI experiments, reading papers, building experiment loops, analyzing outputs, writing research notes, or turning vague curiosity into a disciplined research plan. Emphasizes avoiding absorbed problems, upgrading information inputs beyond shared reading lists, and reasoning backward from outcomes the researcher genuinely wants to exist.

3k tokens

Kamae

by iwasa-kosui

| Kamae (構え) — robust server-side TypeScript design. Functional domain modeling with discriminated unions, pure state transitions, Result types, schema-validated boundaries, and PII protection. error handling, boundary validation, or PII handling on the server side; designing types for business logic; implementing entity/value-object semantics in TS. pure infrastructure-as-code; code unrelated to domain logic.

20k tokens scripts

Kamae Review

by iwasa-kosui

| Adversarial code review of server-side TypeScript for adherence to the kamae principles (discriminated unions, branded types, Result error handling, boundary validation, PII protection). involving domain models, repositories, use cases, business logic, or boundary code. unrelated to domain logic.

4k 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.