Agent Setup Health Audit
tw93/Waza
Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.
Especialista profundo em Claude Code - CLI da Anthropic. An agent skill from majiayu000/claude-skill-registry.
$ npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install majiayu000/claude-skill-registry claude-code-expert --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-llm/claude-code-expert .claude/skills/claude-code-expert && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "claude-code-expert" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/claude-code-expert into .claude/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/claude-code-expertType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install majiayu000/claude-skill-registry claude-code-expert --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ai-llm/claude-code-expert .agents/skills/claude-code-expert && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/claude-code-expert into .agents/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install majiayu000/claude-skill-registry claude-code-expert --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ai-llm/claude-code-expert .cursor/skills/claude-code-expert && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "claude-code-expert" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/claude-code-expert into .cursor/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/majiayu000/claude-skill-registry.git --path skills/ai-llm/claude-code-expert--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install majiayu000/claude-skill-registry claude-code-expert --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ai-llm/claude-code-expert .gemini/skills/claude-code-expert && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/claude-code-expert into .gemini/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install majiayu000/claude-skill-registry claude-code-expertInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ai-llm/claude-code-expert .github/skills/claude-code-expert && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/claude-code-expert into .github/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install majiayu000/claude-skill-registry claude-code-expert --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ai-llm/claude-code-expert .opencode/skills/claude-code-expert && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "claude-code-expert" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/claude-code-expert into .opencode/skills/claude-code-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claude-code-expert", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
claude-code-expertEspecialista profundo em Claude Code - CLI da Anthropic. An agent skill from majiayu000/claude-skill-registry.
Claude Code Expert is an agent skill from majiayu000/claude-skill-registry. Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`).
It sits in Agent Workflows, covering Agent instruction files and MCP servers. The repository describes itself as: Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 2d14a69. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
claudepythonnpmFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
docs.anthropic.comgithub.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
ANTHROPIC_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Claude Code Expert loads about 4k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 1,111 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
"Bash(sudo *)",Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from majiayu000/claude-skill-registry at commit 2d14a69, republished under its MIT licence (© majiayu000). 1,111 words, ~4,031 tokens.
.claude/skills/claude-code-expert/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas. Ativar para: configurar Claude Code, criar hooks, otimizar CLAUDE.md, usar MCPs, criar sub-agentes, resolver erros do CLI, workflows avancados, duvidas sobre qualquer feature.
Voce e o especialista definitivo em Claude Code. Seu objetivo e transformar cada sessao em uma experiencia 10x mais poderosa, rapida e inteligente.
Claude Code e a CLI oficial da Anthropic para usar Claude como agente de codigo diretamente no terminal. Diferente do Claude.ai web, o Claude Code:
npm install -g @anthropic-ai/claude-code
claude # iniciar sessao interativa
claude "sua tarefa aqui" # modo nao-interativo
claude --help # ver todos os flagsclaude -p "prompt" # print mode, ideal para scripts
claude --model claude-opus-4 # especificar modelo
claude --max-tokens 8192 # limite de tokens
claude --no-stream # sem streaming
claude --output-format json # saida em JSON
claude --allowed-tools "Bash,Read,Write" # limitar ferramentas
claude --dangerously-skip-permissions # pular confirmacoes (cuidado!)
claude --max-turns 50 # maximo de turnos autonomosO arquivo CLAUDE.md na raiz do projeto e carregado automaticamente em TODA sessao. E a forma mais poderosa de dar contexto e instrucoes persistentes ao Claude Code.
## Contexto
O que e este projeto, tecnologias, arquitetura
## Comandos Essenciais
Scripts mais usados: npm run dev, pytest, etc.
## Convencoes De Codigo
Estilo, naming, patterns obrigatorios
## Arquitetura
Estrutura de pastas, responsabilidades de cada modulo
## Regras De Negocio Criticas
O que NUNCA fazer, invariantes do sistema
## Agentes E Skills Disponiveis
Lista de skills, quando usar cada uma
## Protocolo Pre-Tarefa
Sempre rodar orchestrator antes de responder~/.claude/projects/<hash-do-path>/memory/
├── MEMORY.md # indice e contexto rapido (max 200 linhas)
├── ai-personas.md # detalhes de personas e skills ativas
├── project-X.md # contexto de projetos especificos
└── decisions.md # decisoes tecnicas importantesCarregar antes de qualquer tarefa: memory/MEMORY.md Para projetos ativos: memory/ai-personas.md
Ao final de sessoes longas, execute: python context-agent/scripts/context_manager.py save
## Context Guardian - Prevenir Perda De Contexto
O context-guardian skill monitora compactacao automatica e salva snapshots.
Ativar no inicio de sessoes longas ou criticas.
---
## 4. Hooks - Automacao Poderosa
Hooks executam comandos automaticamente em eventos do Claude Code.
## Localizacao Dos Hooks
- Global: ~/.claude/settings.json
- Por projeto: .claude/settings.json (na raiz do projeto)
## Tipos De Hooks Disponiveis
| Hook | Quando Dispara |
|------|----------------|
| PreToolUse | Antes de qualquer ferramenta ser usada |
| PostToolUse | Apos qualquer ferramenta ser usada |
| Notification | Ao receber notificacao do sistema |
| Stop | Quando o agente para de responder |
| SubagentStop | Quando sub-agente para |
## Exemplo: Hook De Beep Ao Terminar
```json
{
"hooks": {
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "powershell -c \\"[Console]::Beep(800,300)\\""
}
]
}
]
}
}{
"hooks": {
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "echo dated-action >> ~/.claude/action_log.txt"
}
]
}
]
}
}{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python C:/Users/renat/skills/cred-omega/scripts/secret_scanner.py --staged 2>/dev/null || true"
}
]
}
]
}
}cat ~/.claude/settings.json
python -m json.tool ~/.claude/settings.json # valida o JSONMCP (Model Context Protocol) permite adicionar ferramentas externas ao Claude Code. Cada MCP server expoe novas ferramentas que o Claude pode usar nas sessoes.
claude mcp add filesystem # acesso expandido a arquivos
claude mcp add github # integracao com GitHub (PRs, issues)
claude mcp add postgres # queries SQL em banco Postgres
claude mcp add sqlite # queries SQL em SQLite
claude mcp list # listar MCPs instalados
claude mcp get nome-servidor # detalhes de um MCP especifico
claude mcp remove nome # remover um MCP| MCP | Funcao Principal |
|---|---|
| filesystem | Acesso expandido a arquivos alem do projeto |
| github | PRs, issues, commits, reviews via Claude |
| postgres / sqlite | Consultas SQL diretas sem sair do Claude |
| puppeteer / playwright | Automacao de browser e web scraping |
| slack | Notificacoes e mensagens em canais |
| fetch | HTTP requests diretos para APIs |
// mcp-server.js
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
const server = new Server({ name: "meu-mcp", version: "1.0.0" });
server.setRequestHandler("tools/call", async (req) => {
if (req.params.name === "minha_ferramenta") {
return { content: [{ type: "text", text: "resultado" }] };
}
});
const transport = new StdioServerTransport();
await server.connect(transport);claude mcp add meu-mcp node /caminho/para/mcp-server.jsO Claude Code pode criar sub-agentes via Task tool para trabalho paralelo. Cada sub-agente roda de forma independente com seu proprio contexto.
Spawn paralelo (multiplas tarefas simultaneas): Use Task tool com run_in_background: true para cada tarefa independente. Exemplo com 3 agentes em paralelo:
Tipos de sub-agente:
Isolation com git worktree: Use isolation: worktree para que o sub-agente trabalhe em branch isolada. Ideal para: experimentos, refatoracoes arriscadas, POCs sem risco ao main.
{
"permissions": {
"allow": [
"Bash(git *)",
"Bash(npm *)",
"Read(*)",
"Write(src/**)"
],
"deny": [
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(curl *remote-installer*)"
]
}
}claude --dangerously-skip-permissions # pula TODAS as confirmacoes
claude --allowed-tools "Read,Write,Bash" # apenas estas ferramentas
claude --disallowed-tools "WebFetch" # bloquear especificasApenas em: CI/CD controlados, scripts automatizados, sandboxes isoladas. NUNCA usar em: producao, repos com segredos, ambientes compartilhados.
## Fase 1: Briefing E Planejamento
claude -p "analise a feature X e crie um plano detalhado de implementacao"
## Fase 2: Implementacao
claude "implemente a feature X seguindo o plano gerado"
## Fase 3: Testes
claude "escreva testes completos para a feature X implementada"
## Fase 4: Code Review
claude "faca code review da feature X, identifique problemas e refine"claude --max-turns 100 "complete o ciclo completo de desenvolvimento da feature X"#\!/bin/bash
echo "Carregando contexto do projeto..."
claude -p "leia memory/MEMORY.md e me da um briefing completo do estado atual"
## .Github/Workflows/Claude-Review.Yml
- name: Claude Code Review
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
run: |
claude -p "revise o diff deste PR, identifique bugs e problemas de seguranca" \n --output-format json \n --no-stream \n --max-turns 5| Problema | Causa Provavel | Solucao |
|---|---|---|
| API key not found | ANTHROPIC_API_KEY nao configurada | export ANTHROPIC_API_KEY=sk-ant-... |
| Timeout em tarefas longas | max-turns insuficiente | Adicionar --max-turns 100 |
| Context window cheio | Muitos arquivos no contexto | Usar sub-agentes com contexto focado |
| Sub-agente nao acha arquivo | Path relativo errado | Usar path absoluto sempre |
| Hook nao executa | JSON invalido em settings.json | python -m json.tool ~/.claude/settings.json |
| MCP nao conecta | Servidor MCP nao iniciado | claude mcp list e checar status |
| Compactacao inesperada | Sessao muito longa | Usar context-guardian skill |
| Erro de permissao em Bash | Tool nao permitida | Adicionar ao allow em settings.json |
ls ~/.claude/projects/
ls ~/.claude/projects/<hash>/
cat ~/.claude/projects/<hash>/*.jsonl | python -m json.tool{
"theme": "dark",
"verbose": false,
"cleanupPeriodDays": 30,
"hooks": {
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "powershell -c \\"[Console]::Beep(800,200); Start-Sleep -Milliseconds 100; [Console]::Beep(1000,200)\\""
}
]
}
]
},
"permissions": {
"allow": [
"Bash(git *)",
"Bash(npm *)",
"Bash(python *)",
"Bash(powershell *)",
"Read(*)",
"Write(*)"
]
}
}export ANTHROPIC_API_KEY=sk-ant-SUA_CHAVE_AQUI
export CLAUDE_CODE_MAX_OUTPUT_TOKENS=8192
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 # modo privadopython agent-orchestrator/scripts/scan_registry.py # atualizar registry
python agent-orchestrator/scripts/match_skills.py "tarefa" # identificar skills
python task-intelligence/scripts/pre_task_check.py "tarefa" # briefing
python context-agent/scripts/context_manager.py save # salvar contexto
python context-agent/scripts/context_manager.py load # carregar contextoEsta skill e ativada automaticamente quando o usuario quer:
| Comando | Acao |
|---|---|
| /status | Ver estado atual da sessao e contexto |
| /clear | Limpar historico da conversa atual |
| /compact | Compactar contexto (Claude resume o historico) |
| /memory | Ver e editar arquivos de memoria |
| /hooks | Ver hooks configurados e ativos |
| /mcp | Ver MCPs conectados e seus status |
| /cost | Ver custo em tokens e USD da sessao |
| /model | Trocar modelo em uso (opus, sonnet, haiku) |
| /help | Ver todos os comandos e atalhos disponiveis |
007 - Complementary skill for enhanced analysismatematico-tao - Complementary skill for enhanced analysis© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/ai-llm/claude-code-expert of majiayu000/claude-skill-registry.
Open the folder on GitHubat commit 2d14a69
We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.
Claude Code Expert next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Claude Code Expert this skillmajiayu000/claude-skill-registry | 666 | 4 repos | ~4k | Automated safety check: Notes | MIT | |
| Agent Setup Health Audittw93/Waza | 7.2k | — | ~5.2k | Automated safety check: Notes | MIT | |
| Semantix GuideGnosil/semantix | 821 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Working With Claude Code Docsobra/superpowers-developing-for-claude-code | 142 | — | ~1.5k | Automated safety check: Pass | None | |
| Agnixagent-sh/agnix | 445 | — | ~874 | Automated safety check: Pass | Apache-2.0 | |
| Claude Docs Consultantcentminmod/my-claude-code-setup | 2.7k | — | ~959 | Automated safety check: Pass | MIT |
tw93/Waza
Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.
Gnosil/semantix
Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project…
obra/superpowers-developing-for-claude-code
Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.
agent-sh/agnix
A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.
centminmod/my-claude-code-setup
Consult official Claude Code documentation from code.claude.com using selective fetching.
yoloshii/ClawMem
ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring…
majiayu000/claude-skill-registry
Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry.
majiayu000/claude-skill-registry
Neural search via Exa MCP for web, code, and company research.
majiayu000/claude-skill-registry
Unified media generation via fal.ai MCP — image, video, and audio.
majiayu000/claude-skill-registry
Interact with Zotero reference management libraries using the pyzotero Python client.
majiayu000/claude-skill-registry
Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.
majiayu000/claude-skill-registry
Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner.
Categories
Especialista profundo em Claude Code - CLI da Anthropic. An agent skill from majiayu000/claude-skill-registry. Claude Code Expert is an agent skill from majiayu000/claude-skill-registry. Especialista profundo em Claude Code - CLI da Anthropic.
Claude Code Expert fits situations like: tasks that involve Agent instruction files; tasks that involve MCP servers.
Run `npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a claude-code`. Or copy the skill folder (skills/ai-llm/claude-code-expert in majiayu000/claude-skill-registry) into .claude/skills/claude-code-expert in your project. Claude Code loads it when a task matches its description.
Run `npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a codex`. Or copy the skill folder (skills/ai-llm/claude-code-expert in majiayu000/claude-skill-registry) into .agents/skills/claude-code-expert in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add majiayu000/claude-skill-registry --skill claude-code-expert -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-code-expert, .gemini/skills/claude-code-expert, .github/skills/claude-code-expert and .opencode/skills/claude-code-expert in your project.
Going by SKILL.md and its folder, Claude Code Expert needs the command-line tools its instructions call (claude, python and npm) and credentials named ANTHROPIC_API_KEY. Our summary lists: Python 3; Node.js; A credential in ANTHROPIC_API_KEY.
SKILL.md names 2 domains. As links in the text: docs.anthropic.com and github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Claude Code Expert is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Claude Code Expert: Agent Setup Health Audit (tw93/Waza, 7.2k stars), Semantix Guide (Gnosil/semantix, 821 stars), Working With Claude Code Docs (obra/superpowers-developing-for-claude-code, 142 stars) and Agnix (agent-sh/agnix, 445 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
majiayu000 (a GitHub user) maintains it in majiayu000/claude-skill-registry, which has 666 GitHub stars. The repository holds 1,273 skills in this directory. The repository was last updated on October 7, 2026.
Source: majiayu000/claude-skill-registry on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.