Avotokyo Workflows
heyq02/simpleicons.dev
Use avotokyo/workflows reusable GitHub Actions for TypeScript/Vite+ projects.
Detecta riscos básicos de segurança em repositórios (segredos expostos, configurações perigosas, padrões inseguros) e gera recomendações com evidências.
Install Security Hygiene
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add glaucia86/repocheckai --skill security-hygiene -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install glaucia86/repocheckai security-hygiene --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/glaucia86/repocheckai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/security-hygiene .claude/skills/security-hygiene && 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 "security-hygiene" agent skill from https://github.com/glaucia86/repocheckai/tree/main/.github/skills/security-hygiene into .claude/skills/security-hygiene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hygiene", 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/glaucia86/repocheckai/tree/main/.github/skills/security-hygieneType 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 glaucia86/repocheckai --skill security-hygiene -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install glaucia86/repocheckai security-hygiene --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glaucia86/repocheckai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/security-hygiene .agents/skills/security-hygiene && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "security-hygiene" agent skill from https://github.com/glaucia86/repocheckai/tree/main/.github/skills/security-hygiene into .agents/skills/security-hygiene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hygiene", 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 glaucia86/repocheckai --skill security-hygiene -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install glaucia86/repocheckai security-hygiene --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glaucia86/repocheckai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/security-hygiene .cursor/skills/security-hygiene && 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 "security-hygiene" agent skill from https://github.com/glaucia86/repocheckai/tree/main/.github/skills/security-hygiene into .cursor/skills/security-hygiene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hygiene", 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/glaucia86/repocheckai.git --path .github/skills/security-hygiene--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 glaucia86/repocheckai --skill security-hygiene -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install glaucia86/repocheckai security-hygiene --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glaucia86/repocheckai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/security-hygiene .gemini/skills/security-hygiene && 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 "security-hygiene" agent skill from https://github.com/glaucia86/repocheckai/tree/main/.github/skills/security-hygiene into .gemini/skills/security-hygiene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hygiene", 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 glaucia86/repocheckai security-hygieneInstalls 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 glaucia86/repocheckai --skill security-hygiene -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/glaucia86/repocheckai.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/security-hygiene .github/skills/security-hygiene && 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 "security-hygiene" agent skill from https://github.com/glaucia86/repocheckai/tree/main/.github/skills/security-hygiene into .github/skills/security-hygiene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hygiene", 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 glaucia86/repocheckai --skill security-hygiene -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install glaucia86/repocheckai security-hygiene --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/glaucia86/repocheckai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/security-hygiene .opencode/skills/security-hygiene && 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 "security-hygiene" agent skill from https://github.com/glaucia86/repocheckai/tree/main/.github/skills/security-hygiene into .opencode/skills/security-hygiene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-hygiene", 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.
Facts
- Skill name
security-hygiene- GitHub stars
- 121
- Token cost
- ~819 tokens
- SKILL.md length
- 365 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- MIT
At a glance
Detecta riscos básicos de segurança em repositórios (segredos expostos, configurações perigosas, padrões inseguros) e gera recomendações com evidências.
- Works in 3 steps: Identifique sinais de segredos → Revise GitHub Actions → Revise código de risco
- DevOps & Cloud work in your project
- SKILL.md covers Quando usar esta skill, Escopo (o que está dentro), Entradas esperadas and Como analisar (passo a passo), plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Security Hygiene is an agent skill from glaucia86/repocheckai. Detecta riscos básicos de segurança em repositórios (segredos expostos, configurações perigosas, padrões inseguros) e gera recomendações com evidências.
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud. It works with GitHub Actions and TypeScript. The repository describes itself as: Agentic CLI Tool for GitHub Repository Health Analysis. The licence is MIT.
When your agent uses it
- DevOps & Cloud work in your project
Example prompts
- “/security-hygiene”
Requirements
- Node.js
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Identifique sinais de segredos
- Revise GitHub Actions
- Revise código de risco
What it can do on your machine
Read from SKILL.md and the folder at commit dfc3830. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Security Hygiene loads about 819 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 365 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.
Safety
Auto-check: warnings
The automated check found patterns that need a careful read before installing.
- NoteMentions a .env fileSKILL.md:17
gredos versionados e arquivos suspeitos (.env, credentials, dumps) - NoteMentions a .env fileSKILL.md:30
- arquivos `.env*` (se existirem) - WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:36
tos: `.env`, `secrets`, `credentials`, `id_rsa`
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.
SKILL.md
The full file from glaucia86/repocheckai at commit dfc3830, republished under its MIT licence (© glaucia86). 365 words, ~819 tokens.
Download SKILL.mdSave it as
.claude/skills/security-hygiene/SKILL.md (or your agent's skills folder).- name
- security-hygiene
- description
- Detecta riscos básicos de segurança em repositórios (segredos expostos, configurações perigosas, padrões inseguros) e gera recomendações com evidências.
Skill: Security Hygiene (Repo Doctor)
Quando usar esta skill
Use esta skill quando o objetivo for:
- Encontrar segredos expostos (tokens, chaves, credenciais) no repositório
- Identificar configurações inseguras em CI/CD (GitHub Actions) e scripts
- Detectar padrões de código potencialmente perigosos (ex.: eval, child_process sem validação)
- Gerar recomendações curtas e acionáveis, sempre com evidência
Escopo (o que está dentro)
✅ Inclui:
- Procura de segredos versionados e arquivos suspeitos (.env, credentials, dumps)
- Revisão de workflows do GitHub Actions (permissões, uso de secrets, ações não pinadas)
- Heurísticas de risco em Node.js/TypeScript (exec, eval, deserialização insegura)
❌ Não inclui:
- Pentest, exploração, ou prova de conceito
- Auditoria completa de dependências por CVE (a menos que o projeto já integre scanners)
Entradas esperadas
- Árvore de arquivos do repo
- Conteúdo de:
.github/workflows/*package.json(+ lockfile se existir)- arquivos
.env*(se existirem) - código-fonte relevante (TS/JS)
Como analisar (passo a passo)
Identifique sinais de segredos
- Procure por padrões comuns de tokens (ex.:
ghp_,xoxb-,AIza,sk-, etc.) - Verifique commits/arquivos com nomes suspeitos:
.env,secrets,credentials,id_rsa
- Procure por padrões comuns de tokens (ex.:
Revise GitHub Actions
- Verifique permissões (
permissions:) e prefira mínimo privilégio - Sinalize ações não pinadas por SHA
- Verifique
pull_request_targete contextos perigosos - Avalie exposição de secrets em steps/logs
- Verifique permissões (
Revise código de risco
eval,Function(),child_process.exec,spawncom input externoJSON.parseem payloads não confiáveis sem validação- URLs/redirects sem allowlist
Show full SKILL.md (151 more words)Show less
Regras obrigatórias (qualidade)
Cada achado deve incluir:
- arquivo + range de linhas
- explicação do risco (clara e curta)
- recomendação prática (com passos)
- severidade: S0/S1/S2/S3
- prioridade: P0/P1/P2/P3
Não faça suposições sobre intenção do autor.
Evite “corrigir tudo”: foque no que é mais provável e mais impactante.
Formato de saída (achados)
Use este template por achado:
[Sx/Py] Título curto do risco
- Arquivo:
path/to/file.ts:L10-L42 - Evidência: (1–3 linhas relevantes, sem despejar arquivos longos)
- Risco: explicação objetiva (1 parágrafo)
- Recomendação: passos acionáveis (bullets)
- Critérios de aceite: como validar que foi resolvido
Sugestões de remediação (padrões)
- Secrets:
- Remover do histórico (se necessário)
- Rotacionar credenciais
- Introduzir
.env.examplee secrets via CI/Actions
- GitHub Actions:
- Pin por SHA
permissions: read-all→ mínimo necessário- Revisar
pull_request_target
- Código:
- Validar input com schema (ex.: zod)
- Allowlist de comandos/paths
- Evitar
eval
Limites e cuidado
- Se houver achado de segredo real: trate como S0/P0 e recomende rotação imediata.
- Não exponha tokens completos no relatório: mascare (ex.:
ghp_****).
© glaucia86, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .github/skills/security-hygiene of glaucia86/repocheckai.
Open the folder on GitHubat commit dfc3830
Compare with similar skills
Security Hygiene 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 |
|---|---|---|---|---|---|---|
| Security Hygiene this skillglaucia86/repocheckai | 121 | — | ~819 | Automated safety check: Warn | MIT | |
| Avotokyo Workflowsheyq02/simpleicons.dev | 171 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Kitaru Releasezenml-io/kitaru | 302 | — | ~7k | Automated safety check: Pass | Apache-2.0 | |
| Configuration GeneratorArabelaTso/Skills-4-SE | 253 | — | ~2.8k | Automated safety check: Notes | Apache-2.0 | |
| Workflow Setupathola/claude-night-market | 341 | — | ~1.4k | Automated safety check: Pass | MIT | |
| GitHub Actions Supply Chain Pinningasyncapi/generator | 1.1k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Kitaru Release
zenml-io/kitaru
Discover dependencies and prepare or execute Kitaru core and plugin releases, including version proposals, Kitaru UI selection, release PRs, ordered tag commands, artifact verification, and recovery.
Configuration Generator
ArabelaTso/Skills-4-SE
Generate configuration files for applications, services, and infrastructure.
Workflow Setup
athola/claude-night-market
Configures GitHub Actions CI/CD workflows for testing, linting, and deployment.
GitHub Actions Supply Chain Pinning
asyncapi/generator
A skill your agent uses when editing, adding, or reviewing any file under .github/workflows/, or when a CI step installs a CLI tool (npm i -g, npx, pipx, uses: /setup-).
Linea Dependency Maintenance
Consensys-Incorporated/linea-attestation-registry
Safely plan and execute dependency maintenance for JavaScript/TypeScript (npm, pnpm) and GitHub Actions, including npm lockfiles, pnpm workspaces, catalogs, overrides, SHA-pinned action versions…
More from glaucia86/repocheckai
All 8 skills in this repoCI Workflow Audit
glaucia86/repocheckai
Avalia pipelines CI/CD, detectando gaps e oportunidades de melhoria.
Code Quality Audit
glaucia86/repocheckai
Analisa padrões de qualidade de código e detecta code smells, complexidade elevada e duplicação.
Dependency Health
glaucia86/repocheckai
Analisa dependências para identificar falta de uso, versões permissivas ou riscos.
Docs Audit
glaucia86/repocheckai
Avalia a documentação (README, CONTRIBUTING, etc.) para encontrar lacunas de clareza e onboarding.
Findings To GitHub Issues
glaucia86/repocheckai
Converte achados de outras skills em issues e comentários prontos para o GitHub.
Repo Health
glaucia86/repocheckai
Analisa o perfil do repositório e extrai um modelo estruturado com evidências para orientar outras análises.
Related
Works with
Categories
Questions about Security Hygiene
What does Security Hygiene do?
Detecta riscos básicos de segurança em repositórios (segredos expostos, configurações perigosas, padrões inseguros) e gera recomendações com evidências. Security Hygiene is an agent skill from glaucia86/repocheckai. Detecta riscos básicos de segurança em repositórios (segredos expostos, configurações perigosas, padrões inseguros) e gera recomendações com evidências.
When should I use Security Hygiene?
Security Hygiene fits situations like: devOps & Cloud work in your project.
How do I install Security Hygiene in Claude Code?
Run `npx skills add glaucia86/repocheckai --skill security-hygiene -a claude-code`. Or copy the skill folder (.github/skills/security-hygiene in glaucia86/repocheckai) into .claude/skills/security-hygiene in your project. Claude Code loads it when a task matches its description.
How do I install Security Hygiene in Codex?
Run `npx skills add glaucia86/repocheckai --skill security-hygiene -a codex`. Or copy the skill folder (.github/skills/security-hygiene in glaucia86/repocheckai) into .agents/skills/security-hygiene in your project. Codex loads it when a task matches its description.
Can I use Security Hygiene in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add glaucia86/repocheckai --skill security-hygiene -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/security-hygiene, .gemini/skills/security-hygiene, .github/skills/security-hygiene and .opencode/skills/security-hygiene in your project.
What does Security Hygiene need to run?
SKILL.md names no scripts, command-line tools or credentials: Security Hygiene is instructions for the agent only. Our summary lists: Node.js.
Does Security Hygiene access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Security Hygiene safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.
What licence does Security Hygiene use?
Security Hygiene is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Security Hygiene use?
About 819 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Security Hygiene?
Skills that share tags, products or a category with Security Hygiene: Avotokyo Workflows (heyq02/simpleicons.dev, 171 stars), Kitaru Release (zenml-io/kitaru, 302 stars), Configuration Generator (ArabelaTso/Skills-4-SE, 253 stars) and Workflow Setup (athola/claude-night-market, 341 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Security Hygiene?
glaucia86 (a GitHub user) maintains it in glaucia86/repocheckai, which has 121 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on July 8, 2026.
Source: glaucia86/repocheckai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.