Governance Skill para Claude Code
wrsmith108/governance-claude-skill
Enforça standards de código e governança com ativação proativa
Ver no GitHubSkill de agente para enforçar padrões de engenharia e governança de código. Fornece lembretes proativos durante code reviews e commits, com checklists de PR, verificação de configuração e templates prontos para uso.
Instalação
npx convez-ai wrsmith108/governance-claude-skill1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Code review automatizado com checklists padronizados
- Validação de commits contra padrões de projeto
- Retrospectivas técnicas com templates de governança
- Auditoria de conformidade de código
- Documentação de políticas de engenharia
Veredito

Skill bem estruturado com modelo de dois documentos (operacional + policy) que reduz consumo de tokens. Ativação por trigger, verificação de setup e templates prontos para uso tornam a adoção prática, embora exija config inicial em CLAUDE.md e standards.md no projeto.
README
A tradução para o português deste README ainda está na fila.
Governance Skill for Claude Code
An agent skill for enforcing engineering standards and code governance. Provides proactive reminders during code reviews and commits.
Features
- Proactive Triggers — Activates on "code review", "commit", "standards", "compliance", "retro",
- Two-Document Model — Separates CLAUDE.md (operational) from standards.md (policy)
- Setup Verification —
scripts/governance-check.mjsvalidates configuration with actionable fixes - Anti-Pattern Tables — Code quality, documentation, workflow, and testing anti-patterns
- Pre-Commit Checklist — Reminds about typecheck, lint, test before commits
- PR Review Checklist — Standards for code review (correctness, security, performance)
- Ready-to-Use Default —
standards.mdworks out of the box; extend with your own rules - No Custom Agent Required — Uses the built-in
reviewersubagent type (v2.1+)
Quick Start
Option A: Claude Plugin (Recommended)
claude plugin add github:wrsmith108/governance-claude-skill
Option B: Manual Installation
git clone https://github.com/wrsmith108/governance-claude-skill ~/.claude/skills/governance
Verify Setup
node scripts/governance-check.mjs
How It Works
When your agent (such as Claude) detects trigger phrases like "code review", "commit", "standards", or "compliance", this skill activates and provides:
- Quick reference to relevant standards
- Reminder to run
npm run audit:standards - Checklists for PRs and commits
- Links to authoritative documentation
The skill delegates to the built-in reviewer subagent for context efficiency (70–90% token savings vs. inline execution).
File Structure
governance-claude-skill/
├── .claude/
│ └── agents/
│ └── governance-specialist.md # repo-local development agent
├── scripts/
│ └── governance-check.mjs # setup verification script
├── templates/
│ ├── standards-template.md # full-featured standards template
│ └── audit-standards-template.mjs # configurable audit script
├── agent-prompt.md # full agent protocol
├── SKILL.md # thin dispatcher (v2.1.0)
└── standards.md # minimal working default
Note: .claude/agents/governance-specialist.md is kept for repo-local development use only. It is NOT required for the skill to work — the skill uses the built-in reviewer subagent type.
The Two-Document Model
| Document | Purpose | Update Frequency |
|---|---|---|
| CLAUDE.md | AI operational context (commands, URLs) | Frequent |
| standards.md | Engineering policy (authoritative) | Infrequent |
Benefits:
- CLAUDE.md stays lean (better token efficiency)
- standards.md is the single source of truth for policy
Setting Up in Your Project
-
Install the skill (see Quick Start above)
-
Copy the starter standards.md to your project:
cp ~/.claude/skills/governance/standards.md standards.md # Or to the traditional location: cp ~/.claude/skills/governance/standards.md docs/architecture/standards.mdEdit it with your project-specific rules. Full template at
templates/standards-template.md. -
Add CLAUDE.md at project root with build commands and a cross-reference:
> **Standards**: [standards.md](standards.md) -
Create audit script for automated compliance:
cp ~/.claude/skills/governance/templates/audit-standards-template.mjs scripts/audit-standards.mjs # Add to package.json: "audit:standards": "node scripts/audit-standards.mjs" -
Run setup check:
node scripts/governance-check.mjs
Governance Check Output
🏛️ Governance Setup Check
1. CLAUDE.md (AI Operational Context)
✓ CLAUDE.md exists
✓ Has build commands section
✓ References standards.md
✓ Concise length (452 lines)
2. standards.md (Engineering Policy)
✓ standards.md found at root
✓ Has Code Quality section
✓ Has Testing section
✓ Has Workflow section
3. Audit Script (Automated Compliance)
✓ npm run audit:standards configured
✓ Audit script exists
4. Architecture Decision Records
✓ docs/adr/ directory exists
✓ ADR template exists
5. Pre-commit Hooks
✓ Husky pre-commit hook configured
✓ Hook runs quality checks
6. Governance Skill
✓ Governance skill installed
Governance Score: 100%
Anti-Patterns Enforced
Code Quality
| Anti-Pattern | Correct Pattern |
|---|---|
❌ any type | ✅ unknown for external data |
| ❌ 600+ line files | ✅ Split at 500 lines |
| ❌ Hardcoded secrets | ✅ Environment variables |
Workflow
| Anti-Pattern | Correct Pattern |
|---|---|
| ❌ Commit to main | ✅ Feature branches with PR |
| ❌ Skip audit | ✅ Run audit:standards before commit |
| ❌ Defer issues | ✅ Fix immediately |
Changelog
See CHANGELOG.md for full history.
Contributing
Contributions welcome! Please submit issues and PRs.
License
MIT License — See LICENSE
Credits
Created for the Claude Code community. Patterns refined through real-world governance of AI-assisted development projects.