# skill-governance-loop

skill-governance-loop — a skill for managing other skills: checks quality, compares versions, and decides whether to keep, enable, hide, disable, or remove a given skill from your local collection.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 475 repo stars
- Author: cnfjlhj
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cnfjlhj/ai-collab-playbook/tree/HEAD/skills/full/skill-governance-loop/SKILL.md
- Updated: 2026-10-13
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/skill-governance-loop

## What it does

The skill runs an audit cycle: it examines how a particular skill triggers, compares the local version against the upstream one, and checks for functional overlap with other skills. The output is a single action: keep, enable, hide, disable, merge with a similar skill, split into two, or archive.

The audit starts from a concrete problem — poor triggering, redundancy, or an update request — rather than abstract best practices. The skill separates three questions: what changed in the upstream version, whether to adopt those changes, and what to do with the result (enable, hide, or leave it installed but off).

This skill is not for broad inventory scans of many skills at once. It works with one skill or a small target set when you need a decision for a specific unit.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill skill-governance-loop -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/skill-governance-loop/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/skill-governance-loop/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill skill-governance-loop -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/skill-governance-loop/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill skill-governance-loop -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/skill-governance-loop/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install cnfjlhj/ai-collab-playbook skills/full/skill-governance-loop
```

2. **Manually: put the files in place**
- File: `.github/skills/skill-governance-loop/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill skill-governance-loop -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/cnfjlhj/ai-collab-playbook --path skills/full/skill-governance-loop
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/skill-governance-loop/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/cnfjlhj/ai-collab-playbook/tree/HEAD/skills/full/skill-governance-loop/SKILL.md

## When to use it
- check skill quality and decide whether to keep or remove it
- compare a local skill version against the upstream repository
- find out whether two skills duplicate each other's function
- diagnose why a skill triggers in the wrong context

## Example prompts
- Check `skill-governance-loop` and tell me whether to keep or remove it
- Compare the local `pdf-generator` against the repo version and decide whether to update
- Look at `report-builder` and `csv-exporter` and see if one of them is redundant

## Similar
- [governance-audit](https://affpapa.org/en/nevibecode/hooks/governance-audit.md) — hook · ★ 41430 repo stars
- [Agent Governance Reviewer](https://affpapa.org/en/nevibecode/agents/agent-governance-reviewer.md) — subagent · ★ 41430 repo stars
- [sidclaw-governance-mcp](https://affpapa.org/en/nevibecode/mcp/sidclaw-governance-mcp.md) — MCP server · ★ 15 repo stars
- [oss-governance](https://affpapa.org/en/nevibecode/skills/oss-governance.md) — skill · 13700 installs
- [design-system-governance](https://affpapa.org/en/nevibecode/skills/design-system-governance.md) — skill · 2100 installs
- [alibabacloud-governance-evaluation-report](https://affpapa.org/en/nevibecode/skills/alibabacloud-governance-evaluation-report.md) — skill · 241 installs

From the same set: [cnfjlhj/ai-collab-playbook](https://affpapa.org/en/nevibecode/by/cnfjlhj/ai-collab-playbook.md) — 18 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
