skill-governance-loop
- Repo stars 288
- Author updated Live
- Author repo ai-collab-playbook
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @cnfjlhj · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: skill-governance-loop
description: Use when the user asks to review a skill, analyze skill quality, update a skill version, or run…
category: engineering
runtime: no special runtime
---
# skill-governance-loop output preview
## PART A: Task fit
- Use case: Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disable/archive decision loop from real failures instead of abstract best practices. Use this skill for evidence-based governance of one skill or a small target set. It starts from a concrete problem, audits the skill, and ends with an explici….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Overview / Rules / When to Use” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disable/archive decision loop from real failures instead of abstract best practices. Use this skill for evidence-based governance of one skill or a small target set. It starts from a concrete problem, audits the skill, and ends with an explici…”.
- **02** When the source has headings, the agent prioritizes “Overview / Rules / When to Use” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Overview / Rules / When to Use”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: skill-governance-loop
description: Use when the user asks to review a skill, analyze skill quality, update a skill version, or run…
category: engineering
source: cnfjlhj/ai-collab-playbook
---
# skill-governance-loop
## When to use
- Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disa…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Overview / Rules / When to Use” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "skill-governance-loop" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Overview / Rules / When to Use
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Skill Governance Loop
Overview
Use this skill for evidence-based governance of one skill or a small target set. It starts from a concrete problem, audits the skill, and ends with an explicit keep, disable, merge, split, or archive decision.
Rules
- Start from a concrete case such as poor triggering, overlap, bloat, or a version update request.
- Produce three outputs every time: the case, the audit, and the decision.
- Separate static quality from observed usefulness; a pretty skill is not automatically a useful skill.
- Use inventory tooling first when the scope is broad enough to need filesystem evidence.
- Record the next hypothesis so the next governance pass has a sharper starting point.
When to Use
Use when:
- the user asks to review a skill, analyze skill quality, or update a skill version
- a skill may need to be kept, disabled, merged, split, archived, or moved
- the user wants a repeatable governance loop instead of one-off edits
Do not use when:
- the task is broad inventory scanning of many skills at once
- the work is simple skill authoring with no governance decision
- the request is only to discover whether a skill exists
Decide Fit First
Design Intent
How To Use It
Boundaries And Review