agentleFS
swestfall21swestfall21/claude-skills/review-quality-gate/SKILL.md

review-quality-gate

Skill0 starsChanged 4 months agoMITView on GitHub

Enforce a strong review standard before approving or finishing any change. Use for code reviews, design reviews, and architecture reviews.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not finish a review until the review is actually useful.

    line 8
  2. Distinctive:

    Verify that the change addresses the stated problem and does not create a hidden scope expansion.

    line 12
  3. Distinctive:

    Check correctness, maintainability, operability, and security risk.

    line 13
  4. Distinctive:

    Leave actionable feedback with a clear recommendation.

    line 19
  5. Distinctive:

    If a change is not ready, say so clearly and explain why.

    line 21
  6. Distinctive:

    If a change is ready, explain the reason concisely and specifically.

    line 22
  7. Distinctive:

    Do not approve a change just because it is "probably fine."

    line 26
  8. Distinctive:

    Do not leave vague feedback such as "needs work" without explaining the problem.

    line 27
  9. Distinctive:

    Do not let style concerns override correctness and risk.

    line 28
  10. Distinctive:

    Do not treat review as a formality when the change has real impact.

    line 29
  11. Distinctive:

    Use this skill to ensure reviews improve the system rather than merely adding delay.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review quality gate

Do not finish a review until the review is actually useful. A weak review is not a review; it is a delay.

Before approving

  • Verify that the change addresses the stated problem and does not create a hidden scope expansion.
  • Check correctness, maintainability, operability, and security risk.
  • Identify the highest-risk issue first, not the smallest nit.
  • Distinguish between style preferences and real defects.

Review standards

  • Leave actionable feedback with a clear recommendation.
  • Point to the underlying issue rather than only the symptom.
  • If a change is not ready, say so clearly and explain why.
  • If a change is ready, explain the reason concisely and specifically.

Non-negotiables

  • Do not approve a change just because it is "probably fine."
  • Do not leave vague feedback such as "needs work" without explaining the problem.
  • Do not let style concerns override correctness and risk.
  • Do not treat review as a formality when the change has real impact.

Use this skill to ensure reviews improve the system rather than merely adding delay.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.