agentleFS
wheeloswheelos/apollo-lite/.agents/skills/change-review/SKILL.md

change-review

Skill177 starsChanged 7 days agoApache-2.0View on GitHub

Review diffs for behavioral bugs, contract violations, and missing regression evidence. Use for code review, pre-submit review, and cross-consumer change audits.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read changed logic, its callers, existing tests, and the owning contract.

    line 12
  2. Distinctive:

    Check state, timing, coordinates, failure paths, concurrency, and lifecycle only where relevant to the change.

    line 13
  3. Very specific:

    Use test-impact-analysis when proof scope is unclear.

    line 18
  4. Distinctive:

    No cosmetic complaints presented as bugs, invented runtime evidence, automatic fixes, or automatic commits.

    line 25
  5. Distinctive:

    If source or contracts are unavailable, narrow the claim rather than inventing an API.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “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

Change Review

Procedure

  1. Establish the exact base and diff, preserve dirty work, and read applicable rules. Do not review unrelated history or modify code unless requested.
  2. Read changed logic, its callers, existing tests, and the owning contract. Check state, timing, coordinates, failure paths, concurrency, and lifecycle only where relevant to the change.
  3. Trace each candidate finding to a concrete trigger and incorrect observable result. Verify it against source; distinguish introduced defects from pre-existing issues and unsupported assumptions.
  4. Use test-impact-analysis when proof scope is unclear. Do not require broad runtime execution merely to review a local diff.
  5. Report actionable findings with file/line, trigger, impact, and evidence. Rank by actual consequence; separate unverified questions from findings.

Acceptance and failure handling

No cosmetic complaints presented as bugs, invented runtime evidence, automatic fixes, or automatic commits. State the reviewed scope and material blind spots. If source or contracts are unavailable, narrow the claim rather than inventing an API. Explicit vulnerability reviews use the runtime's security-review path.

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.