agentleFS
Sign inStart free
swyxioswyxio/skills/autoreview/SKILL.md

autoreview

Skill176 starsChanged 7 months agoMITView on GitHub

Perform a structured final code review of a local diff, commit, branch, or pull request. Use only when the user explicitly asks for autoreview, a second review, or a final review before commit, merge, or release, or when repository instructions require one. Do not trigger automatically for ordinary non-trivial edits.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 5

    Distinctive

    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 push, rewrite history, or manufacture a diff merely to make review possible.

    line 15
  2. Distinctive:

    Prefer concrete defects with a reproducible path.

    line 28
  3. Distinctive:

    Treat every finding as advisory until confirmed against the real code path.

    line 32
  4. Distinctive:

    Read adjacent code, types, tests, and authoritative dependency documentation when needed.

    line 33
  5. Distinctive:

    Stop when no confirmed actionable findings remain.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 38 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

Auto Review

Review the completed change as a closeout check. Use the review capability available in the current environment; do not make completion depend on a particular helper, model, service, or installation.

Select the real change

  • For dirty work, review the staged, unstaged, and relevant untracked diff.
  • For a commit, review that commit and its immediate context.
  • For branch or pull-request work, compare against the actual base branch.
  • Do not push, rewrite history, or manufacture a diff merely to make review possible.

Review priorities

Inspect the changed code and adjacent ownership boundaries for:

  1. correctness and violated invariants;
  2. security, privacy, authorization, and unsafe data handling;
  3. error handling, retries, concurrency, cleanup, and partial failure;
  4. compatibility with persisted state and public contracts;
  5. missing or misleading tests;
  6. unnecessary complexity introduced by the change.

Prefer concrete defects with a reproducible path. Reject speculative edge cases, style-only churn, unrelated rewrites, and fixes that cost more complexity than the risk warrants.

Verify findings

  • Treat every finding as advisory until confirmed against the real code path.
  • Read adjacent code, types, tests, and authoritative dependency documentation when needed.
  • Fix accepted findings at the narrowest correct ownership boundary.
  • Rerun affected tests after review-driven edits.
  • Re-review only the changed result when a fix could have introduced another defect.

Stop when no confirmed actionable findings remain. Do not seek extra reviewers or repeat a clean review solely for more reassuring wording.

Report

Include:

  • the target reviewed;
  • findings accepted and rejected, with brief reasons;
  • fixes made and tests run;
  • remaining risks or verification gaps.

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.

Reviews can't be read right now.

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.

Check your setup, free