agentleFS
coleam00coleam00/skills/.claude/skills/piv-fix-review-findings/SKILL.md

piv-fix-review-findings

Skill738 starsChanged 3 days agoMITView on GitHub

Triage code-review findings (manual or AI), fix the ones you choose one at a time with tests, defer/log the rest, then validate — and if the work is on a PR, commit and push so the PR reflects the fixes. Use after a review has produced a list of issues or a review file.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the Code-review is a file, read the entire file first so you understand every finding before triaging.

    line 16
  2. Distinctive:

    Don't let the reviewer dictate scope — "real, but later" is a valid and common call.

    line 30
  3. Distinctive:

    Create and run a test that proves it.

    line 38
  4. Very specific:

    Run the piv-validate skill to finalize the fixes.

    line 42
  5. Very specific:

    If these fixes are on a PR branch, commit them (use piv-commit) and push so the PR reflects the fixes and the review can re-run on the …

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Fix Review Findings

A review produced findings — but a review is input, not a work order. You decide what happens to each one.

Code-review (file or description of issues): $review

Direction / scope (what to fix now vs defer): $scope

If the Code-review is a file, read the entire file first so you understand every finding before triaging.

1. Triage first (the human's call)

Sort the findings before touching code. Honor any direction in the scope argument; if it's unclear, surface the findings grouped and ask rather than fixing everything by default:

  • Fix now (this PR) — real, in-scope, belongs with this change.
  • Defer / log as an issue — real but later; don't bloat this PR. Create a tracker issue (or note it) instead of fixing it here.
  • Needs a human look / manual test — anything you should inspect or test by hand before trusting it. Flag it, don't silently auto-fix.
  • Noise / won't-fix — say why, then drop it.

Don't let the reviewer dictate scope — "real, but later" is a valid and common call; a clean small PR beats a sprawling one.

2. Fix the "fix now" set — one at a time

For each:

  1. Explain what was wrong.
  2. Make the fix.
  3. Create and run a test that proves it.

3. Validate

Run the piv-validate skill to finalize the fixes.

4. If operating on a PR — commit and push

If these fixes are on a PR branch, commit them (use piv-commit) and push so the PR reflects the fixes and the review can re-run on the updated PR. If nothing was fixed (everything deferred), there's nothing to push — just make sure the deferred items are logged as issues.

Output

A short report: what was fixed (with its test), what was deferred/logged (with issue refs), what needs a manual look/test — and, if on a PR, the pushed commit + confirmation the PR is updated.

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.