agentsclimarketplace

Reviewing pull requests

Skill Mike-Jenkins-Org/skill-testing/examples/reviewing-pull-requests

Author, evaluate, security-review, and autonomously improve Claude agent skills - 21-check harness, behavioral/trigger/value-add evals, self-tested + CI

Install
npx -y skills add Mike-Jenkins-Org/skill-testing --skill reviewing-pull-requests

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Reviews a pull request diff against a structured rubric covering correctness, tests, security, and style, then produces a prioritized comment list. Use when the user asks to review a PR, audit a diff, or check changes before merging.

SKILL.md

1.5 KB, as published. Nobody here has run it

Reviewing Pull Requests

When to use

The user explicitly asks to review, audit, or critique a pull request, a diff, or staged changes — including phrasing like "review this PR", "look over my diff", "anything risky in these changes".

Steps

  1. Fetch the diff with whatever tool fits the context (git diff, gh pr diff, file contents the user pasted).
  2. Apply the rubric in reference.md section by section.
  3. For each finding, classify priority: blocker, important, or nit. Include file:line references.
  4. Emit the report in the output format below. Lead with blockers; nits go last and may be omitted if the diff is small.

Output

## Blockers
- file:line — issue + suggested fix

## Important
- file:line — issue + suggested fix

## Nits (optional)
- file:line — minor issue

## Summary
<one sentence: ship / hold / needs-rework>

Notes

  • Don't restate what the diff already shows. A reviewer's job is to flag what's wrong or missing, not narrate the change.
  • If you can't tell whether something is correct without more context (the caller, the schema, the test that exercises it), say so — don't guess.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.