agentsclimarketplace

Pull request review

Skill bakerstreetco/skills/pull-request-review

Reusable agent skills for real repository work: review, implementation, release, documentation, and project hygiene.

Install
npx -y skills add bakerstreetco/skills --skill pull-request-review

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

Review code changes with a bug-first engineering stance. Use when asked to review a pull request, branch diff, staged changes, patch, or recent commit for regressions, missing tests, risky behavior, incorrect assumptions, or maintainability issues.

SKILL.md

1.8 KB, 315 tokens by cl100k_base, as published. Nobody here has run it

Pull Request Review

Use this skill to review changes as if they are about to merge. Prioritize correctness, regressions, security, data loss, compatibility, and missing tests over style preferences.

Workflow

  1. Inspect repository instructions and the target diff before forming conclusions.
  2. Determine the intended behavior from the issue, PR description, commit messages, changed files, and nearby code.
  3. Review changed code paths and their callers, not only the edited lines.
  4. Check tests, docs, migrations, generated files, and release notes when relevant.
  5. Run focused verification when practical, or state clearly what was not run.
  6. Report only actionable findings. Avoid low-value nits unless they mask a real bug.

Review Checks

  • Correctness: edge cases, null/empty states, concurrency, error handling, time zones, ordering, and resource cleanup.
  • Compatibility: public API changes, schema changes, migration safety, CLI flag behavior, config defaults, and persisted data.
  • Security: auth, permissions, secrets, injection, unsafe deserialization, logs, and dependency exposure.
  • Testing: missing regression tests, weak assertions, untested failure paths, and brittle fixtures.
  • Maintainability: misplaced ownership, unclear names, excessive coupling, and comments that no longer match behavior.

Output

Lead with findings ordered by severity. Each finding should include a tight file/line reference when possible, the impact, and the concrete fix direction.

If there are no findings, say so directly and mention any residual risk or verification gap.

What ships with it: 2 files

667 B alongside SKILL.md

agents/

Gives 0 of the 12 instructions most pr commit review skills give in 315 tokens

Counted across 888 of the 1,342 authors here whose files we hold, read 2026-08-07

  • Use conventional commits formatin 127 of 888, across 115 files
  • Keep subject line under 72 charactersin 62 of 888, across 48 files
  • Delete branches after mergein 51 of 888, across 38 files
  • Use imperative mood in subject linein 51 of 888, across 42 files
  • Use imperative mood in commit messagesin 44 of 888
  • Verify directory is ignored before creating worktreein 43 of 888, across 12 files
  • Generate a conventional commit messagein 43 of 888
  • Add unignored worktree directories to gitignorein 42 of 888, across 10 files
  • Make atomic commitsin 39 of 888, across 27 files
  • Run tests before committingin 36 of 888, across 25 files
  • Verify clean test baselinein 35 of 888, across 9 files
  • Split unrelated changes into separate commitsin 35 of 888, across 30 files

Said here and by no other author read

  • Review changes as if about to merge
  • Prioritize correctness over style preferences
  • Inspect repository instructions and the target diff
  • Determine the intended behavior before reviewing
  • Review changed code paths and their callers
  • Check relevant tests, docs, migrations, and release notes

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

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.