agentsclimarketplace
Sign in

Review

Skill yyqqCoding/engineering-flow-skills/skills/review

Review a diff, branch, pull request, or work-in-progress change without applying fixes.From its SKILL.md

Install
npx -y skills add yyqqCoding/engineering-flow-skills --skill 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

  • 1 stars1 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.

SKILL.md

2.3 KB, 427 tokens by cl100k_base, as published. Nobody here has run it

Review

Perform an evidence-backed, read-only review. Do not edit files, commit, or push.

1. Define the comparison

  • Use the supplied fixed point when present.
  • For a branch comparison, resolve the merge base and inspect commits plus the three-dot diff.
  • For current uncommitted work, inspect staged, unstaged, and relevant untracked files against HEAD.
  • Fail clearly on a bad reference or empty scope instead of reviewing the wrong change.

2. Recover intent

Read, in priority order:

  • The user's current review request
  • Project instructions
  • The originating requirement, issue, design, or acceptance criteria
  • Relevant tests and documentation

If no specification exists, state that the review can assess correctness risks and maintainability but not complete requirement fidelity.

3. Review independent axes

  • Requirements: missing, partial, incorrect, or unrequested behavior
  • Correctness: edge cases, failure handling, concurrency, state, and call-site impact
  • Safety: permissions, trust boundaries, data integrity, destructive effects, compatibility, and accessibility
  • Design: ownership, semantic reuse, false deduplication, abstraction cost, and unnecessary dependencies
  • Readability: explicit flow/effects, meaningful names, local reasoning, debuggability, and unjustified novelty
  • Tests: whether tests exercise stable public behavior and can detect the defect
  • Documentation: stale or contradictory facts and requirements rewritten to fit implementation
  • Scope: unrelated edits, temporary diagnostics, generated artifacts, and unauthorized operations

Apply the code-design pressure, ownership, and abstraction-cost standards when needed. Do not flag preferences already enforced by tooling or purely subjective alternatives with no maintenance impact.

4. Report findings

Order by impact. Each finding includes:

  • Severity
  • File and precise location
  • Evidence from the diff and relevant requirement or invariant
  • User-visible or maintenance impact
  • Smallest credible correction direction

Do not hide important findings inside a summary. If no material findings exist, say so and note any verification gap.

What ships with it: 1 file

231 B alongside SKILL.md

agents/

Gives 0 of the 12 instructions most pr commit review skills give in 427 tokens

Counted across 1,055 of the 1,911 authors here whose files we hold, read 2026-09-06

  • Use conventional commit message formatin 150 of 1055, across 145 files
  • Announce skill usage at startin 78 of 1055
  • Use imperative mood for commit descriptionsin 54 of 1055, across 51 files
  • Add directory to gitignore if not ignoredin 52 of 1055, across 41 files
  • Use imperative mood for commit subjectin 52 of 1055
  • Run tests to verify clean baselinein 42 of 1055, across 32 files
  • Push branch to originin 40 of 1055, across 38 files
  • Verify worktree directory is ignored before creationin 39 of 1055, across 32 files
  • Delete branches after mergingin 38 of 1055, across 30 files
  • Create worktree with new branchin 37 of 1055, across 32 files
  • Wrap body text at 72 charactersin 36 of 1055, across 34 files
  • Auto-detect and run project setupin 35 of 1055, across 27 files

Said here and by no other author read

  • Perform a read-only review
  • Resolve the merge base for branch comparisons
  • Inspect staged and unstaged files against HEAD
  • Fail on bad references or empty scopes
  • Read requirements and documentation first
  • Assess correctness risks and maintainability

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 325,949. 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.