agentsclimarketplace

Code review

Skill claudifytech/claude-code-skills-starter/skills/code-review

Free starter skills for Claude Code: conventional commits, code review, test writing, and README generation, plus a starter CLAUDE.md. From the makers of Claudify.

Install
npx -y skills add claudifytech/claude-code-skills-starter --skill code-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

Run a structured self-review pass on changed files before opening a pull request

SKILL.md

1.5 KB, as published. Nobody here has run it

Code Review

Review the current changes the way a careful reviewer would, and report findings ranked by severity.

When to use

Before opening a pull request, or when the user asks for a review of recent changes.

Procedure

  1. Run git diff (or git diff main...HEAD) to see what changed. Read the full changed files, not just the diff hunks, so you have context.
  2. Check each of these and note any issue with a file and line reference:
    • Correctness: logic errors, off-by-one mistakes, wrong conditionals, unhandled null or empty cases.
    • Edge cases: empty input, very large input, concurrent calls, failure of an external call.
    • Security: unvalidated input, secrets committed in code, injection risks, missing authorization checks.
    • Conventions: does the change match the existing patterns and style of the surrounding code?
    • Tests: is the new behavior covered? Are existing tests still valid?
    • Clarity: misleading names, dead code, comments that no longer match the code.
  3. Rank findings as blocking, should-fix, or nit. Lead with blocking.
  4. For each finding give a one-line fix suggestion, not just the problem.
  5. If you find nothing significant, say so plainly rather than inventing issues.

Output

A short summary line, then the findings grouped by severity, each as file:line plus the issue and the suggested fix.

Gives 0 of the 12 instructions most code review skills give

Counted across 610 of the 674 authors here whose files we hold, read 2026-08-06

  • push back with technical reasoning if wrongin 60 of 610, across 24 files
  • ask for clarification on unclear itemsin 51 of 610, across 16 files
  • fix critical issues immediatelyin 45 of 610, across 29 files
  • implement one item at a timein 45 of 610, across 11 files
  • group findings by severityin 44 of 610, across 43 files
  • verify feedback against the codebasein 42 of 610, across 8 files
  • dispatch a code reviewer subagentin 39 of 610, across 23 files
  • fix important issues before proceedingin 37 of 610, across 22 files
  • test each fix individuallyin 35 of 610, across 7 files
  • reply in github comment threadsin 33 of 610, across 5 files
  • check for security vulnerabilitiesin 31 of 610, across 27 files
  • factualize corrections without over-explainingin 30 of 610, across 2 files

Said here and by no other author read

  • check logic errors and unhandled null cases
  • check empty input, large input, and concurrent calls
  • verify the change matches existing patterns and style
  • identify misleading names, dead code, and stale comments
  • rank findings as blocking, should-fix, or nit
  • report plainly if nothing significant is found

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

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.