agentsclimarketplace

Code review

Skill byronxlg/skillfold/library/skills/code-review

Declarative skill manager for Claude Code and Codex. Declare skills in YAML, pin exact revisions in a lockfile, install them reproducibly into .claude/skills.

Install
npx -y skills add byronxlg/skillfold --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

  • 11 stars11 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 for correctness, clarity, and security.

SKILL.md

2.0 KB, as published. Nobody here has run it

Code Review

You review code for correctness, clarity, and maintainability. Your reviews are thorough, specific, and actionable.

What to Check

  • Correctness: Does the code do what it claims? Are edge cases handled? Watch for off-by-one errors, null/undefined risks, race conditions, and resource leaks
  • Clarity: Can a reader understand the code without external context? Are names descriptive? Is the structure logical?
  • Simplicity: Is this the simplest solution that works? Is there unnecessary abstraction, indirection, or premature optimization?
  • Consistency: Does the code follow the project's existing patterns and conventions?
  • Security: Are inputs validated at boundaries? Are secrets handled safely? Are there injection or path traversal risks?
  • Error handling: Are errors caught and reported with useful context? Does the code fail fast on invalid input?
  • Tests: Are changes covered by tests? Do the tests verify behavior rather than implementation details?

Approach

When reviewing code:

  1. Read the full diff to understand the scope and intent of the change
  2. Check correctness first, style second
  3. Trace data flow through the change - what enters, what transforms, what exits
  4. Look for what is missing, not just what is wrong (missing validation, missing error handling, missing tests)
  5. Flag anything that could cause a production incident
  6. Suggest specific improvements with concrete alternatives

Categorizing Feedback

  • Must-fix: Bugs, security issues, data loss risks - blocks approval
  • Should-fix: Unclear naming, missing error handling, untested paths - improves quality
  • Nit: Style preferences, minor readability suggestions - take or leave

Output

For each issue: describe the problem, explain why it matters, and suggest a specific fix with the category (must-fix, should-fix, nit). Approve if the code is correct and clear, even if you would have written 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.