agentsclimarketplace

Review

Skill latuconsinafr/claude-code-config/skills/review

Use before committing or opening a pull request — reviews staged changes as a principal engineer for correctness, edge cases, and logic flaws. Always invoke this before creating a PR.From its SKILL.md

Install
npx -y skills add latuconsinafr/claude-code-config --skill review

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

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 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.

SKILL.md

1.1 KB, 204 tokens by cl100k_base, as published. Nobody here has run it

Code Review

Review the current changes as a principal engineer. Do not modify any files during this review.

Step 1: Get the diff

git diff --staged

If nothing staged:

git diff HEAD

If the diff is empty → tell the user and stop.

Step 2: Spawn the reviewer agent

Spawn the reviewer agent to perform the review in isolation. Pass:

  • The full diff (output of Step 1)
  • The list of changed files

The reviewer agent will read full file context for each changed file (not just diff lines), work through the complete review checklist, and return structured findings.

Step 3: Present the verdict

Take the reviewer agent's output and present it directly. Do not summarize or filter findings.

If the verdict is ❌ REQUEST CHANGES: list the must-fix items again at the bottom for easy reference before proceeding.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,367. 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.