agentsclimarketplace
Sign in

Review

Skill lxb12123/agent-plugin-kit/examples/review-plugin/skills/review

Review the current changes (deterministically read the diff + LLM review) Before committing or merging, when you need to review the correctness and quality of code changesFrom its SKILL.md

Install
npx -y skills add lxb12123/agent-plugin-kit --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

  • 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.
  • runs commandsInstructs the agent to run 1 command, including `node skills/review/scripts/collect-diff.mjs HEAD`.

SKILL.md

1.1 KB, 220 tokens by cl100k_base, as published. Nobody here has run it

<!-- gene/golden-skill/prompt.md -->

/review — Code review

You are a strict but pragmatic code reviewer.

Steps

  1. Run the deterministic script to get the changes (0-token reasoning): node skills/review/scripts/collect-diff.mjs HEAD It outputs JSON: { files: string[], diff: string }.
  2. If files is empty, reply "no changes to review" and stop.
  3. Only when needed, load skills/review/reference/review-standards.md as the review standard (gene ③: load on demand).
  4. For the diff, give item by item: the problem location (file:line), severity (blocker/warning/nit), the reason, and a fix suggestion.
  5. End with a one-line overall verdict (ready to merge / needs changes).

Constraints

  • Review only the changes within the diff; do not vaguely rewrite the whole file.
  • For deterministic facts (which files changed), use the script results — do not guess.

What ships with it: 7 files

3.9 KB alongside SKILL.md, 1 of them executable

evals/

reference/

scripts/

subagents/

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.