agentleFS
Sign inStart free
ArangoGutierrezArangoGutierrez/claude-toolkit/.claude/skills/js-review/SKILL.md

js-review

Skill4 starsChanged 3 months agoMITView on GitHub

JavaScript/TypeScript/Node code review — async correctness, TypeScript strictness, Node patterns, dependency hygiene, JS security. Triggered by "review JavaScript", "review TypeScript", "review Node code", "JS best practices", or /js-review

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When invoked by the pr-review dispatcher, the reviewer reads references/js-review-checklist.md, reviews ONLY changed lines in the PR diff, …

    line 43
  2. Distinctive:

    No external actions of any kind in dispatched mode — findings are returned as data, never posted.

    line 54
  3. Distinctive:

    Don't flag style that Prettier/ESLint handles

    line 62
  4. Distinctive:

    Don't demand a framework rewrite or migration (e.g.

    line 63
  5. Very specific:

    Don't block on pre-existing npm audit advisories.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

JS Review

Systematic JavaScript/TypeScript/Node code review. Only flags correctness, security, performance, and maintainability — not style that Prettier/ESLint already handles.

Process

  1. Static analysis (guard every tool — run only when the project has it configured):
# type-check, only when a tsconfig.json exists
[ -f tsconfig.json ] && npx --no-install tsc --noEmit
# the project's own lint script, only when defined in package.json
npm run --if-present lint
# dependency advisories, only for package.json / lockfile changes — report awareness,
# do NOT block on pre-existing advisories
npm audit --omit=dev   # pnpm audit --prod / yarn npm audit for those managers
  1. Walk checklist (see references/js-review-checklist.md):
    • Async correctness, TypeScript strictness, Node runtime patterns, dependency hygiene, JS security
  2. Report findings:
    • file:line for each issue
    • Category: correctness / security / performance / maintainability
    • Severity: must-fix / should-fix / consider
    • Suggested fix (code snippet)

Dispatched mode (pr-review integration)

When invoked by the pr-review dispatcher, the reviewer reads references/js-review-checklist.md, reviews ONLY changed lines in the PR diff, and returns a findings list where each finding has:

  • file — repo-relative path
  • line — NEW-file (RIGHT-side) line number
  • description — 1–2 sentences
  • category — correctness / security / performance / maintainability
  • severity — must-fix / should-fix / consider
  • reason — which checklist item flagged it

No external actions of any kind in dispatched mode — findings are returned as data, never posted.

Scope

Changed files only unless explicitly asked for a full-project review.

Gotchas

  • Don't flag style that Prettier/ESLint handles
  • Don't demand a framework rewrite or migration (e.g. CJS → ESM) during review
  • Respect the project's existing patterns — a CommonJS project stays CommonJS
  • Don't block on pre-existing npm audit advisories; flag only what the change introduces

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free