agentleFS
wataru-maedawataru-maeda/react-native-boilerplate/.agents/skills/review-code/SKILL.md

review-code

Skill521 starsChanged 15 days agoMITView on GitHub

Review a branch diff against repository rules, with required security and license reviews. Report cited violations and offer scoped fixes when the user requests a code review.

We split this skill into the rules it gives an agent

12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 55 edited versions we read keep these.

  • 10

    Distinctive

    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:

    Read git diff --name-only <base>...HEAD and git diff <base>...HEAD.

    line 14
  2. Distinctive:

    Read AGENTS.md, including Git rules.

    line 15
  3. Distinctive:

    Check required utilities, file placement, names, imports, and types.

    line 20
  4. Very specific:

    Check testIDs and Maestro flows for new screens, and tests beside new components.

    line 21
  5. Distinctive:

    Check branch names and commit messages against Git rules.

    line 22
  6. Distinctive:

    Read and run the security review.

    line 28
  7. Distinctive:

    Read and run the license review.

    line 29
  8. Distinctive:

    Use the same base and head as this review for both.

    line 30
  9. Distinctive:

    Do not treat a missing or incomplete review as a pass.

    line 35
  10. Distinctive:

    Do not claim unrun checks passed.

    line 47
  11. Distinctive:

    Run relevant checks for non-trivial edits.

    line 54
  12. Distinctive:

    Do not commit, push, or open a PR unless requested.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 55 edited versions of this file we could read. “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

Review Code

Review the branch diff against repository rules. A review request does not authorize edits.

Inspect

  • Choose the base from the branch table: dev for work branches, main for hotfixes. Ask when the branch prefix does not identify one.
  • Read git diff --name-only <base>...HEAD and git diff <base>...HEAD.
  • Read AGENTS.md, including Git rules.
  • Exclude package-lock.json, node_modules/, ios/, android/, dist/, and coverage/ from this rules review. Report excluded scope.

Review

  • Check required utilities, file placement, names, imports, and types.
  • Check testIDs and Maestro flows for new screens, and tests beside new components.
  • Check branch names and commit messages against Git rules.
  • Report only issues introduced by the diff. Do not flag unrelated existing code.
  • Cite a rule for each violation. Label uncertainty as advisory. Label any personal suggestion as outside the rules.

Required Reviews

  1. Read and run the security review.
  2. Read and run the license review.
  3. Use the same base and head as this review for both. Exclude unrelated uncommitted work.
  4. Include both review results in the report. Record findings, limitations, and any dependencies or assets that could not be checked. If license review finds no relevant changes, state that explicitly.
  5. Recheck affected findings if the diff changes after review. Do not reuse results from an older diff.

Complete both reviews before reporting. Do not treat a missing or incomplete review as a pass.

Report

Lead with the important findings. For each finding, give the file and line, rule heading, observed behavior, required behavior, and suggested fix.

  • Separate violations from advisories.
  • State the number of files reviewed and findings.
  • Say explicitly when no violations were found.
  • Include at most two useful examples of compliance.
  • Do not claim unrun checks passed.

Fix

  1. Offer to fix violations one at a time. Do not auto-apply advisories.
  2. For “yes,” make the smallest approved edit. For “no,” leave it.
  3. For “skip rest,” stop offering fixes.
  4. Run relevant checks for non-trivial edits. Check that the chosen fix works without restarting the full review.
  5. Report fixed and skipped violations, remaining advisories, and the next action.

Respect an explicit request to fix a defined set without repeating approval. Do not commit, push, or open a PR unless requested.

Download now (ZIP)

  • Other versions66 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 66

    1. penpot/penpot★ 62ksame name
    2. pnpm/pnpm★ 37ksame name
    3. verdaccio/verdaccio★ 18ksame name
    4. NVIDIA-NeMo/DataDesigner★ 2.4ksame name
    5. OpenAEV-Platform/openaev★ 1.8ksame name
    6. bazel-contrib/rules_python★ 687same name
    7. ankitvgupta/exo★ 496same name
    8. ankitvgupta/mail-app★ 496same name
    9. ninehills/skills★ 280same name
    10. hmislk/hmis★ 236same name

    56 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use clear-caches, electron-devtools-testing and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • mrdulasolutionsSkill

      clear-caches

      Clear extension caches, analysis data, and drafts from the database. Use when testing sender lookups, analysis, or draft generation from a clean state.

      Also in 3 projects that use this

    • mrdulasolutionsSkill

      electron-devtools-testing

      Test the Electron app interactively using Chrome DevTools Protocol. Use when the user asks to test, verify, or interact with the running app via browser automation.

      Also in 3 projects that use this

    • ba0918Skill

      review-deps

      A focused read-only review that treats manifests, lockfiles, and dependency diffs as first-class input and evaluates known vulnerabilities and supply chain signals. Use when the user says "review the dependencies", "look at the dependency vulnerabilities", "check the lockfile", "supply chain risk", "organize the npm audit output", "detect typosquats", "dependency health", or "review-deps". Its subject is the health of the dependencies, not test quality or code quality.

      Also in 3 projects that use this

    • fabianbothSkill

      reviewloop

      Run the autonomous review loop to address PR comments, fix issues, and push changes iteratively until all comments are resolved.

      Also in 3 projects that use this

    • sarfraznawaz2005Skill

      take-screenshots

      A Windows screenshot skill that provides both programmatic full-screen capture and interactive region selection.

      Also in 3 projects that use this

    • PydanticSkill

      review-security

      Security review of the current branch against its merge base — sandbox escapes, memory errors, panics and resource-limit bypasses. Use when reviewing changes for security risk, or before merging anything touching the heap/ module, path_security.rs, the wire protocol or the pool.

      Also in 6 projects that use this

    • +1 more from mrdulasolutions
  • In this repository5 other files it gives its agents.

Does it work?

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

Reviews can't be read right now.

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.