agentleFS
Sign inStart free
tadoEngtadoEng/web-starter/.claude/skills/review/SKILL.md

review

Skill2 starsChanged 3 months agoMITView on GitHub

Review this product's pending change before opening a PR — verification ladder plus the boundary checks that screenshots never catch. Use when asked to review, check work before a PR, or confirm a change is ready to ship.

  • Reads credentials

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 159 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Every new route has an explicit response_model?

    line 33
  2. Distinctive:

    Every new mutation authorized server-side?

    line 36
  3. Distinctive:

    All five async states present on new surfaces?

    line 56

“Common” is measured: kept by at least 6 in 10 of the 159 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

Pre-PR review

1. Run the ladder

./scripts/verify.sh

Report what actually ran. If a step failed or was skipped, say which and why — a green claim without output is not evidence.

2. Ask what each test proves

For every new or changed test: what property does this actually prove? A test that only demonstrates the code ran is not coverage. Name the behaviour that would break if someone deleted the implementation — if you can't, the test is decorative.

3. Boundary review — separate from visual correctness

These are the failures a screenshot review never catches.

Contract

  • Did frontend/src/generated/ change? Is that change intended and reviewed?
  • Any hand-written TypeScript DTO, or a raw fetch() to our own API? Both are defects.
  • Every new route has an explicit response_model?

Authorization

  • Every new mutation authorized server-side?
  • Tests for all four cases: no token, wrong role, wrong owner, correct?
  • Any client-side check being relied on as a control rather than as UX?

Data

  • New queries bounded and paginated?
  • Migration read line by line? Destructive changes logged in docs/OPERATIONS.md?
  • Multi-step invariants inside one transaction?

Input

  • New user input validated on the Pydantic model rather than ad hoc in a handler?
  • Uploads size- and type-limited? Any user-supplied URL fetched server-side (SSRF)?
  • Anything sensitive newly reaching the logs?

Deployment

  • New env var? Then: .env.example, Vercel (all environments), Cloud Run, and docs/DEPLOYMENT.md. All four.
  • Any secret value in a diff, a doc, or a VITE_* variable? VITE_* ships to the browser.

Frontend

  • All five async states present on new surfaces?
  • Keyboard reachable, labelled, visible focus, contrast?

4. Scope

  • Does the diff do only what was asked? Unrelated cleanup makes review harder and bisects worse.
  • Did an architectural boundary move without a docs/DECISIONS.md entry? That is the stop condition, and it should have been raised before implementation, not discovered here.

5. Report

Findings ranked by severity, each with the file, the concrete failure it causes, and the fix. Say plainly if the change is not ready. "Looks good" without the checks above having been run is not a review.

Download now (ZIP)

  • Other versions192 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 192

    1. garrytan/gstack★ 139ksame name
    2. ansible/ansible★ 71ksame name
    3. docling-project/docling★ 70ksame name
    4. traefik/traefik★ 65ksame name
    5. ClickHouse/ClickHouse★ 51ksame name
    6. temporalio/temporal★ 24ksame name
    7. tisfeng/Easydict★ 15ksame name
    8. juicedata/juicefs★ 15ksame name
    9. elie222/inbox-zero★ 13ksame name
    10. gitkraken/vscode-gitlens★ 9.9ksame name

    182 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 daily-arxiv, exp-eval and 9 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.
    • LambenthanSkill

      daily-arxiv

      每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

      Also in 5 projects that use this

    • LambenthanSkill

      exp-eval

      实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

      Also in 5 projects that use this

    • SethGammonSkill

      ascii-diagram

      Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

      Also in 4 projects that use this

    • DAIR-AutoResearchSkill

      exp-pilot-eval

      Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

      Also in 4 projects that use this

    • DAIR-AutoResearchSkill

      exp-pilot-run

      Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

      Also in 4 projects that use this

    • +5 more from Lambenthan
    • +1 more from DAIR-AutoResearch
  • In this repository9 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.

Check your setup, free