agentleFS
wakqasahmedwakqasahmed/skills/skills/engineering/review-gate/SKILL.md

review-gate

Skill2 starsChanged 3 months agoMITView on GitHub

Run an independent semantic review gate before merging non-trivial work, on top of (not duplicating) Alibaba Code Review and CI. Use after implementation and verification, especially for medium/high-risk changes.

21 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use afk, performance-review and 4 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.
  • jaaxkSkill

    afk

    Toggle AFK (Away From Keyboard) mode. When enabled, a PostToolUse hook sends a summary of every tool (that involves writing to files or changing settings) Claude runs to a dedicated Slack thread so the user can monitor remotely. Toggle on with /afk, toggle off with /afk again.

    Also in 3 projects that use this

  • AnthropicSkill

    performance-review

    Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment template, writing a manager review for a direct report, prepping rating distributions and promotion cases for calibration, or turning vague feedback into specific behavioral examples.

    Also in 3 projects that use this

  • yakatotechSkill

    advisor

    Provide improvement suggestions and advice on work content. Use for document review, efficiency suggestions, and best practices

    Also in 3 projects that use this

  • SentrySkill

    security-review

    Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.

    Also in 4 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

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 18 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. Distinctive:

    Use this after implementation and before merge.

    line 8
  2. Distinctive:

    Read Alibaba Code Review's findings and the GitHub CI/check results on the PR before starting the independent review — don't re-derive …

    line 19
  3. Very specific:

    Check business logic and edge cases, regressions and compatibility, security and authorization, API/database/queue/integration contracts, …

    line 21

“Common” is measured: kept by at least 6 in 10 of the 18 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 Gate

Use this after implementation and before merge.

Division of Labor

  • Mechanical checks — owned by Alibaba Code Review and CI: linting, formatting, conventional style, and straightforward static-analysis findings. Alibaba Code Review's output is recorded via ai-agent-pr-metadata.
  • Semantic review — owned by this gate: requirements compliance, correctness, regressions, security/authorization, contract/integration risk, and acceptance-test adequacy — everything mechanical tooling can't judge.

Workflow

  1. Confirm linked issue and acceptance criteria.
  2. Confirm verification commands and results.
  3. Read Alibaba Code Review's findings and the GitHub CI/check results on the PR before starting the independent review — don't re-derive what's already there.
  4. Review spec compliance before code style.
  5. Check business logic and edge cases, regressions and compatibility, security and authorization, API/database/queue/integration contracts, and test adequacy including missing acceptance tests.
  6. Revisit an Alibaba Code Review or CI finding only when it indicates an unresolved correctness, security, data-loss, configuration, or acceptance-criteria issue — not to relitigate style or formatting.
  7. Post concrete findings or explicitly state no blocking issues. Do not repeat resolved lint, formatting, conventional-style, or straightforward static-analysis findings Alibaba Code Review or CI already covered.
  8. Apply review findings before merge.

Reviewer Contract

The reviewer should read the issue, acceptance criteria, Alibaba Code Review's output, CI results, and the PR diff first. Pull more context only when needed.

Merge Rule

CI remains a hard merge gate; this review does not replace it and is not the place to rerun or restate lint/static-analysis automation. Do not merge non-trivial work without a review record. If an automated or subagent reviewer stalls, post a manual expert review that states residual risk.

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.