agentleFS
hellocrossmanwildhellocrossmanwild/Claude-skills-tools/skills/review-loop/SKILL.md

review-loop

Skill0 starsChanged 37 days agoMITView on GitHub

Decides if an app is ready to launch from evidence, not promises: six checks ending in go or not yet. Use for 'is it ready', 'review my app', 'can I launch' or 'is it production ready'.

  • Reads credentials

54 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use motion-design, polish 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.
  • soilmassSkill

    motion-design

    Create animations and motion graphics using industry standards. Use when asked to animate UI elements, create video content, implement transitions, or build motion systems. Implements W3C Design Tokens, Material Design 3 baseline, and Lottie specification compliance.

    Also in 5 projects that use this

  • HK-hubSkill

    polish

    Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

    Also in 3 projects that use this

  • GoogleSkill

    to-spec

    Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 4 projects that use this

  • GoogleSkill

    improve-codebase-architecture

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    Also in 5 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 4 projects that use this

  • MicrosoftSkill

    council

    Convene the persona panel — six orthogonal review lenses — on a target. Cold independent fan-out, debate-to-consensus, synthesized verdict with recorded dissent and a roster manifest.

    Also in 3 projects that use this

  • +4 more from google

The file

Files
SKILL.md

Review loop

You're reviewing an app for someone who can't read the code, so evidence is everything. Don't say "looks good": show it. Claude shouldn't mark its own homework, so if this session built the app, recommend running this review in a fresh session and say why.

Work through the six questions in order. For each, gather the evidence, then give a verdict: ✓ ready, ⚠️ fix first, or ✗ blocker. Copy this checklist into your reply and tick it off as you go, so they can see progress:

Launch review
- [ ] 1. Front end
- [ ] 2. Back end
- [ ] 3. Security
- [ ] 4. Everything works
- [ ] 5. Production ready
- [ ] 6. Paying customer

If you can't open pages yourself (for example in a normal chat rather than the Code tab), give them a short numbered list of exactly what to click and ask them to report back or send screenshots. Never mark a step passed without seeing the result.

1. Is all the front end good?

Evidence: screenshots of every main flow (land → sign up → the core action → pay), at desktop and phone width. Look for broken layouts, unreadable text, placeholder copy, dead buttons, and screens with no way forward.

2. Is all the back end good?

Evidence: run the tests and show the output. If there are no tests, write a few for the most important actions (creating an account, the core action, payment unlocking access), run them and show the results.

3. Is it all secure?

Evidence: a table of every page and who can see it (logged out, free, paid), tested logged out; no secret keys in the code or git history; .env* in .gitignore; the database only reachable from the server. (The Access check and Data check skills go deeper.)

4. Does everything actually work?

Evidence: click every link, submit every form and press every button in a full run-through, and list anything that errors, goes nowhere or does nothing.

5. Is it production ready?

Evidence: check the live (or preview) deployment's logs after the full run-through for errors and warnings; confirm environment variables are set in Vercel; confirm the domain and HTTPS work; check page speed on a phone.

6. Can I take a paying customer?

Evidence: one complete test payment end to end in Stripe's sandbox: checkout, access unlocks, receipt email arrives, and access ends correctly on refund or cancel. (The Payment test skill goes deeper.)

Report

Finish with:

  • A table of the six questions with ✓ / ⚠️ / ✗ and a one-line reason each
  • Verdict: Go, or Not yet, with the shortest list of what must happen before launch, most important first
  • Anything that's fine to fix after launch (put it on a Later list)

Offer to fix the ⚠️ and ✗ items on a branch, one at a time.

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.