Accept five
Skill timeyour/agentskills-audit-collection/.claude/skills/accept-five
AI delivery acceptance and audit system for vibe-coded websites, web apps, and agent-built products.
npx -y skills add timeyour/agentskills-audit-collection --skill accept-fiveAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Run five-pass acceptance testing on a website, app, repo, feature, or audit target: baseline, functional, edge/failure, visual/deployment, and retest/experience. Use when one inspection is not enough and repeated findings must become reusable experience.
SKILL.md
1.9 KB, as published. Nobody here has run it
Accept Five
Use this skill for important audits or releases.
Passes
- Baseline: load target, identify product, inventory features, map happy path.
- Functional: execute safe flows and record expected vs actual.
- Edge/failure: test invalid, empty, mobile, auth, refresh, loading, and missing-state behavior.
- Visual/deployment/product-pattern: inspect craft, responsive polish, accessibility, SEO, production dependencies, and product-pattern fit.
- Retest/experience: verify blockers, detect repeated patterns, improve prompts, and propose guardrails.
- Classify findings with
S0-S4severity and keep reproduction/regression evidence through all passes. - Use progressive reporting after every pass, and use the permission model before any live or authenticated action.
- In the final pass, decide whether lessons stay in the validation report, become a skill-reference update, or deserve promotion to
CLAUDE.md. Usedocs/roadmap/self-evolving-audit-engine.mdas the roadmap for this decision.
Reference
Read references/five-pass-acceptance.md.
For website/app targets, also read ../audit/references/web-surface-discovery.md, ../audit/references/permission-model.md, and ../audit/references/progressive-reporting.md.
For product-pattern or conversion-readiness questions, consult ../ai-product-audit/references/product-pattern-rubric.md.
For repeated lessons or self-improvement proposals, consult ../../../docs/roadmap/self-evolving-audit-engine.md.
Output
- Five pass report.
- Issue cards.
- Retest table.
- S0-S4 severity.
- Regression checks.
- Experience ledger.
- Guardrail update proposals.