agentsclimarketplace

Flow test

Skill timeyour/agentskills-audit-collection/.claude/skills/flow-test

AI delivery acceptance and audit system for vibe-coded websites, web apps, and agent-built products.

Install
npx -y skills add timeyour/agentskills-audit-collection --skill flow-test

Assembled 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

Test every visible function and user workflow in a website, web app, or open-source project. Use for live QA: navigation, CTAs, forms, auth, search, upload, checkout, dashboards, error states, mobile behavior, expected vs actual results, and issue cards with copyable fixes.

SKILL.md

1.8 KB, as published. Nobody here has run it

Flow Test

Use this skill to walk a product like a real user.

Do

  1. Inventory every visible feature.
  2. Map visible pages, controls, media, documents, auth/payment/upload/admin boundaries, and unknown surfaces before detailed clicking.
  3. Determine the permission level before live interaction; production defaults to public read-only or safe navigation unless the user grants a test scope.
  4. Execute every safe public workflow.
  5. Record expected vs actual behavior.
  6. Test edge states: empty input, invalid input, duplicate submit, back/refresh, mobile, auth boundary.
  7. Mark unsafe/payment/private/destructive flows as SKIPPED-SAFE.
  8. Produce issue cards with exact live positions and copyable fix prompts.
  9. Use S0-S4 severity and include reproduction plus regression checks.
  10. For multi-step live testing, emit progress updates after each major route, CTA group, form, auth boundary, or blocker.

Reference

Read references/live-functional-audit.md before running the audit. For long runs, also read ../audit/references/progressive-reporting.md and use its update format. For broad website tests, read ../audit/references/web-surface-discovery.md before clicking. For any live interaction, read ../audit/references/permission-model.md and apply its least-privilege levels.

Output

  • Feature inventory.
  • Flow execution log.
  • Edge/failure table.
  • S0-S4 severity.
  • Reproduction steps.
  • Issue cards.
  • Copyable fix pack.
  • Regression checks.
  • Lessons.
  • Final verdict.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.