flow-test
Skill1 starsChanged 6 months agoMITView on GitHub
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.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- baodhg/FLOWtheir own version, first seen Nov 8, 2026
- emiliodominguez/flow-skillstheir own version, first seen Oct 15, 2026
- fancylight/skillstheir own version, first seen Jul 23, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- baodhg/FLOW★ 2same name
- emiliodominguez/flow-skills★ 1same name
- fancylight/skills★ 1same name
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.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/audit-live-workbench.mdcCursor rule
- accept-fiveSkill
- agent-diagnoseSkill
- ai-product-auditSkill
- auditSkill
- deploy-checkSkill
- harnessSkill
- physical-flow-testSkill
- skill-studySkill
- visual-qaSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use this skill to walk a product like a real user.
- Distinctive: line 20
Test edge states: empty input, invalid input, duplicate submit, back/refresh, mobile, auth boundary.
- Very specific: line 23
Use S0-S4 severity and include reproduction plus regression checks.
- Very specific: line 28
Read references/live-functional-audit.md before running the audit.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Flow Test
Use this skill to walk a product like a real user.
Do
- Inventory every visible feature.
- Map visible pages, controls, media, documents, auth/payment/upload/admin boundaries, and unknown surfaces before detailed clicking.
- Determine the permission level before live interaction; production defaults to public read-only or safe navigation unless the user grants a test scope.
- Execute every safe public workflow.
- Record expected vs actual behavior.
- Test edge states: empty input, invalid input, duplicate submit, back/refresh, mobile, auth boundary.
- Mark unsafe/payment/private/destructive flows as
SKIPPED-SAFE. - Produce issue cards with exact live positions and copyable fix prompts.
- Use
S0-S4severity and include reproduction plus regression checks. - 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.
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
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.