Physical flow test
Skill timeyour/agentskills-audit-collection/.claude/skills/physical-flow-test
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 physical-flow-testAssembled 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
Generate executable real-browser flow tests using Python Playwright from business flows. Use when cognitive audit, flow-test, audit, or accept-five needs physical browser proof for CTA, form, auth, upload, checkout, dashboard, production, staging, or local workflows.
SKILL.md
4.7 KB, as published. Nobody here has run it
Physical Flow Test
Use this skill to turn business flows into real executable browser tests.
business flow -> harness decomposition -> Python Playwright package -> real execution -> artifacts -> regression check -> lessons
This skill must not guess whether a workflow works. It produces tests that a user, CI job, or real browser environment must execute.
When To Use
Use /physical-flow-test when the user needs to:
- Verify critical user paths with real browser clicks.
- Upgrade
/flow-testfrom static inspection to physical execution. - Generate repeatable regression tests for important workflows.
- Validate staging, production, or local environments with real network behavior.
- Collect physical evidence for
/auditor/accept-five. - Check CTA, forms, login, signup, dashboard actions, uploads, exports, checkout, or booking flows.
- Convert business-level acceptance criteria into runnable browser tests.
Prefer /harness first. If /harness is unavailable, perform a minimal harness decomposition inside this skill before generating code.
Core Rules
- Never claim a workflow works without real execution evidence.
- Decompose the business goal into minimal executable units before writing tests.
- Generate Python tests using
pytestandplaywright.sync_api. - Use
python -m pytest -q tests/, not the Node/TypeScript Playwright runner, unless the user explicitly asks for TypeScript. - Every generated test must include trace capture, screenshot on failure, HAR/network capture, video when supported, console log capture, clear assertions, and safe failure handling.
- Output generated packages under
./artifacts/physical-tests/{timestamp}-{flow-name}/. - Use the audit permission model before generating tests for production, authenticated, payment, deletion, upload, admin, or private-data flows.
- Mark payment, deletion, irreversible submission, production email/SMS sending, and real purchase flows as
SKIPPED-SAFEunless explicitly allowed. - Never hardcode secrets, passwords, tokens, or cookies. Use environment variables and
.env.exampleplaceholders. - Require artifact redaction before sharing HAR, trace, screenshots, video, or console logs.
- Use
S0-S4severity and preserve the shared output shape.
Workflow
- Intake and scope: identify flow name, URL or local command, environment, browser target, auth needs, test account, high-risk actions, expected results, and required artifacts.
- Surface and permission check: use any available web surface map, apply the permission model, and mark unsafe units
SKIPPED-SAFE. - Harness decomposition: map business goal -> user intent -> page/route -> action -> locator -> expected result -> checkpoint -> failure signal.
- Generate test package: create
README.md,requirements.txt,.env.example,run-tests.sh,tests/test_{flow_name}.py, and artifact directories. - Execution instruction: provide exact commands for installing Python dependencies, installing Chromium, and running pytest.
- Artifact review: inspect returned trace, screenshots, HAR, console logs, video, and result JSON against expected behavior.
- Regression and lessons: convert findings into regression checks, locator rules, auth/session rules, network dependency rules, timeout rules, and safe-skip rules.
References
references/python-playwright-template.mdreferences/artifact-schema.mdreferences/safe-execution-policy.mdreferences/locator-policy.mdreferences/regression-lessons-ledger.md../audit/references/permission-model.md../audit/references/web-surface-discovery.mdwhen a surface map is needed before test generation
Output Format
Physical Flow Test Summary
Target Flow:
Environment:
Harness Used:
Execution Mode:
Risk Level:
Scope
Evidence
Findings
Severity
Reproduction
Fix Suggestion
Regression Check
Lessons
Anti-Patterns
- Claiming a workflow works without physical execution.
- Mentally simulating browser clicks.
- Generating tests without requiring execution.
- Testing only happy paths.
- Missing trace, HAR, video, console log, or failure screenshot capture.
- Hardcoding credentials.
- Sharing raw HAR files without redaction.
- Running destructive production actions by default.
- Using brittle selectors when accessible locators exist.
- Treating docs, marketing copy, source code, or screenshots as proof of working behavior.