Agent skill
oe-e2e-site-visit
End-to-end verification for the site-visit (Step 7) flow. Use when you need to reproduce or validate that the system reaches the site-visit prompt/options and can proceed to confirmation, either via deterministic backend-only traces (manual_ux_scenario_I/H) or via browser UI checks (Playwright/MCP).
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/oe-e2e-site-visit
SKILL.md
oe-e2e-site-visit
Deterministic lane (fast, backend-only)
Use this lane first to prove workflow correctness without UI variability.
-
Generate a trace that includes the site-visit flow:
python3 scripts/manual_ux/manual_ux_scenario_I.py > /tmp/ux_site_visit_I.json- (optional variant)
python3 scripts/manual_ux/manual_ux_scenario_H.py > /tmp/ux_site_visit_H.json
-
Validate the trace invariants (fails fast with a precise message):
python3 scripts/manual_ux/validate_manual_ux_run.py /tmp/ux_site_visit_I.json --require_site_visit
-
If validation fails:
- Identify the first record whose
actionindicates the break (searchconfirmation_site_visit/confirmation_site_visit_sentin the trace). - Correlate with Step 7 routing and state machine:
backend/workflows/steps/step7_confirmation/trigger/step7_handler.pybackend/workflows/runtime/pre_route.py
- Identify the first record whose
Browser lane (UI correctness)
Use this when you need to confirm the frontend shows the site-visit message/options.
-
Start backend:
./scripts/dev/dev_server.sh start
-
Start frontend:
cd atelier-ai-frontend && npm run dev
-
Drive the UI until the site-visit step appears:
- Prefer Playwright MCP (agent can inspect DOM, click actions, and capture screenshots).
- Otherwise, do manual browser steps and capture screenshots in
.playwright-mcp/.
Evidence capture (for PRs / debugging agents)
- Attach:
- the trace file (
/tmp/ux_site_visit_*.json) - the validator output
- a UI screenshot when using the browser lane.
- the trace file (
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?