All skills
e2e-testing
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when a critical assembled journey needs proof unavailable below E2E; skip risks proved by component, seam, or contract tests.
- Group
- Quality & testing
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- prove a critical assembled user or business journey across the deployed boundaries it actually depends on
Do not use when
Anti-triggers — as binding as the triggers above
- component integration contract or API evidence sufficiently proves the changed acceptance risk
Required inputs
What must be supplied before this skill can decide anything
- current task contract
- selected primary Professional Skill
- task-local trigger evidence
Output contract
What this skill owes the next role
- assembled-journey proof plan with selected paths, owned data, semantic oracles, cleanup, flake handling, environment coverage, diagnostic-artifact protection, and residual risk
Escalation signals
When this skill must hand the decision back
- Isolation cleanup environment authority irreversible effects or deployment-blocking flake ownership remains unresolved
Loaded by
This skill never owns a task. These professionals may pull it in as Layer 3.
Targeted references
Each reference carries its own load condition. None of them enter context by default.
| Reference | Load when | Do not load when | Required by |
|---|---|---|---|
| benchmarks-and-patterns.mdbenchmark-pattern | Journey admission isolation readiness environment or flake strategies remain open | Lower-level proof closes the risk or one accepted assembled journey has an owned proof path | AnalysisTaskReview |
| checklist.mddecision-checklist | Critical journeys cross roles persistence eventual results recovery versions or external sandboxes | No assembled user or business outcome changes | AnalysisTaskReview |
| evidence-patterns.mdevidence-pattern | Journey oracle execution isolation cleanup flake or environment claims need fresh scoped proof | No journey-completeness or flake claim awaits approval | AnalysisTaskReview |