All skills
quality-test-gate
ProfessionalRuntime top levelUse analysis-agent to map acceptance to validation, task-agent to add or run bounded tests, and review-agent to assess proof coverage. Skip work with no material change or already-fresh complete validation.
- Group
- Quality, security, reliability and delivery gates
- Routing mode
- automatic
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- changed behavior needs proof
- validation freshness required
Do not use when
Anti-triggers — as binding as the triggers above
- no material change
- validation already fresh and complete
Required inputs
What must be supplied before this skill can decide anything
- observable acceptance and non-goals
- validation entry points material risks and execution constraints
Output contract
What this skill owes the next role
- validation strategy
- covered behavior
- coverage verdict
Escalation signals
When this skill must hand the decision back
- scope, authority, or material risk exceeds the selected task contract
Related expertise
12 Layer 3 candidates may be loaded behind this skill. A single task loads at most three, and only when the current evidence justifies them.
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 |
|---|---|---|---|
| checklist.mddecision-checklist | Ordinary acceptance-to-test mapping needs a compact checklist | The root checklist already covers the bounded change | AnalysisTaskReview |
| index.mdindex | competing quality test gate references require dependency, conflict, or output-fragment selection | the quality test gate root or a task-named reference already resolves selection | AnalysisTaskReview |
| test-output-and-gates.mdtargeted | Migration, security, release, concurrency, or multi-boundary proof needs deeper calibration | A local targeted test is sufficient | AnalysisTaskReview |
| test-structure-boundaries.mdtargeted | Fixtures, mocks, golden data, shared helpers, private access, or test placement affect correctness | No test-structure decision exists | AnalysisTaskReview |