All skills
requirement-clarification
FoundationJIT onlyanalysis-agent: use when goals, constraints, assumptions, or missing facts need blocking, non-blocking, and safe-assumption decisions; skip when requirements are clear.
- Group
- Intake & requirements
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- clarify ambiguous goals constraints assumptions missing information
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local requirement clarification decision is required
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
- clarification decision with material ambiguity, inspected evidence, blocking classification, bounded assumptions or options, proceed and wait boundary, owner questions, reopen signals, and downstream updates
Escalation signals
When this skill must hand the decision back
- Unclear intent can invalidate all downstream design and implementation
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 | unknown authority reversibility or partial progress leaves options viable | one verified owner decision resolves every material ambiguity | Analysis |
| checklist.mddecision-checklist | request contains blocking unknowns assumptions conflicts or unsafe defaults | current facts and authority establish all behavior-changing decisions | Analysis |
| evidence-patterns.mdevidence-pattern | stakeholder source freshness or prior-decision claims need verification | current source and owner records prove each clarification fact | Analysis |