All skills
non-goal-boundary-definition
FoundationJIT onlyanalysis-agent: use when scope, exclusions, deferred decisions, version limits, or assumptions need explicit boundaries; skip when no task-local non-goal decision is needed.
- Group
- Intake & requirements
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- separate in-scope work from non-goals exclusions and deferred decisions
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local non goal boundary definition 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
- non-goal boundary with observable exclusions, reasons and authority, unchanged and deferred items, dependencies, assumptions and version limits, exclusion oracles, reopen conditions, and owners
Escalation signals
When this skill must hand the decision back
- Unbounded scope expands implementation and review beyond safe control
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 | scope exclusions conflict with version compatibility or required controls | approved scope and commitments determine every exclusion | Analysis |
| checklist.mddecision-checklist | slice needs explicit forbidden surfaces placeholders or deferred decisions | acceptance names testable included and excluded artifacts | Analysis |
| evidence-patterns.mdevidence-pattern | out-of-scope not-present or deferred claims need fresh scans | current routes schemas jobs UI and tests prove exclusions | Analysis |