All skills
state-machine-modeling
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when lifecycle states, transitions, guards, or terminal states need modeling; skip when no state-machine decision exists.
- Group
- Domain modeling
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- model lifecycle states transitions guards side effects and terminal states
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local state machine modeling 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
- state-machine decision with state invariants, transition authority and guards, concurrency, side-effect boundaries, time and recovery semantics, forbidden-path evidence, legacy handling, and residual owners
Escalation signals
When this skill must hand the decision back
- Invalid transitions cause data corruption and unrecoverable workflow states
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 | transition authority persistence effects or recovery ordering remains unresolved | one established lifecycle authority determines transition behavior | AnalysisTaskReview |
| checklist.mddecision-checklist | change affects states transitions guards actors effects retries or recovery | no lifecycle state or transition behavior changes | AnalysisTaskReview |
| evidence-patterns.mdevidence-pattern | transition denial ordering or stored-state claims need fresh proof | current writers events migrations and tests prove each claim | AnalysisTaskReview |