All skills
interaction-state-modeling
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when loading, empty, error, success, disabled, timeout, or permission states change; skip when visible state is unaffected.
- Group
- Experience design
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- model empty loading error success disabled focused and permission states
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local interaction state 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
- interaction-state decision with authoritative state mapping, transitions, uncertainty, available actions, optimistic and asynchronous behavior, accessibility signals, forbidden states, evidence limits, and residual owners
Escalation signals
When this skill must hand the decision back
- Missing states create inaccessible confusing or brittle user experiences
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 |
|---|---|---|---|
| state-semantics-benchmark-anchors.mdbenchmark-pattern | State semantics need benchmark anchors from current operation and product evidence | Current operation semantics already fix the observable state distinctions | AnalysisTaskReview |
| state-distinction-and-outcome-patterns.mdbenchmark-pattern | Unknown, partial, optimistic, or durable outcomes need comparison | Current authority already fixes outcome distinctions and user actions | AnalysisTaskReview |
| state-derivation-and-recovery-decisions.mdtargeted | State derivation, retry, cancellation, or recovery decisions remain open | Current backend contract fixes transitions, repeat safety, and recovery | AnalysisTaskReview |
| state-transition-and-backend-evidence.mdevidence-pattern | Transition or backend-alignment claims need current evidence | No transition or backend-alignment claim awaits validation | AnalysisTaskReview |
| state-accessibility-evidence.mdevidence-pattern | Accessibility signals for changed states need current evidence | No changed state accessibility claim awaits validation | AnalysisTaskReview |
| state-evidence-freshness-and-tool-boundary.mdevidence-pattern | State evidence freshness, tool boundary, or proof limit remains open | Current source and validation already bind the state evidence and tool boundary | AnalysisTaskReview |
| checklist.mddecision-checklist | UI states span loading, denial, partial success, rollback, or recovery. | No loading, denial, rollback, or recovery state changes. | AnalysisTaskReview |