All skills
user-role-identification
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when actors, personas, admins, customers, service accounts, or role risks need identification; skip when roles are unchanged.
- Group
- Intake & requirements
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- identify actors personas operators administrators customers and service accounts
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local user role identification 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
- role inventory with responsibilities permissions and affected journeys
Escalation signals
When this skill must hand the decision back
- Wrong role boundaries cause permission defects and broken workflows
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 | human machine support or external actor boundaries remain ambiguous | current policy uniquely defines every affected actor class | AnalysisTaskReview |
| checklist.mddecision-checklist | change affects roles authority visibility tenants machines or external actors | no actor authority or data-visibility boundary changes | AnalysisTaskReview |
| evidence-patterns.mdevidence-pattern | role scope trust or tenant claims need fresh proof | current policies entry points and tests prove each claim | AnalysisTaskReview |