All skills
configuration-runtime-policy
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when typed config, defaults, flags, modes, rollout, rollback, or cleanup changes; skip when runtime policy is unaffected.
- Group
- Delivery & platform
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- configuration runtime policy typed config default validation fail fast hot reload feature flag owner expiry cleanup kill switch stale flag mode kind switch tenant user experiment rollout rollback config observability
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local configuration runtime policy 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
- Return a Configuration Policy: define scope, schema, defaults, fail-fast validation, flag lifecycle, kill/runtime-switch rationale, test matrix, cleanup owner, rollout, rollback, and residual risk
Escalation signals
When this skill must hand the decision back
- Untyped config stale flags and vague mode switches bypass invariants create hidden strategy systems and make rollout rollback unsafe
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 | Precedence, rollout, reload, or kill-switch mechanisms remain unsettled. | The typed source and runtime behavior are unchanged. | TaskReviewAnalysis |
| checklist.mddecision-checklist | Configuration affects defaults, variants, security, or cleanup lifecycle. | No behavior-changing key, flag, or mode changes. | TaskReviewAnalysis |
| evidence-patterns.mdevidence-pattern | Config safety depends on fresh effective-state and variant validation. | No default, rollout, or bounded-mode claim needs proof. | TaskReviewAnalysis |