All skills
language-idiom-enforcement
FoundationJIT onlyanalysis-agent/task-agent/review-agent: use when idioms for errors, types, resources, modules, naming, concurrency, or APIs need enforcement; skip when idioms are unaffected.
- Group
- Technology selection
- Supported roles
- MainAnalysisTaskReview
- Source
- SKILL.md
Use when
Trigger signals that make this skill the right owner
- language idioms error handling type modeling resource management module boundaries naming casing visibility exports public API naming predicate boolean names collection names concurrency formatting standard library hallucinated APIs non idiomatic code
Do not use when
Anti-triggers — as binding as the triggers above
- no task-local language idiom enforcement 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
- language-idiom decision with current authority, affected semantic boundary, chosen pattern, justified deviations, compatibility effects, and validation evidence
Escalation signals
When this skill must hand the decision back
- Non idiomatic code hides correctness defects and increases maintenance cost even when tests pass
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 | local convention and language idiom suggest competing public-surface choices | one established repository idiom determines the changed surface | TaskReviewAnalysis |
| checklist.mddecision-checklist | changed code affects public contracts errors resources concurrency or boundaries | formatter and adjacent conventions cover the local-only change | TaskReviewAnalysis |
| evidence-patterns.mdevidence-pattern | idiom API stability or AI-symbol claims need current validation | post-edit checks and inspected local examples prove each claim | TaskReviewAnalysis |