Skip to content
rd-skills
All skills

language-idiom-enforcement

FoundationJIT only

analysis-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.

ReferenceLoad whenDo not load whenRequired by
benchmarks-and-patterns.mdbenchmark-patternlocal convention and language idiom suggest competing public-surface choicesone established repository idiom determines the changed surfaceTaskReviewAnalysis
checklist.mddecision-checklistchanged code affects public contracts errors resources concurrency or boundariesformatter and adjacent conventions cover the local-only changeTaskReviewAnalysis
evidence-patterns.mdevidence-patternidiom API stability or AI-symbol claims need current validationpost-edit checks and inspected local examples prove each claimTaskReviewAnalysis