Skip to content
rd-skills
All skills

ai-code-review-refactor

ProfessionalRuntime top level

Use review-agent on implementation or repair diffs for hallucinated APIs, unsupported assumptions, unsafe abstractions, and dependency or regression risks. Skip work without a diff or after reviewer edits.

Group
Independent review, incident and routing governance
Routing mode
evidence-only
Supported roles
MainAnalysisTaskReview
Source
SKILL.md

Use when

Trigger signals that make this skill the right owner

  • implementation diff ready
  • repair diff ready for re-review

Do not use when

Anti-triggers — as binding as the triggers above

  • no actual diff
  • reviewer implemented changed scope

Required inputs

What must be supplied before this skill can decide anything

  • acceptance
  • boundary summary
  • actual diff
  • validation evidence

Output contract

What this skill owes the next role

  • reviewed and unreviewed scope
  • material current-task findings and non-repair adjacent findings
  • review-obligation coverage and subsumption
  • scoped repair Evidence invalidation and re-review
  • residual risk

Escalation signals

When this skill must hand the decision back

  • scope, authority, or material risk exceeds the selected task contract

Targeted references

Each reference carries its own load condition. None of them enter context by default.

ReferenceLoad whenDo not load whenRequired by
ai-review-pattern-catalog.mdbenchmark-patternFindings need pattern-calibrated examples for recurring AI failure modesThe issue is already concrete and no calibration examples are neededReview
checklist.mddecision-checklistA bounded review needs a compact checklist before approvalPattern examples or exhaustive gates are requiredReview
index.mdindexcompeting ai code review refactor references require dependency, conflict, or output-fragment selectionthe ai code review refactor root or a task-named reference already resolves selectionReview
review-output-and-gates.mdtargetedL5 review needs exhaustive schema, quality gates, handoff routing, or repair/re-review semanticsA compact severity finding list is sufficientReview
solution-optimality.mdtargetedAn AI-generated diff introduces a material algorithm, data-structure, concurrency, cache, abstraction, or measurable resource-use choiceThe issue is already a concrete finding or no material implementation choice changedReview