# Rtl Review Refactor

> LLM code review + controlled refactor with mandatory re-validation gates; cross-cutting support for P4-P6, not a phase step. Trigger: 'review and refactor'.

- Skill: `babyworm/rtl-review-refactor` (Agent Skill)
- Install (CLI): `npx skillmds@latest add babyworm/rtl-review-refactor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/babyworm/rtl-review-refactor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: babyworm (https://skillmd.com/u/babyworm)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/babyworm/rtl-review-refactor

---


<Purpose>
Run structured review/refactor workflow with explicit severity and re-validation policy.
</Purpose>

<Use_When>
- Need structured LLM review findings and safe refactoring plan
- Want replayable validation after code changes
- Need cross-cutting quality work inside/after phase execution (typically P4/P5/P6)
</Use_When>

<Do_Not_Use_When>
- Requirements or architecture are still unstable
- This workflow is not a replacement for the phase pipeline itself
  (it is cross-cutting support for review/refactor within/after phases)
- Need to advance core phase progression (P1-P6)
  (use phase action skills, then apply this workflow as support)
</Do_Not_Use_When>

## Execution

Task(subagent_type="rtl-agent-team:review-refactor-orchestrator",
     prompt="Run review/refactor workflow for scope: $ARGUMENTS")