# Rtl P4 Rapid Impl Policy

> Internal reference: rtl p4 rapid impl policy (agent-loaded; do not invoke).

- Skill: `babyworm/rtl-p4-rapid-impl-policy` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add babyworm/rtl-p4-rapid-impl-policy`
- Raw SKILL.md: https://api.skillmd.com/api/skills/babyworm/rtl-p4-rapid-impl-policy/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-p4-rapid-impl-policy

---


# RTL Design Policy (P4)

## Gate Priority
- Functional correctness is mandatory.
- Lint and CDC must be clean at module and block sanity scope.

## P4 Minimum Gates
- Lint PASS (module + touched integration scope)
- CDC PASS (module + touched crossings)
- Smoke functional PASS
- Block sanity integration PASS

## State Template Note
- `templates/p4-state.json` initializes `modules` as an empty map.
- The orchestrator populates concrete module keys at runtime from discovered targets.

## Rapid-Mode Gate Scope

The 4 gates above (lint, CDC, smoke, block sanity) are a minimal subset of the full
10-Wave pipeline defined in `rtl-p4-implement-policy`. The rapid-mode orchestrator
intentionally skips Waves 4-5 (code review), Wave 8 (protocol), Wave 9 (refactoring),
and Stream B artifact generation. Use `rtl-p4-implement` for the full pipeline.

## Failure Handling
- Prefer smallest-scope fix and re-run.
- If repeated failure on same category, escalate with root-cause summary.