rat-auto-design-policy

Community

Policy & quality gates for RTL autopilot.

Authorbabyworm
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Provides a formalized policy layer that prevents downstream implementation work from violating higher-level specifications by defining artifact and quality gates, retry/escalation behavior, and traceability conventions for a 6-phase RTL design pipeline.

Core Features & Use Cases

  • Phase Gate Definitions: Explicit Artifact and Quality Gate rules for Research→Architecture→μArch→RTL→Verify→Design Note transitions, including required files and pass criteria.
  • Review & Retry Orchestration: Enforces 3-round iterative reviews, reviewer roles, rebuttal handling, fallback/last-chance strategies, and per-gate retry budgets.
  • Traceability & Feedback Loops: Requirement-to-architecture-to-RTL traceability, Stream B artifact rules (SVA/CDC/TB skeletons), and structured feedback-loop state for unit/integration/design fixes.
  • Use Case: Use as a reference to validate project readiness before automated phase execution, to generate review checklists, or to drive gate decision logic in an orchestrator.

Quick Start

Invoke the rat-auto-design-policy skill to validate current phase artifacts, run the quality gate checklist, and produce a PASS/FAIL summary with required findings and next actions.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: rat-auto-design-policy
Download link: https://github.com/babyworm/rtl-agent-team/archive/main.zip#rat-auto-design-policy

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.