Skills
.Work. You
Rest

refactor-classification-policy

Community

Classify RTL refactors into safety tiers

Software Engineering#automation#verification#safety#refactor#policy#code-review#rtl
Authorbabyworm
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The refactor-classification-policy eliminates uncertainty in RTL refactoring by categorizing proposed edits into SAFE, RESTRICTED, or PROHIBITED tiers and defining approval, verification, and escalation rules to prevent behavioral regressions or contract violations.

Core Features & Use Cases

  • Classifies refactoring changes as SAFE for behavior-preserving cleanups, RESTRICTED for structural or test-affecting edits that require approval, and PROHIBITED for semantic, timing, or interface contract changes.
  • Enforces pass/fail gates and escalation policies, marking ambiguous or risky edits for manual review and requiring approvals for prohibited changes.
  • Produces a structured Refactor Execution Report useful for automated review workflows, CI gating, and audit trails within RTL design and verification pipelines.

Quick Start

Use the refactor-classification-policy to classify a proposed RTL change and produce a Refactor Execution Report for review.

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: refactor-classification-policy
Download link: https://github.com/babyworm/rtl-agent-team/archive/main.zip#refactor-classification-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.