rule-quality-evaluator

Official

Score your agent rules for real effectiveness

AuthorAndurilCode
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It helps you audit existing agent instruction rule sets that appear to be ignored, fail to steer behavior, or are too vague to reliably improve outcomes.

Core Features & Use Cases

  • Static rule scoring: Reads an instruction file and scores each extracted rule against seven properties to identify noise, unfalsifiable guidance, missing intent, and weak scope.
  • Structural diagnostics: Detects redundancy with linters/types/CI, flags scope mismatches, and maps coverage across architecture, domain, conventions, integrations, operations, testing, security, performance, and tech debt.
  • Optional behavioral validation: Can generate targeted coding tasks and (via an evaluation harness) measure whether the rules actually change agent behavior, not just how they read on paper.

Quick Start

Ask an AI to run the rule-quality-evaluator on your current agent instructions file and report a scorecard plus the top improvements needed to increase behavioral impact.

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: rule-quality-evaluator
Download link: https://github.com/AndurilCode/craftwork/archive/main.zip#rule-quality-evaluator

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.