mcpField
R
rules-eval

rules-eval

github.com/atholaTesting & quality34397 installsUpdated 1d ago
Repository

About rules-eval

rules-eval is a Claude Code skill for assessing rules in `.claude/rules/`. It checks frontmatter, glob patterns, content, organization, and token efficiency, then assigns scores across five quality dimensions.

Key features

  1. 01Validates YAML frontmatter
  2. 02Checks glob syntax and specificity
  3. 03Flags Cursor-only fields
  4. 04Assesses clarity and conflicts
  5. 05Reviews naming and organization
  6. 06Measures redundancy and token use

Use cases

  1. 01Auditing a project's Claude Code rules
  2. 02Finding invalid frontmatter or glob patterns
  3. 03Prioritizing rule improvements by score

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/athola/claude-night-market --skill rules-eval

After installing, type/rules-evalin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

modules/
content-quality-metrics.md
frontmatter-validation.md
glob-pattern-analysis.md
organization-patterns.md

Details

From the project README

Rules Evaluation Framework

When NOT To Use

  • Evaluating skills (use abstract:skills-eval)
  • Evaluating hooks (use abstract:hooks-eval)
  • Writing a new rule (use hookify:writing-rules)

Overview

This skill evaluates Claude Code rules in .claude/rules/ directories against quality standards. It validates YAML frontmatter, glob pattern syntax, content quality, and directory organization. Rules files support path-scoped conditional loading via paths frontmatter and unconditional rules (no paths field).

Key validations: YAML syntax errors, unquoted glob patterns, Cursor-specific fields (alwaysApply, globs), overly broad patterns, content verbosity, and naming conventions.

Quick Start

# Evaluate rules in current project
/rules-eval

# Evaluate specific directory
/rules-eval .claude/rules/

# Detailed analysis with recommendations
/rules-eval --detailed

Evaluation Workflow

  1. Scan .claude/rules/ for all .md files (including subdirectories)
  2. Validate YAML frontmatter syntax and fields
  3. Analyze glob patterns for correctness and specificity
  4. Assess content quality (actionable, concise, non-conflicting)
  5. Check organization (naming, structure, symlinks)
  6. Measure token efficiency and redundancy

Scoring

CategoryPointsFocus
Frontmatter Validity25YAML syntax, required fields, correct field names
Glob Pattern Quality20Syntax, specificity, quoting
Content Quality25Actionable, concise, non-conflicting
Organization15Naming, structure, symlink usage
Token Efficiency15Rule size, redundancy detection
ScoreLevel
91-100Excellent - Production-ready
76-90Good - Minor improvements possible
51-75Basic - Needs optimization
26-50Below Standards - Significant issues
0-25Critical - Invalid or broken rules

Resources

Skill-Specific Modules
  • Frontmatter Validation: See modules/frontmatter-validation.md
  • Glob Pattern Analysis: See modules/glob-pattern-analysis.md
  • Content Quality Metrics: See modules/content-quality-metrics.md
  • Organization Patterns: See modules/organization-patterns.md
Tools
  • Rules Validator: scripts/rules_validator.py
Related Skills
  • abstract:skills-eval - Skill evaluation framework
  • abstract:hooks-eval - Hook evaluation framework

Exit Criteria

  • Every .md file under .claude/rules/ (including subdirectories) receives a quality score (0-100) with per-category breakdown across the five dimensions.
  • YAML frontmatter syntax errors and unquoted glob patterns are listed as blocking findings before any score is reported.
  • Rules using Cursor-specific fields (alwaysApply, globs) are flagged as non-compliant with the expected Claude Code schema.
  • Any rule scoring below 26 (Critical tier) is reported with at least one concrete corrective action, not just a score.

Comments

Markdown supported