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)
Table of Contents
- Overview
- Quick Start
- Evaluation Workflow
- Scoring
- Resources
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
- Scan
.claude/rules/ for all .md files (including subdirectories)
- Validate YAML frontmatter syntax and fields
- Analyze glob patterns for correctness and specificity
- Assess content quality (actionable, concise, non-conflicting)
- Check organization (naming, structure, symlinks)
- Measure token efficiency and redundancy
Scoring
| Category |
Points |
Focus |
| Frontmatter Validity |
25 |
YAML syntax, required fields, correct field names |
| Glob Pattern Quality |
20 |
Syntax, specificity, quoting |
| Content Quality |
25 |
Actionable, concise, non-conflicting |
| Organization |
15 |
Naming, structure, symlink usage |
| Token Efficiency |
15 |
Rule size, redundancy detection |
| Score |
Level |
| 91-100 |
Excellent - Production-ready |
| 76-90 |
Good - Minor improvements possible |
| 51-75 |
Basic - Needs optimization |
| 26-50 |
Below Standards - Significant issues |
| 0-25 |
Critical - 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 frameworkabstract:hooks-eval - Hook evaluation framework
Exit Criteria
Source: athola/claude-night-market → plugins/abstract/skills/rules-eval/SKILL.md
1---2name: rules-eval3description: Evaluate Claude Code rules in .claude/rules/. Use for frontmatter, globs, and quality audits.4---5
6# Rules Evaluation Framework
7
8## When NOT To Use
9
10- Evaluating skills (use `abstract:skills-eval`)
11- Evaluating hooks (use `abstract:hooks-eval`)
12- Writing a new rule (use `hookify:writing-rules`)
13
14## Table of Contents
15
161. [Overview](#overview)
172. [Quick Start](#quick-start)
183. [Evaluation Workflow](#evaluation-workflow)
194. [Scoring](#scoring)
205. [Resources](#resources)
21
22## Overview
23
24This 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).
25
26Key validations: YAML syntax errors, unquoted glob patterns, Cursor-specific fields (`alwaysApply`, `globs`), overly broad patterns, content verbosity, and naming conventions.
27
28## Quick Start
29
30```bash
31# Evaluate rules in current project
32/rules-eval
33
34# Evaluate specific directory
35/rules-eval .claude/rules/
36
37# Detailed analysis with recommendations
38/rules-eval --detailed
39```
40
41## Evaluation Workflow
42
431. Scan `.claude/rules/` for all `.md` files (including subdirectories)
442. Validate YAML frontmatter syntax and fields
453. Analyze glob patterns for correctness and specificity
464. Assess content quality (actionable, concise, non-conflicting)
475. Check organization (naming, structure, symlinks)
486. Measure token efficiency and redundancy
49
50## Scoring
51
52| Category | Points | Focus |
53|----------|--------|-------|
54| Frontmatter Validity | 25 | YAML syntax, required fields, correct field names |
55| Glob Pattern Quality | 20 | Syntax, specificity, quoting |
56| Content Quality | 25 | Actionable, concise, non-conflicting |
57| Organization | 15 | Naming, structure, symlink usage |
58| Token Efficiency | 15 | Rule size, redundancy detection |
59
60| Score | Level |
61|-------|-------|
62| 91-100 | Excellent - Production-ready |
63| 76-90 | Good - Minor improvements possible |
64| 51-75 | Basic - Needs optimization |
65| 26-50 | Below Standards - Significant issues |
66| 0-25 | Critical - Invalid or broken rules |
67
68## Resources
69
70### Skill-Specific Modules
71- **Frontmatter Validation**: See `modules/frontmatter-validation.md`
72- **Glob Pattern Analysis**: See `modules/glob-pattern-analysis.md`
73- **Content Quality Metrics**: See `modules/content-quality-metrics.md`
74- **Organization Patterns**: See `modules/organization-patterns.md`
75
76### Tools
77- **Rules Validator**: `scripts/rules_validator.py`
78
79### Related Skills
80- `abstract:skills-eval` - Skill evaluation framework
81- `abstract:hooks-eval` - Hook evaluation framework
82
83## Exit Criteria
84
85- [ ] Every `.md` file under `.claude/rules/` (including subdirectories) receives a quality score
86 (0-100) with per-category breakdown across the five dimensions.
87- [ ] YAML frontmatter syntax errors and unquoted glob patterns are listed as blocking findings
88 before any score is reported.
89- [ ] Rules using Cursor-specific fields (`alwaysApply`, `globs`) are flagged as
90 non-compliant with the expected Claude Code schema.
91- [ ] Any rule scoring below 26 (Critical tier) is reported with at least one concrete
92 corrective action, not just a score.
93
94---
95
96**Source:** [`athola/claude-night-market`](https://github.com/athola/claude-night-market) → `plugins/abstract/skills/rules-eval/SKILL.md`
athola