Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
athola avatar

Rules Eval

  • 93 installs
  • 325 repo stars
  • Updated August 2, 2026
  • athola/claude-night-market

Rules-eval is an agent skill that scores Claude Code rules for actionability, length, topic focus, and frontmatter validity.

About

Rules-eval is an agent skill from athola’s claude-night-market that acts as a linter for Claude Code rule files. It encodes content-quality metrics—actionability, conciseness, non-conflicting guidance, and single-topic focus—and a 25-point deductive rubric that zeroes out empty files and penalizes bodies under ten words or over roughly five hundred tokens. It also documents valid frontmatter (paths globs, description) and common YAML failures when globs start with asterisks unquoted. Solo builders curating .claude/rules or similar drops use it while tightening Ship/review gates and again in Build/agent-tooling when authoring new rules so conditional path loading works. Output is qualitative fixes aligned to the scoring table, not a deployed CI service unless you wire it yourself. Pair with your repo’s rule set before onboarding contributors so agents load consistent, non-contradictory instructions.

  • 25-point deductive scoring with penalties for empty, too-short, or overly verbose rule bodies
  • Enforces actionable guidance—not bare project descriptions
  • Validates Claude Code frontmatter fields paths (glob list) and optional description
  • Documents YAML glob pitfalls (quote patterns like **/*.ts)
  • Expects focused single-topic rules typically under ~500 tokens

Rules Eval by the numbers

  • 93 all-time installs (skills.sh)
  • Ranked #459 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill rules-eval

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs93
repo stars325
Security audit3 / 3 scanners passed
Last updatedAugust 2, 2026
Repositoryathola/claude-night-market

What it does

Score and fix Claude Code rule files for actionability, size, conflicts, and valid YAML frontmatter before they silently misfire in the agent.

Who is it for?

Maintainers of claude-night-market-style rule packs or custom.claude rules who want a consistent quality bar before sharing templates.

Skip if: Skip if you do not use Claude Code conditional rules or only rely on a single global AGENTS.md with no per-path rules.

When should I use this skill?

When adding, editing, or reviewing Claude Code rule files and you need actionable content plus valid paths/description frontmatter.

What you get

Each rule file meets actionable, concise, single-topic standards with valid paths frontmatter and a clear score against the 25-point rubric.

  • Per-rule quality score with rubric deductions
  • Concrete edits for actionability, length, and frontmatter fixes

By the numbers

  • 25-point deductive scoring rubric
  • Typical rule files expected under 500 estimated tokens
  • Empty rule body deducts full 25 points

Files

SKILL.mdMarkdownGitHub ↗

Rules Evaluation Framework

Table of Contents

1. Overview 2. Quick Start 3. Evaluation Workflow 4. Scoring 5. 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

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

Related skills

How it compares

A rule-quality rubric skill—not application test coverage and not MCP policy enforcement.

FAQ

Who is rules-eval for?

Developers and template authors who ship Claude Code rule directories and need repeatable content and frontmatter checks.

When should I use rules-eval?

Use it in Ship/review before merging rule changes, and in Build/agent-tooling while drafting new path-scoped rules or fixing glob YAML errors.

Is rules-eval safe to install?

It evaluates text rules locally in agent workflows; confirm repo trust via the Security Audits panel on this Prism page before installing.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.