skills.rest
michaail
michaailCOMMUNITY
Explore all skills by this author →
GitHub

10x-rule-review

Reviews AI rules files and produces a five-check scorecard with concrete fixes.

Updated Aug 26, 2026
Search Tags:#code review#prompt engineering#claude.md#agents.md#ai rules#scorecard#cursor rules
One-click install
npx skills add https://github.com/michaail/hybrid-logs-analyzer --skill 10x-rule-review-michaail
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: 10x-rule-review
Source: https://github.com/michaail/hybrid-logs-analyzer/tree/main/.cursor/skills/10x-rule-review
Command: npx skills add https://github.com/michaail/hybrid-logs-analyzer --skill 10x-rule-review-michaail

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI rules files like CLAUDE.md, AGENTS.md, and .cursor/rules/*.mdc often grow bloated, vague, and poorly ordered, which wastes context window space and causes agents to ignore critical instructions. This Skill audits any rules-for-AI markdown file and returns a structured scorecard with actionable fixes. ## Core Features & Use Cases - Five-dimension audit: Scores length, direct code snippets, vague language, redundant knowledge, and rule ordering with OK/WARN/FAIL verdicts. - Grounded rewrites: Translates vague phrases like "write clean code" into testable, project-specific rules using signals from the file and repo. - Interactive reordering: Proposes a better section order based on U-shaped attention and asks for approval before moving any content. - Use Case: A team notices their agent ignores security rules buried at line 300 of AGENTS.md. Run this Skill to get a scorecard showing the ordering failure, plus a proposal to lift critical rules to the top. ## Quick Start Review the rules in @AGENTS.md and give me the scorecard with fixes.

Frequently Asked Questions about 10x-rule-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review my CLAUDE.md or AGENTS.md file quality?▼

Pass the file path to the skill, for example @CLAUDE.md or AGENTS.md. It reads the file, runs five checks covering length, code snippets, vague language, redundancy, and ordering, then prints a scorecard with concrete fixes per line.

What makes a good AI rules file for coding agents?▼

A good rules file stays under 200 non-blank lines, avoids embedded code snippets in favor of @-references, uses testable project-specific rules instead of vague phrases, and places critical rules at the top where models pay the most attention.

Does the rule review work with .cursor/rules .mdc files?▼

Yes, it treats .mdc files like any rules-for-AI markdown. Frontmatter such as globs and alwaysApply is treated as configuration and excluded from rule line counts, and all five checks still run.

Will the review edit my rules file automatically?▼

No, the default output is read-only. The only possible edit is a section reorder from Check 5, and that happens only after you explicitly approve one of the proposed options.

Why does my agent ignore rules in the middle of a long file?▼

Models exhibit U-shaped attention, weighting the start and end of context more heavily than the middle. Critical rules buried past line 200 are statistically less likely to be followed, so the review flags this and proposes moving them up.

Related Skills

Explore More Software Engineering Skills→
dmedina-devdmedina-dev
1

forge-init

Initialize Claude Code and generate AGENTS.md with standardized conventions.

Community
Advanced
hotovohotovo
1.4k

agent-creator

Create and configure AiderDesk agent profiles with tool groups, approvals, and subagent settings.

Official
Intermediate
carlkiblercarlkibler
3

post-mortem

Analyze failure incidents to identify root causes and generate lessons learned.

Community
Advanced
sandgardenhqsandgardenhq
130

new-sdk-app

Scaffold TypeScript or Python Claude Agent SDK projects with dependency installation and verification.

Official
Intermediate