Skills
.Work. You
Rest

roast-my-agents-md

Community

Audit AI instructions with evidence.

Software Engineering#code review#prompt engineering#performance optimization#a/b testing#instruction tuning#ai configuration
Authorvltansky
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a brutally honest, evidence-backed review of your AI configuration files (like AGENTS.md or CLAUDE.md), proving which instructions are redundant or ineffective.

Core Features & Use Cases

  • Static Roast: Performs a quick audit for common "sins" like bloat, redundancy, and anti-patterns, with a comedic tone.
  • Evidence Round: Conducts A/B tests to empirically prove which rules the AI already follows without explicit instruction, identifying "dead weight."
  • Verdict & Fixes: Delivers a data-backed score and offers actionable steps for optimization and restructuring.
  • Use Case: You've spent hours crafting a detailed AGENTS.md file. Use this Skill to get objective proof of which parts are actually helping and which are just costing you tokens.

Quick Start

Use the roast-my-agents-md skill to audit my AGENTS.md file.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 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: roast-my-agents-md
Download link: https://github.com/vltansky/skills/archive/main.zip#roast-my-agents-md

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 223,000+ vetted skills library on demand.