evaluate-instructions

Community

Assess and refine AI agent instructions.

AuthorEATSTEAK
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of creating high-quality, effective instructions for AI agents, ensuring they perform optimally and safely.

Core Features & Use Cases

  • Quality Assessment: Evaluates agent instruction files against 20 academic papers and official guides, providing a quantitative score across 8 critical categories (Structure, Clarity, Context, Reasoning, Feedback, Safety, Agentic, Evolution).
  • Actionable Recommendations: Identifies specific weaknesses and provides concrete suggestions for improvement, prioritizing impact.
  • Automated Improvement: Can initiate a self-improvement cycle based on the evaluation results.
  • Use Case: A developer has written a complex set of instructions for a new AI coding agent. They use this Skill to get an objective quality score and detailed feedback on how to make the instructions clearer, safer, and more effective before deploying the agent.

Quick Start

Evaluate the quality of the agent instructions found in the file '/path/to/your/AGENTS.md'.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: evaluate-instructions
Download link: https://github.com/EATSTEAK/dotagents/archive/main.zip#evaluate-instructions

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.