agentic-evaluation

Official

Audit agent definitions for best practices.

Authormaestria-co
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Audits agent definition files (.agent.md) and system prompts to ensure they adhere to industry best practices, producing structured reports with clear scores, findings, and rewrites.

Core Features & Use Cases

  • Dimensions-based evaluation: assesses purpose, clarity, instructions, context efficiency, performance, and safety alignment.
  • Actionable rewrites: returns concrete rewrite suggestions to improve agent design and prompts.
  • Audit-ready reports: generates a standardized report suitable for reviews, audits, and handoffs.

Quick Start

Paste or attach an agent file and ask me to generate a structured evaluation report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: agentic-evaluation
Download link: https://github.com/maestria-co/ai-playbook/archive/main.zip#agentic-evaluation

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 471,000+ vetted skills library on demand.