rubrics

Official

Evaluate and refine AI agent performance.

AuthorAnkh-Studio
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a structured framework for evaluating AI agents and their associated components (prompts, rubrics, etc.) based on defined criteria, ensuring consistent and objective assessment.

Core Features & Use Cases

  • Rubric Validation: Ensures evaluation rubrics are well-defined, consistent, and support automation.
  • Adversarial Testing: Stress-tests rubrics against manipulation attempts to ensure robustness.
  • AgentSkills Evaluation: Integrates with the AgentSkills.io format for standardized AI skill evaluation.
  • Use Case: A team developing an AI customer support agent can use this Skill to rigorously evaluate the quality of the agent's responses against predefined rubrics, identify weaknesses, and ensure it meets performance benchmarks before deployment.

Quick Start

Run a full validation of all rubrics in the current directory.

Dependency Matrix

Required Modules

fspath

Components

scriptsreferencesassets

💻 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: rubrics
Download link: https://github.com/Ankh-Studio/copilot-enterprise-eval-plugin/archive/main.zip#rubrics

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.