evaluator-framework

Community

Rigorous evaluator gates for AI agent quality.

Authorj-mckerracher
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Evaluator gate and rubric framework for AI agent quality checks. Use this skill when building or running evaluator agents that assess artifacts against programmatic gates and subjective rubrics.

Core Features & Use Cases

  • Deterministic programmatic gates for artifact validation, including schema validation, completeness, structural integrity, and range checks.
  • Rubric-based scoring with defined severity levels to guide pass/fail decisions.
  • Actionable feedback templates and escalation guidance to drive artifact improvements in multi-agent workflows.

Quick Start

Activate the evaluator framework and run programmatic gates followed by rubric evaluation on your artifact.

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: evaluator-framework
Download link: https://github.com/j-mckerracher/agent-research/archive/main.zip#evaluator-framework

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.