evaluation-harness

Community

Repeatable evaluation frameworks for LLMs.

Authorpatricio0312rev
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Builds repeatable evaluation systems for LLM applications, enabling standardized benchmarking, scoring, and regression analysis.

Core Features & Use Cases

  • Golden dataset format, scoring rubrics, and regression reports for end-to-end model evaluation.
  • Continuous evaluation and CI integration to track performance across commits.
  • Flexible test runner and report generation to compare model outputs against expected results.

Quick Start

Run the evaluation harness on your model to load a dataset and generate a regression 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: evaluation-harness
Download link: https://github.com/patricio0312rev/skillset/archive/main.zip#evaluation-harness

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.