mofa-eval

Official

Automatically judge agent outputs with an LLM.

Authormofa-org
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill automatically scores and tracks the quality of agent outputs against a defined rubric, enabling rapid detection of regressions and consistency issues across runs.

Core Features & Use Cases

  • LLM-as-a-judge: Evaluates actual outputs against expected results using a rubric and returns a structured JSON score.
  • Evaluation persistence: Stores every evaluation in SQLite by run_id for audit trails and trend analysis.
  • Batch and regression: Supports batch_eval, score_summary, and compare_runs to assess performance changes over time across multiple tests.

Quick Start

Run a single evaluation by piping a JSON object with run_id, expected, and actual to mofa-eval evaluate_response.

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: mofa-eval
Download link: https://github.com/mofa-org/mofa-skills/archive/main.zip#mofa-eval

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.