mofa-org/mofa-skills/mofa-eval

Claude Code and agent skill by mofa-org/mofa-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

An LLM-as-a-Judge agent evaluation skill built in Rust for MoFA IDE Testing.

Install

npx vskill@latest install mofa-org/mofa-skills/mofa-eval

SKILL.md

mofa-eval (Agent Testing Skill)

This skill brings a robust agentic testing platform to MoFA. Utilizing OpenAI (via async-openai) as an LLM Judge, this skill can autonomously grade the outputs of other MoFA agents against standard rubrics and track regressions in a SQLite database.

Capabilities

  • LLM-as-a-Judge: Uses OpenAI's GPT models to determine if an actual output logically entails the expected output without strict string matching.
  • Evaluation Persistence: Stores every evaluated interaction categorized by run_id into a SQLite database.
  • Regression Testing: Provides an automated compare_runs tool to explicitly notify if Agent Prompts have regressed performance between run iterations.

Usage Examples

Trigger a single evaluation:

bash
echo '{"run_id":"test-run-01", "expected":"The capital is Paris.", "actual":"Paris is the capital city of France."}' | mofa-eval evaluate_response

Get a summary of a test run:

bash
echo '{"run_id":"test-run-01"}' | mofa-eval score_summary

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
12
Repository forks
14
7-day trend score
18

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mofa-org/mofa-skills/mofa-eval/badge)](https://verified-skill.com/skills/mofa-org/mofa-skills/mofa-eval)

Something wrong with this skill or its page? Tell us.