eval-run

Community

Quantify output quality with evals.

AuthorpetrSimonidesXart
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Evaluates an AI or skill output against a structured evals.yaml by producing a transparent, per-assertion score report to help detect regressions and measure output quality.

Core Features & Use Cases

  • Load an output file and a corresponding evals.yaml and verify all assertions (code and llm-judge) deterministically or via LLM judgment.
  • Generate a structured report showing PASS/FAIL per assertion, total scores, and details for failures, suitable for auditing skill performance across releases.
  • Use cases include baseline scoring after changes, before/after quality comparisons, and automated quality gates in Skill Optimize workflows.

Quick Start

Run the eval-run skill by supplying the produced output file and its evals.yaml to generate a structured per-assertion score report.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: eval-run
Download link: https://github.com/petrSimonidesXart/xPmGateway/archive/main.zip#eval-run

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.