eval-optimize

Official

Auto-improve skills by diagnosing failures.

Authoropendatahub-io
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Automated skill improvement loop that analyzes eval results, identifies judge failures, reads traces and rationale, edits the SKILL.md to fix issues, and re-runs validations to verify improvements.

Core Features & Use Cases

  • Automated evaluation and iterative SKILL.md edits based on judge reasoning and transcripts.
  • Re-run eval suites and verify without user prompts, iterating until all judges pass or max iterations are reached.
  • Supports end-to-end evaluation workflows, handling per-case and batch modes depending on eval.yaml configuration, and ensures regressions are caught.

Quick Start

Trigger the optimization workflow to analyze current eval results and begin automatic skill improvements.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 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-optimize
Download link: https://github.com/opendatahub-io/agent-eval-harness/archive/main.zip#eval-optimize

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.