Skills
.Work. You
Rest

evaluate-presets

Community

Test and validate Ralph's presets efficiently.

Software Engineering#automation#testing#logs#metrics#CLI#presets#evaluate
Authormikeyobrien
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the testing of Ralph's hat presets to ensure stability and UX quality.

Core Features & Use Cases

  • Single preset evaluation: Run and validate a specific preset against a backend.
  • Full-suite evaluation: Execute the entire preset library and generate consolidated metrics and logs.
  • Observability & QA aids: Produce logs, session data, and a summary report to guide fixes.

Quick Start

Use the evaluate-presets capability to run evaluations from the command line.

  • Run a single preset: ./tools/evaluate-preset.sh tdd-red-green claude
  • Evaluate all presets: ./tools/evaluate-all-presets.sh claude
  • Review results in the .eval directory: logs and results under .eval/logs and .eval/results

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: evaluate-presets
Download link: https://github.com/mikeyobrien/ralph-orchestrator/archive/main.zip#evaluate-presets

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.