Skills
.Work. You
Rest

configure-experiment

Community

Plan and configure benchmark experiments.

Software Engineering#workflow#validation#yaml#config#benchmark#ai-agent#experiment
AuthorTheodoreGalanos
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Build an end-to-end experiment.yaml config interactively by discovering available tasks, guiding agent and model choices, validating the manifest, and previewing the trial plan.

Core Features & Use Cases

  • Discover tasks by scanning task.toml files in the project and reporting available disciplines, difficulties, and datasets.
  • Guide agent and model configuration, including multiple agents for model comparison and a dry-run preview of the trial plan.
  • Validate the final manifest against the ExperimentManifest schema and write a ready-to-run experiment.yaml in the project root.

Quick Start

Ask the assistant to configure a new experiment by walking you through task discovery, agent setup, and a dry run.

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: configure-experiment
Download link: https://github.com/TheodoreGalanos/aec-bench/archive/main.zip#configure-experiment

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 510,000+ vetted skills library on demand.