Setup

This handles the initial setup for an autoresearch agent by creating the necessary folder structure and configuration files. You'd run it once at the start of a new research project to get everything organized. It's the kind of boilerplate setup work that's easy to forget or do inconsistently, so having it automated makes sense. The scope is pretty narrow, just scaffolding out directories and dropping in starter configs, but that's exactly what you want from a setup utility. Think of it as the init command for research workflows.

skills.sh installs: 1.5K
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill setup --agent claude-code

Installs into .claude/skills of the current project.

Files

/autoresearch-agent:setup — Create New Experiment

Set up a new autoresearch experiment with all required configuration.

Usage

/autoresearch-agent:setup                                    # Interactive mode
/autoresearch-agent:setup engineering api-speed src/api.py "pytest bench.py" p50_ms lower
/autoresearch-agent:setup --list                             # Show existing experiments
/autoresearch-agent:setup --list-evaluators                  # Show available evaluators

What It Does

If arguments provided

Pass them directly to the setup script:

python {skill_path}/scripts/setup_experiment.py \
  --domain {domain} --name {name} \
  --target {target} --eval "{eval_cmd}" \
  --metric {metric} --direction {direction} \
  [--evaluator {evaluator}] [--scope {scope}]