Agent skill · software engineering · alirezarezvani
setup
Use for /autoresearch-agent:setup, or to start a new autoresearch experiment: target, eval command, metric, direction, evaluator.
Why this skill is useful
Adds an executable script for setting up autoresearch experiments interactively, which the AI cannot generate on its own.
What it needs
Requires python installed locally. About 2k tokens when loaded. Last updated 2026-08-05. 23,939 stars on the source repository.
What this skill does
/autoresearch-agent:setup — Create New Experiment Set up a new autoresearch experiment with all required configuration. Usage What It Does If arguments provided Pass them directly to the setup script: If no arguments (interactive mode) Collect each parameter one at a time: 1. Domain — Ask: "What domain? (engineering, marketing, content, prompts, custom)" 2. Name — Ask: "Experiment name? (e.g., api-speed, blog-titles)" 3. Target file — Ask: "Which file to optimize?" Verify it exists. 4. Eval command — Ask: "How to measure it? (e.g., pytest bench.py, python evaluate.py)" 5. Metric — Ask: "What metric does the eval output? (e.g., p50ms, ctrscore)" 6. Direction — Ask: "Is lower or higher better?" 7. Evaluator (optional) — Show built-in evaluators. Ask: "Use a built-in evaluator, or your own?" 8. Scope — Ask: "Store in project (.autoresearch/) or user (~/.autoresearch/)?" Then run setupexperiment.py with the collected parameters. Listing Built-in Evaluators Name Metric Use Case ------ -------- ---------- benchmarkspeed p50ms (lower) Function/API execution time benchmarksize sizebytes (lower) File, bundle, Docker image size testpassrate passrate (higher) Test suite pass percentage buildspeed buildseconds (lower) Build/compile/Docker build time memoryusage peakmb (lower) Peak memory during execution llmjudgecontent ctrscore (higher) Headlines, titles, descriptions llmjudgeprompt qualityscore (higher) System prompts, agent instructions llmjudgecopy engagementscore (higher) Social posts, ad copy, emails After Setup Report to the user: Experiment path and branch name Whether the eval command worked and the baseline metric Suggest: "Run /ar-run {domain}/{name} to start iterating, or /ar-loop {domain}/{name} for autonomous mode."
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/setup--83d46d