autoresearch

Scan a codebase to find files and functions where autoresearch could be applied — code with tunable parameters, magic numbers, scoring logic, or prompt templates that could be optimized against a measurable metric. Use when the user wants to find optimization candidates, asks 'where could I use autoresearch?', 'what can I tune?', 'find tunable code', or wants to discover what's optimizable before running /autoresearch.

Set up and run Karpathy-style autoresearch experiments on any codebase with a measurable metric. Use this skill whenever the user wants to autonomously optimize code by running iterative experiments — tuning search ranking, scoring functions, prompt templates, weight parameters, algorithm configurations, or any logic where changes can be evaluated against a numerical metric. Also trigger when the user mentions 'autoresearch', 'overnight optimization', 'autonomous experiments', 'autoresearch loop', 'Karpathy loop', or wants to 'let Claude Code optimize this while I sleep'. This skill generates the full experiment harness: instructions.md, eval script, test data template, and launch prompt — scoped to their specific codebase.