autoresearch-agent

原文涵盖的主题

• Autoresearch Agent
• Slash Commands
• When This Skill Activates
• Setup
• First Time — Create the Experiment
• What Setup Creates
• Domains
• If program.md Already Exists

You sleep. The agent experiments. You wake up to results. Autonomous experiment loop inspired by Karpathy's autoresearch. The agent edits one file, runs a fixed evaluation, keeps improvements, discards failures, and loops indefinitely. Not one guess — fifty measured attempts, compounding. -- | Command | What it does | |---------|-------------| | /autoresearch-agent:setup | Set up a new experiment interactively | | /ar-run | Run a single experiment iteration | | /ar-loop | Start autonomous loop with configurable interval (10m, 1h, daily, weekly, monthly) | | /ar-status | Show dashboard and results | | /ar-resume | Resume a paused experiment | -- Recognize these patterns from the user: "Make this faster / smaller / better" "Optimize [file] for [metric]" "Improve my [headlines / copy / prompts]" "Run experiments overnight" "I want to get [metric] from X to Y" Any request involving: optimize, benchmark, improve, experiment loop, autoresearch If the user describes a target file + a way to measure success → this skill applies. -- Run the setup script. The user decides where experiments live: Project-level (inside repo, git-tracked, shareable with team): User-level (personal, in /.autores

这里只展示节选，请以完整原文和当前要求为准。