Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
$npx -y skills add brycewang-stanford/auto-empirical-research-skills --skill autoresearch-skillInstalls into the current project.
Run `npx skills use "https://github.com/brycewang-stanford/auto-empirical-research-skills" --skill "brycewang-stanford/auto-empirical-research-skills/autoresearch-skill"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/brycewang-stanford/auto-empirical-research-skills" that are relevant to the current task. Run `npx skills add "https://github.com/brycewang-stanford/auto-empirical-research-skills"` and select the relevant skills, then follow their instructions.