Autonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Uses four-way separation in both modes. Inspired by Karpathy's autoresearch.
$npx -y skills add naveedharri/benai-skills --skill autoresearchInstalls into the current project.
Run `npx skills use "https://github.com/naveedharri/benai-skills" --skill "naveedharri/benai-skills/autoresearch"` 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/naveedharri/benai-skills" that are relevant to the current task. Run `npx skills add "https://github.com/naveedharri/benai-skills"` and select the relevant skills, then follow their instructions.