domains / families / research / autoresearch

autoresearch

combined

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. Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on "optimize this page", "run autoresearch", "score these variants", "A/B test this copy".

When to use

• You have a research question explorable through experiments
• There's a measurable proxy metric for inner loop optimization
• The real contribution requires synthesis beyond the metric
• You want continuous autonomous research operation
• You have a specific one-off task (train a model, run eval, write a paper)
• No iterative experimentation needed

When not to use

• domain-specific execution tasks

Skill page

Conflict

The two skills share the name 'autoresearch' but define fundamentally different procedures. The first is a marketing/content optimization loop that generates variants of copy and scores them with a simulated 5-expert panel. The second is a scientific research orchestration skill that manages a two-loop architecture (inner experiment loop, outer synthesis loop) for autonomous AI research projects, including literature review and paper writing. They do not reproduce, shorten, or wrap each other; they are distinct workflows that happen to share a name.