What problem does it solve? Running a multi-hypothesis AI research project requires constant experiment iteration, literature tracking, and synthesis that humans cannot sustain continuously. This Skill turns an AI agent into an autonomous research project manager that keeps experiments running, records results, and steers research direction without human supervision. ## Core Features & Use Cases - Two-Loop Research Engine: An inner loop runs rapid experiments with locked protocols and measurable metrics, while an outer loop synthesizes patterns, updates findings, and decides whether to deepen, broaden, pivot, or conclude. - Continuous Agent Operation: Sets up a mandatory 20-minute wall-clock loop via Claude Code /loop or OpenClaw cron so research never stalls between sessions, with workspace files (research-state.yaml, findings.md, research-log.md) acting as persistent memory. - Domain Skill Routing and Paper Output: Routes execution tasks to domain skills (training, evaluation, interpretability, MLOps) and produces progress presentations plus a final paper via the ml-paper-writing skill. - Use Case: You want to investigate whether sleep-like consolidation phases accelerate grokking in small transformers. The skill bootstraps a literature survey, forms hypotheses, runs dozens of experiments overnight, and delivers a trajectory plot, findings narrative, and paper draft. ## Quick Start Start an autonomous research project on my question about efficient transformer architectures, set up the workspace and continuity loop, and keep running experiments until you can write the paper.
