@zhelunsun

agentic-research-harness enforces cognitive discipline for ai-led experiments through repo structure, governance rules, and phase workflows rather than prescriptive recipes. teaches agents how to reason about controlled experiments, dual-track validation, effect sizes, and claim boundaries before scaling.

Turn any idea into a polished, versioned, publishable OpenClaw skill — no scaffolding, no guesswork. Just say "新 skill" or "build a skill" and Skill Factory...