groom
Deep-research a feature, bug, or refactor and produce a specified, estimated plan with Definition of Done. Cross-validates architecture with a second model when useful. Use when the user describes a new piece of work that needs to be shaped before implementation.
experiment-execution
Execute AI/ML experiments locally or remotely with environment, runtime, and logging controls. Prefer invoking via research-workflow. TRIGGER when: user asks to run/launch/start/resume/monitor a training job, evaluation, or benchmark, or a plan is ready for execution, or experiment needs rerun/recovery. DO NOT TRIGGER when: research investigation only (use deep-research), planning without execution (use research-plan), or env setup without launch (use project-context).
Deep Researchï¼æ·±åº¦è°ç 8 æ¥æ³ï¼
å°ç¨æ·æåºç模ç³ä¸»é¢ï¼éè¿ç³»ç»åæ¹æ³è½¬å为é«è´¨éãå¯äº¤ä»çè°ç æ¥åã