Menu
Skills in this repository
SkillsMP has collected 84 skills from zjunlp/Mechanist. Open a skill to review its source and details.
zjunlp/MechanistShowing 4 of 84 collected skills.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative external LLM review (llm-chat MCP). Use when the user says "refine my approach", "decompose this problem", "refine research…
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. The external LLM reviewer (via llm-chat MCP) evaluates results against intended claims and routes to next action (pivot, supplement,…
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", or needs to launch training jobs.
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.