training-check
Training Check
Periodically read WandB metrics during training to catch problems early. Do not wait until training finishes to discover it was a waste of GPU time.
Context: $ARGUMENTS
Constants
- WANDB_ENTITY and WANDB_PROJECT: read from CLAUDE.md or passed as argument (format:
entity/project/run_id) - CHECK_INTERVAL: starts at 10 minutes, then gradually increases if consistently healthy: 10 min → 20 min → 30 min → 60 min (cap)
- REVIEWER_MODEL =
gpt-5.5— used via Codex MCP for ambiguous cases only
When to Use
- After training is confirmed running (session alive, loss decreasing for first few steps)
- Set up via CronCreate to fire periodically during training
- This skill checks training QUALITY, not process HEALTH. Process health (session alive, GPU utilization) is watchdog.py's job.
Workflow
More from wanshuiyin/auto-claude-code-research-in-sleep
idea-creator
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
146idea-discovery
Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says \"找idea全流程\", \"idea discovery pipeline\", \"从零开始找方向\", or wants the complete idea exploration workflow.
143research-lit
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
136auto-review-loop
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
135research-review
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
134research-pipeline
Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop) → Workflow 3 (paper writing, optional). Goes from a broad research direction all the way to a polished PDF. Use when user says \"全流程\", \"full pipeline\", \"从找idea到投稿\", \"end-to-end research\", or wants the complete autonomous research lifecycle.
132