Polls WandB metrics during training runs to catch NaN values, loss divergence, and gradient explosions before you waste GPU hours. Starts checking every 10 minutes, then backs off to hourly if everything looks healthy. The clever bit is it only calls out to GPT-5.5 via Codex when metrics are ambiguous, like a flattening loss curve that might be normal or might be trouble. Otherwise it just applies hard rules and stays out of your way. Works alongside the watchdog for process-level checks. Set it up with CronCreate after your first few training steps stabilize and let it run unattended. Better than discovering at 3am that your 16-hour run diverged after step 100.

skills.sh installs
512
GitHub stars
18.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add wanshuiyin/auto-claude-code-research-in-sleep --skill training-check --agent claude-code

Installs into .claude/skills of the current project.

Files

Training Check

Before each reviewer slot, follow Selectable Reviewers: resolve invocation → .aris/reviewer.json → Claude Code default (Codex MCP) with reviewer_route.py through the canonical helper resolver, preserving this slot's tier, fresh contexts, source/image inputs and deterministic gates. Codex examples/pins below apply only to backend=codex; other routes use their own first-call/reply contract. Save the route and actual returned identity; unavailable selections are REVIEW_UNAVAILABLE. Classify acceptance from actual families/completion/scope. Forward invocation reviewer/model/effort overrides to reviewer-bearing children. Generation workers are unchanged.

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.

Sponsors

Details

Repository
github.com/wanshuiyin/auto-claude-code-research-in-sleep
Categories
Data Science & ML, Automation & Workflows
First seen
Jun 3, 2026

More from wanshuiyin/auto-claude-code-research-in-sleep

All 41
1luwill avatarpaper-slide-deckluwill/research-skillsUse when the user wants visually striking, shareable slide-deck IMAGES from any content — an article, blog post, topic, or paper — where look-and-feel matters m505skills.sh installs
2wanshuiyin avatarsystem-profilewanshuiyin/auto-claude-code-research-in-sleepProfile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says "profile", "benchmark", "bottleneck", or wants perfor503skills.sh installs
3comet-ml avatarinstrumentcomet-ml/opik-skillsAdd Opik tracing to an existing codebase. Detects language (Python/TypeScript), identifies LLM frameworks, adds appropriate decorators and integrations, marks e389skills.sh installs
4liangdabiao avatarstock-question-refinerliangdabiao/claude-code-stock-deep-research-agent股票投资调研问题细化技能。将用户提供的股票名称/代码细化为结构化的8阶段投资尽调指令。通过提问澄清投资风格(价值/成长/困境反转)、持有周期(短/中/长线)、风险偏好、研究重点,生成符合专业投资研究标准的结构化调研任务。当用户提到股票分析、投资研究、股票尽调时使用此技能。369skills.sh installs
5kastalien-research avatarzod4kastalien-research/thoughtbox-dot-claudeComprehensive guide for Zod 4 schema validation library. This skill should be used when migrating from Zod 3, learning Zod 4 idioms, or building new validation 289skills.sh installs
6kastalien-research avatareffect-tskastalien-research/thoughtbox-dot-claudeComprehensive guide for Effect-TS, the functional TypeScript library. Use when building Effect applications, especially MCP servers. Covers correct APIs, common288skills.sh installs