Multi-platform ML training workflow: dispatch, monitor, harvest across Kaggle / Colab / SSH / cloud GPU.
配置或查看项目的训练平台默认值(Kaggle/Colab/SSH 远程 GPU)。首次在项目中使用 trainhub 前运行,或要切换默认平台、更新凭据引用、调整指标口径时使用。触发词:配置训练平台、setup training、训练默认值、切平台。
训练完成后下载产物,解析指标,归档到 weights/ 目录。接在 train-watch 检测到 COMPLETE 之后。触发词:收实验结果、下载 kernel output、归档 weights、parse results.csv。
把训练任务派发到目标平台(Kaggle kernel / Colab notebook / SSH 远程主机)。适用:在本地准备好代码 + 配置后,推到远端开跑。触发词:提交训练、push kernel、run on kaggle/colab/ssh、派发实验。
轮询训练任务状态(Kaggle kernel / SSH tmux session / Colab runtime)。单次查询,不循环。要周期性监控请组合 /loop。触发词:查训练状态、kernel status、实验跑完没、training 进度。
Personal marketplace for Claude Code plugins developed by @Shallow-dusty.
| Plugin | Description |
|---|---|
| scriptorium | Academic research toolkit — paper search (arXiv/bioRxiv/medRxiv/PubMed/Google Scholar), Zotero integration, LaTeX thesis build/wordcount/cross-ref check, LaTeX experiment tables, animation-rich HTML presentations. |
| trainhub | Multi-platform ML training workflow — dispatch / monitor / harvest training jobs across Kaggle kernels, Google Colab, SSH remote GPU hosts. Project defaults persisted in .trainhub.json. |
# Add this marketplace to Claude Code
claude plugin marketplace add https://github.com/Shallow-dusty/claude-plugins
# Install plugins
claude plugin install scriptorium@shallow-local
claude plugin install trainhub@shallow-local
Or locally (for development):
git clone https://github.com/Shallow-dusty/claude-plugins ~/.claude/plugins/local
claude plugin marketplace add ~/.claude/plugins/local
0.1.0 — Early release, API may shift. Used daily by the author for thesis/research work.
MIT
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub shallow-dusty/claude-plugins --plugin trainhubAcademic research toolkit: paper search, Zotero, LaTeX thesis, experiment tables, and HTML slides.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).