菜单
Bootstrap new biomedical ML research repositories with production-grade structure. Use when: (1) Creating a new research project from scratch, (2) Setting up pyproject.toml with uv, (3) Establishing directory layout, CLAUDE.md, or config patterns for a biomedical/healthcare ML project.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/1nslyn/biomed-agent-kit --skill project-scaffold命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Process and analyze biomedical text data (clinical notes, radiology reports, PubMed abstracts). Use when: (1) Loading biomedical language models (PubMedBERT, ClinicalBERT, BioBERT, BioGPT) and extracting embeddings, (2) Named entity recognition for medical concepts with scispaCy, (3) UMLS concept linking, (4) Text classification of clinical documents, (5) Extracting structured data from unstructured clinical text (vitals, lab values, findings).
Smart granular commit workflow that groups changes into separate, logically-grouped commits by feature, functionality, or type. Never commits everything at once. No co-author line. Uses Conventional Commits. Use when user says commit, /commit, or commit my changes, or asks to save/checkpoint work, or at the end of a task when changes need to be committed.
Load and preprocess biomedical data (DICOM, NIfTI, whole-slide images, tabular clinical data). Use when: (1) Loading DICOM/NIfTI/WSI files and extracting metadata, (2) Intensity normalization for CT/MRI, (3) Stain normalization for histopathology, (4) Building PyTorch Dataset classes with caching or HDF5, (5) Designing augmentation pipelines for medical imaging (2D or 3D).
基于 SOC 职业分类
正在显示 SKILL.md
| name | project-scaffold |
| description | Bootstrap new biomedical ML research repositories with production-grade structure. Use when: (1) Creating a new research project from scratch, (2) Setting up pyproject.toml with uv, (3) Establishing directory layout, CLAUDE.md, or config patterns for a biomedical/healthcare ML project. |
python scripts/init_project.py my-study --path /path/to/workspace --python-version 3.11
python scripts/init_project.py my-study --path /path/to/workspace --python-version 3.11 --docker --dependency monai
cd my-study && uv sync && uv run pytest tests/
Creates a uv-managed Python project with: src/<pkg>/config.py for
paths/settings, tests/, a dated docs/<YYYYMMDD>/ directory, CLAUDE.md,
pre-commit hooks, ruff config, and standard biomedical ML dependencies.
my-study/
├── pyproject.toml # uv/hatch config + dependencies + ruff config
├── .python-version # Pinned Python version
├── .pre-commit-config.yaml # ruff linting + formatting
├── .env.example # Template for secrets
├── .gitignore
├── CLAUDE.md # Agent guidance
├── README.md
├── Dockerfile # Optional, if --docker is passed
├── .dockerignore # Optional, if --docker is passed
├── src/<pkg>/
│ ├── __init__.py
│ └── config.py # Paths and project settings (env var overrides)
├── scripts/ # CLI entry points
├── tests/
│ └── test_config.py
└── docs/<YYYYMMDD>/ # Dated reports and figures
ASK the user before scaffolding:
| File | Read When |
|---|---|
| references/project-structure.md | Directory layout conventions, uv setup, config patterns, CLAUDE.md template, pre-commit/ruff setup, Docker support, env var management |
| Script | Purpose |
|---|---|
scripts/init_project.py | Scaffold a minimal new project (supports --python-version, --docker, and repeatable --dependency flags) |