Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

NCI Imaging Data Commons Explorer

Query, download, and preview public NCI cancer imaging data (CT, MR, PET, digital pathology) using idc-index.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

Teaches Claude the correct workflow for the idc-index Python package against the NCI Imaging Data Commons (IDC) — a large public cancer imaging archive that needs no authentication.

  • SQL metadata queries across index, collections_index, analysis_results_index, seg_index, sm_index, clinical_index, volume_geometry_index, and more, returned as pandas DataFrames.
  • DICOM downloads by collection, patient, series UID, or manifest, with dirTemplate control over folder layout.
  • Browser visualization via generated OHIF viewer URLs — no local DICOM viewer needed.
  • License and citation handling: distinguishes CC BY from CC BY-NC and emits APA/BibTeX citations.
  • Safety discipline: never installs on your behalf, forbids --break-system-packages, and pins the tested version so query results stay reproducible.
  • Documents alternative access paths: S3/GCS buckets, DICOMweb, BigQuery, and direct Parquet queries.

Who it's for

  • Researchers and grad students assembling medical-imaging datasets for AI training
  • Anyone filtering image subsets by cancer type, modality, or anatomical site
  • Industry teams that must verify commercial-use licensing before downloading
  • Digital pathology users needing slide microscopy series, annotations, or segmentations

Examples

  1. Lung CT training set: "From the NLST collection, pick chest CT series with regularly spaced 3D volumes, save a 200-series manifest, and estimate download size first."
  2. Commercially safe subset: "Exclude any CC BY-NC collection, download brain MR studies, and generate APA citations."
  3. Match annotations to source images: "Find liver segmentations in seg_index, join them to their source CT series, and give me viewer links for a few cases."

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/imaging-data-commons folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/imaging-data-commons/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/imaging-data-commons ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (PowerShell or WSL on Windows).
  2. Clone the skill repository: 
    git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy the skill into your Claude skills folder: 
    mkdir -p ~/.claude/skills
cp -r scientific-agent-skills/skills/imaging-data-commons ~/.claude/skills/
  4. Create and activate a Python virtual environment: 
    python -m venv .venv && source .venv/bin/activate
  5. Install the pinned, tested dependencies: 
    pip install 'idc-index==0.11.14' pandas pydicom
  6. Restart Claude Code and try: "List the lung CT collections available in IDC."
  7. On first run, confirm the data version with client.get_idc_version() (expect v23), and always check collection size and license before downloading — some collections are terabytes.
View source on GitHub ↗License: MIT