Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

NCI Imaging Data Commons Explorer

Query, download, and visualize public cancer imaging data from the NCI Imaging Data Commons with no authentication required.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Queries public IDC cancer imaging data (CT, MR, PET, slide microscopy) with no login required.
  • Picks the cheapest correct access path: the hosted IDC MCP server if the session has it, the REST API over curl for read-only metadata, or the idc-index Python package when you need downloads, DataFrames, or large result sets.
  • Documents the IDC data model, index tables (index, collections_index, ct_index, seg_index, ...) and the SeriesInstanceUID join key so SQL comes out right the first time.
  • Handles DICOM downloads, one-click browser viewer URLs (OHIF/SLIM), license checks (CC BY vs CC BY-NC), and citation generation.
  • Flags classic footguns, such as the reversed argument order between download_from_selection and download_dicom_series.

Who it's for

  • Researchers and grad students assembling medical-imaging AI training sets.
  • Clinical/translational scientists building radiology or digital-pathology cohorts.
  • Anyone who must verify licensing and attribution before publishing or shipping a product.

Examples

  1. "List 20 breast-cancer MR series" → generates SQL joining collections_index.cancer_types to index.
  2. "Download 5 chest CT series from the nlst collection into ./data" → extracts SeriesInstanceUIDs, then calls download_from_selection.
  3. "Can I use this cohort commercially?" → aggregates license_short_name to spot CC BY-NC series and emits APA/BibTeX citations.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/imaging-data-commons/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

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.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/imaging-data-commons ~/.claude/skills/
  5. Restart Claude Code and try a prompt such as "Find lung cancer CT data in IDC".
  6. (Optional) For file downloads or pandas analysis, install the package in a virtual environment: pip install idc-index. Metadata-only questions work with no install via the REST API.
View source on GitHub ↗License: MIT