This gives Claude direct access to the NCI's Imaging Data Commons, a public repository of cancer imaging data including CT, MR, PET scans, and pathology slides. You query metadata with SQL, download DICOM files, and generate browser viewer URLs without needing authentication. The skill covers 23 releases of IDC data organized into collections and analysis results (like segmentations and AI annotations). Built on the idc-index Python package with comprehensive guides for clinical data joins, cloud storage access, and digital pathology workflows. Useful when you need training data for medical imaging models or want to explore large scale radiology datasets without setting up your own PACS infrastructure. All data has individual licensing, mostly CC-BY with some non-commercial restrictions.

skills.sh installs
2K
GitHub stars
56.6K
last updated
Aug 21, 2026

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill imaging-data-commons --agent claude-code

Installs into .claude/skills of the current project.

Files

Imaging Data Commons

Overview

Query and download public cancer imaging data from the National Cancer Institute Imaging Data Commons (IDC). No authentication required for data access.

Expected network access: IDC metadata is reachable three ways — a bundled local DuckDB index (offline after installation; additional indices are fetched from GitHub and clinical tables from S3), or the hosted IDC service over MCP or REST (api.imaging.datacommons.cancer.gov, no authentication). File downloads use public GCS (storage.googleapis.com) and AWS S3 (s3.amazonaws.com) — no authentication required. DICOMweb access uses either the public IDC proxy (proxy.imaging.datacommons.cancer.gov, no auth) or the Google Cloud Healthcare API (healthcare.googleapis.com, requires GCP authentication). Optional BigQuery queries (bigquery.googleapis.com) also require GCP authentication. Citation resolution contacts DOI services. Public IDC routes require no credentials; optional Google clients use Application Default Credentials.

Reviewed 2026-09-30: idc-index 0.12.5, idc-index-data 24.2.2, IDC v24; hosted API 3.0.0b3. Recheck at use time.

Sponsors

Details

Repository
github.com/k-dense-ai/scientific-agent-skills
Categories
Backend & APIs, Security, AI & Agent Building, Data Science & ML
First seen
Jun 3, 2026

More from k-dense-ai/scientific-agent-skills

All 137
1mcollina avatarnodejs-coremcollina/skillsContributes to and debugs Node.js core, including nodejs/node commit and PR tone, contribution workflows, native crashes, V8 performance, node-gyp builds, N-API2Kskills.sh installs
2kostja94 avatargoogle-search-consolekostja94/marketing-skillsWhen the user wants to analyze Google Search Console data, use the GSC API, or interpret search performance. Also use when the user mentions "GSC," "Search Cons2Kskills.sh installs
3openprose avataropen-proseopenprose/proseActivate when the user types `prose ...`, opens a `.prose.md` file with `kind:` frontmatter, opens a `.prose` file, or asks for reusable multi-agent orchestrati2Kskills.sh installs
4zernie avatarlinter-docszernie/vigilesDeep linter reference for authoring or debugging a vigiles enforce() rule — plugin tables, AST selectors, type-aware rules, auto-fix, and edge cases for ESLint,2Kskills.sh installs
5davila7 avatarscientific-writingdavila7/claude-code-templatesCore skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create sect2Kskills.sh installs
6jamiemill avatarlayers-interaction-flowjamiemill/layers-skillsTechniques for mapping interaction structure and flow — places, affordances, edge cases, and failure paths — without committing to visual form2Kskills.sh installs