imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with extensive executable examples and a clear overall workflow, but it is long and somewhat redundant, and its batch-download workflows lack embedded validation checkpoints. Progressive disclosure is reasonable but the main file carries content that could be offloaded to references.

Suggestions

Consolidate the repeated "always consult indices_overview" reminders and trim overlapping seg_index/join examples to reduce redundancy and length.

Embed an explicit validation checkpoint in the download workflow (e.g., verify a sample series opens with pydicom and confirm total size before proceeding with large batch downloads).

Move the full "Common SQL Query Patterns" and analysis-pipeline integration sections into a reference file, keeping SKILL.md as a leaner overview with well-signaled links.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific API/schema detail, but the ~1180-line body repeats the "consult indices_overview" guidance and overlaps some join/segmentation examples; the inline version pin (0.11.7, v23) is not isolated in a deprecated/old-patterns section.	2 / 3
Actionability	Extensive copy-paste-ready, executable code and CLI commands across querying, downloading, viewing, citations, and manifests — fully concrete guidance.	3 / 3
Workflow Clarity	The core query→download→visualize sequence and numbered use cases are clear, but batch/TB-scale downloads lack an explicit validation checkpoint/feedback loop embedded in the workflow (validation appears only in Troubleshooting), which caps clarity at 2 per the batch-operation guidance.	2 / 3
Progressive Disclosure	References to real one-level-deep files are well-signaled, but the SKILL.md itself is a large monolithic body carrying full SQL pattern references and integration examples that could be split out, matching the "content that should be separate is inline" anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and explicitly states both the capability and the use conditions. It lists concrete actions, uses natural trigger terms, and is highly distinct from other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Query and download public cancer imaging data", "Query by metadata, visualize in browser, check licenses" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (query/download IDC data via idc-index) and when ("Use for accessing large-scale radiology... for AI training or research"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "cancer imaging data", "radiology (CT, MR, PET)", "pathology", "AI training", "visualize in browser", "check licenses" — giving good coverage of natural phrasings.	3 / 3
Distinctiveness Conflict Risk	A clear, narrow niche (NCI Imaging Data Commons via idc-index) with distinct triggers that are unlikely to fire for other skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1184 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/imaging-data-commons/SKILL.md
Commit: 52845c3

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.