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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

72%

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

A strong, highly actionable skill body with executable examples throughout and excellent progressive disclosure into real reference files. The main weaknesses are verbosity from repeated SQL patterns and missing explicit validation feedback loops for batch download operations.

Suggestions

Add an explicit validate→fix→retry checkpoint to the batch download loop (e.g., verify file counts or pydicom.dcmread(force=True) per batch before proceeding) to lift workflow clarity.

Consolidate the repeated sql_query boilerplate into a single canonical pattern and push the longer exploratory queries into sql_patterns.md to reduce token load.

Trim or relocate the inline BigQuery/Tool-Selection tables to references where they duplicate content already available in bigquery_guide.md.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and mostly avoids explaining concepts Claude already knows, but at ~830 lines with multiple large SQL blocks and inline tables it is longer than necessary; the same SQL-query pattern is repeated across several sections and some prose could be tightened or pushed to references.	2 / 3
Actionability	Nearly every capability is demonstrated with executable, copy-paste-ready Python (sql_query, download_from_selection, get_viewer_URL, citations_from_selection) and shell (idc download) examples including realistic parameters, default dirTemplate values, and manifest formats.	3 / 3
Workflow Clarity	The core query→download→visualize sequence and version-verification-first step are clear, but batch/download operations lack explicit validation checkpoints: downloads proceed without integrity verification, and the recommended batch loop has no verify-then-retry feedback loop, which caps clarity at 2 per the rubric's destructive/batch guidance.	2 / 3
Progressive Disclosure	The body is a well-organized overview with a Quick Navigation table that signals each reference guide and its trigger, and all eight referenced files (index_tables_guide, use_cases, sql_patterns, clinical_data_guide, cloud_storage_guide, dicomweb_guide, digital_pathology_guide, bigquery_guide) exist as real one-level-deep bundle files, keeping detail out of SKILL.md.	3 / 3
	Total	10 / 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, specific, and complete: it names the tool, the concrete actions, the natural trigger terms, and an explicit "Use for" clause scoped to a distinctive niche. Voice is appropriately third-person with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Query and download public cancer imaging data", "Query by metadata, visualize in browser, check licenses" — using specific verbs tied to the idc-index package.	3 / 3
Completeness	It answers both "what" (query/download public cancer imaging data via idc-index) and "when" with an explicit "Use for accessing large-scale radiology... and pathology datasets for AI training or research" trigger clause.	3 / 3
Trigger Term Quality	It surfaces natural user-facing terms like "radiology (CT, MR, PET)", "pathology datasets", "AI training or research", and "cancer imaging data" that a user would plausibly say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and clearly scoped to NCI Imaging Data Commons / idc-index public cancer imaging data, with concrete modality and license triggers that make collision with generic data skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (848 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/imaging-data-commons/SKILL.md
Commit: f627ab5

Reviewed: about 7 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.