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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/imaging-data-commons/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

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 executable code and clear references, but it is over-long with redundant boilerplate and general imaging tutorials, and it ships a broken reference (clinical_data_guide.md) plus inlined content that belongs in separate files. Batch download workflows also lack validation feedback loops.

Suggestions

Add the missing references/clinical_data_guide.md to the bundle (or remove its three inline references) so progressive disclosure navigation is not broken.

Trim general-concept tutorials (DICOM hierarchy, pydicom/SimpleITK/NumPy basics) and factor the repeated `from idc_index import IDCClient; client = IDCClient()` boilerplate into a single setup snippet to improve conciseness.

Insert explicit validation/feedback steps into the batch download and manifest workflows (e.g., verify download integrity and retry on failure) so workflow clarity is not capped at 3.

Dimension	Reasoning	Score
Conciseness	At ~1180 lines it is mostly useful and skill-specific but includes unnecessary explanation of concepts Claude already knows (DICOM hierarchy, pydicom/SimpleITK/NumPy basics) and repeated import boilerplate across many code blocks, so it could be tightened.	3 / 5
Actionability	Pervasive copy-paste-ready SQL and Python, concrete CLI commands, and parameter tables cover the common cases fully and are executable as written.	5 / 5
Workflow Clarity	The Query→Download→Visualize sequence is clear, but batch/download operations lack explicit validation checkpoints or validate→fix→retry feedback loops, which the rubric caps at 3 for destructive/batch workflows.	3 / 5
Progressive Disclosure	Structure with one-level-deep references is good, but references/clinical_data_guide.md is referenced three times yet is absent from the bundle, and large SQL-patterns and integration-tutorial content is inlined rather than split out.	3 / 5
	Total	14 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 specific, trigger-rich, and clearly distinguishes the skill with an explicit Use-for clause and third-person voice. It only narrowly misses full trigger-term marks by omitting a few common synonyms (e.g., DICOM, medical images).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Query and download", "Query by metadata, visualize in browser, check licenses") with comprehensive coverage of the skill's capabilities, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ("Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index") and when ("Use for accessing large-scale radiology... for AI training or research") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms ("cancer imaging data", "radiology (CT, MR, PET)", "pathology", "AI training or research") but missing common synonyms like "DICOM" or "medical images", placing it just below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	A clear niche (NCI IDC / cancer imaging) with a specific package (idc-index) and distinct modality triggers gives it minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 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: 3a6c3a9

Reviewed: 1 day 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.