CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/imaging-data-commons/SKILL.md
SKILL.md
Quality
Evals
Security

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 commands covering realistic scenarios, but it is too long: duplicated SQL patterns, a padding 'Related Skills' section, and bulk content inlined rather than split into reference files. Batch download workflows also lack explicit verification steps.

Suggestions

Deduplicate the SQL examples: the seg_index and join queries in 'Common SQL Query Patterns' largely repeat the 'Joining Tables' section — keep one canonical set and cross-reference it.

Move 'Common Use Cases', 'Integration with Analysis Pipelines', and 'Common SQL Query Patterns' into references/ files (like bigquery_guide.md) and keep SKILL.md as a concise overview with clearly signaled links.

Add explicit verification steps to download workflows (e.g., check downloaded file counts/sizes against instanceCount/series_size_MB before proceeding, and a validate-and-retry loop for batch downloads).

DimensionReasoningScore

Conciseness

The ~1100-line body duplicates content (seg_index/join queries appear in both 'Joining Tables' and 'Common SQL Query Patterns'; 'Always consult indices_overview' is repeated ~4 times) and pads with a 'Related Skills' section describing matplotlib/seaborn/plotly that Claude already knows. Content is otherwise dense and domain-specific rather than padded with basics, so it sits at anchor 3 rather than 2.

3 / 5

Actionability

Fully executable throughout: complete Python/SQL snippets, copy-paste CLI commands ('idc download rider_pilot --download-dir ./data'), manifest generation, and troubleshooting with specific fixes like 'pydicom.dcmread(file, force=True)'. Common cases are covered.

5 / 5

Workflow Clarity

The core workflow (query -> download -> visualize) and use cases are clearly sequenced, but batch-download workflows lack explicit verification checkpoints (no step to verify downloaded files or sizes before proceeding). Per the rubric, batch operations without validation cap workflow clarity at 3.

3 / 5

Progressive Disclosure

The two references (bigquery_guide.md, dicomweb_guide.md) are real, clearly signaled, and one level deep, but the body inlines ~1100 lines of bulk content — Common SQL Query Patterns, Integration with Analysis Pipelines, and four full Use Cases — that belongs in separate reference files, matching anchor 3.

3 / 5

Total

14

/

20

Passed

Description

87%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 strong: it states concrete third-person capabilities, includes an explicit and specific 'Use for' trigger clause, and occupies a distinctive niche. The only weakness is moderate trigger-term coverage that omits common synonyms like DICOM and MRI.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Query and download public cancer imaging data', 'Query by metadata, visualize in browser, check licenses') in third person, with minor gaps such as the generic standalone 'query' and omission of citation/CLI capabilities covered in the body.

4 / 5

Completeness

Explicitly answers both: 'what' via 'Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index' and 'when' via a concrete 'Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research' trigger clause.

5 / 5

Trigger Term Quality

Good natural coverage ('cancer imaging data', 'radiology (CT, MR, PET)', 'pathology', 'AI training or research') but missing common variations users would say such as 'DICOM', 'MRI', and 'medical imaging'.

4 / 5

Distinctiveness Conflict Risk

Names a clear niche (NCI Imaging Data Commons, idc-index, public cancer imaging) with distinct triggers; minimal overlap risk with other data-access skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1151 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/imaging-data-commons/SKILL.md

Reviewed

Table of Contents

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.