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.
77
75%
Does it follow best practices?
Impact
73%
1.35xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/imaging-data-commons/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly identifies a specific domain (cancer imaging data from NCI), names the tool (idc-index), lists concrete actions (query, download, visualize, check licenses), and provides explicit usage triggers. The inclusion of imaging modalities (CT, MR, PET) and use cases (AI training, research) adds excellent specificity and trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: query, download, access radiology/pathology datasets, query by metadata, visualize in browser, check licenses. Also specifies modalities (CT, MR, PET) and the specific tool (idc-index). | 3 / 3 |
Completeness | Clearly answers 'what' (query and download public cancer imaging data, query by metadata, visualize, check licenses) and 'when' ('Use for accessing large-scale radiology and pathology datasets for AI training or research'). The 'Use for' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'cancer imaging', 'NCI Imaging Data Commons', 'idc-index', 'radiology', 'CT', 'MR', 'PET', 'pathology', 'AI training', 'research', 'download'. Good coverage of domain-specific terms a researcher would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: NCI Imaging Data Commons, idc-index, cancer imaging data. Very unlikely to conflict with other skills given the specific domain, tool name, and data source. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with comprehensive, executable code examples covering the full IDC workflow. However, it suffers significantly from verbosity — it tries to be both an overview document and a comprehensive reference, undermining the progressive disclosure structure it sets up with its reference guides. The workflow lacks explicit validation checkpoints for batch operations like large downloads.
Suggestions
Reduce inline content by 50-60%: move CLI documentation to cli_guide.md, cloud storage details to cloud_storage_guide.md, integration pipeline code to use_cases.md, and detailed table schemas to index_tables_guide.md — keep only the core query/download/visualize patterns inline
Add validation checkpoints to the download workflow: verify download count matches query count, check file sizes, and include retry logic for batch operations
Remove the version check/upgrade code block at the top — a single line instruction ('Ensure idc-index ≥0.11.10') suffices; Claude knows how to upgrade packages
Consolidate the repeated version verification reminders (appears 3+ times) into a single best-practice bullet point
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~600+ lines. It includes extensive inline content that should be in reference files (full SQL examples, detailed table schemas, integration pipeline code with SimpleITK/numpy, CLI documentation, cloud storage details). Much of this duplicates what the referenced guide files already cover. Claude doesn't need explanations of what DICOM is or how to stack numpy arrays. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code throughout — SQL queries, download commands, visualization code, CLI examples, and integration patterns. Every code block is concrete with real function calls, parameters, and expected outputs. | 3 / 3 |
Workflow Clarity | The core workflow is stated (query → download → visualize) and individual steps have clear code, but there are no validation checkpoints for potentially destructive batch download operations. The batch processing section lacks error handling, retry logic, or verification that downloads completed successfully. The troubleshooting section is separate rather than integrated into workflows. | 2 / 3 |
Progressive Disclosure | The skill has a good Quick Navigation table pointing to 9 reference guides with clear decision triggers, which is excellent. However, the main document itself contains far too much inline content that belongs in those reference files — full CLI documentation, cloud storage details, integration pipeline code, detailed table schemas, and extensive SQL examples are all inline when they should be in the referenced guides. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (844 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- 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.