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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill imaging-data-commons89
Quality
92%
Does it follow best practices?
Impact
73%
1.35xAverage score across 3 eval scenarios
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 specialized niche (NCI cancer imaging data), lists concrete capabilities, and provides explicit usage triggers. The description effectively uses domain-specific terminology that users in this field would naturally use, and the specificity of the data source (NCI Imaging Data Commons, idc-index) makes it highly distinguishable from other data-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Query and download', 'Query by metadata', 'visualize in browser', 'check licenses'. Also specifies data types (CT, MR, PET, pathology) and use cases (AI training, research). | 3 / 3 |
Completeness | Clearly answers 'what' (query/download cancer imaging data, visualize, check licenses) and 'when' with explicit trigger: 'Use for accessing large-scale radiology and pathology datasets for AI training or research.' | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'cancer imaging', 'NCI', 'Imaging Data Commons', 'idc-index', 'radiology', 'CT', 'MR', 'PET', 'pathology', 'AI training', 'research'. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific niche: NCI Imaging Data Commons, idc-index tool, cancer imaging data. Very unlikely to conflict with other skills due to specialized domain and named data source. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, well-structured skill that provides comprehensive guidance for accessing IDC imaging data. Its strengths are excellent actionability with executable code examples, clear workflow sequencing, and smart progressive disclosure to reference guides. The main weakness is moderate verbosity - some sections could be tightened without losing clarity, particularly the introductory material and repeated version checking reminders.
Suggestions
Consolidate version checking into a single concise block rather than repeating the importance multiple times throughout the document
Remove explanatory text that Claude already knows (e.g., 'PDF (Portable Document Format)' equivalent explanations about DICOM hierarchy basics) and trust Claude's medical imaging knowledge
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | While the skill is comprehensive and well-organized, it includes some redundant explanations (e.g., explaining what IDC is multiple times, verbose setup sections) and could be tightened. The version checking code block at the top is lengthy, and some sections repeat information that Claude would already know. | 2 / 3 |
Actionability | Excellent executable code examples throughout - SQL queries, Python download code, CLI commands, and integration examples are all copy-paste ready. Every major capability has concrete, working code with realistic parameters and expected outputs. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints. The core workflow is stated upfront (query → download → visualize), version verification is emphasized as a first step, and troubleshooting provides clear error-solution pairs. Batch processing includes size estimation guidance. | 3 / 3 |
Progressive Disclosure | Excellent structure with Quick Navigation table pointing to 9 reference guides with clear 'When to Load' triggers. Core content is inline with appropriate depth, while advanced topics (BigQuery, DICOMweb, pathology) are properly delegated to separate files. One-level-deep references throughout. | 3 / 3 |
Total | 11 / 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 | |
- 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.