clinical-data-cleaner
Clean and standardize clinical trial data to CDISC SDTM standards for FDA/EMA regulatory submissions. Handles missing values, outlier detection, date standardization, and generates audit trails for DM, LB, and VS domains.
92
91%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%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, technically specific description that clearly identifies its niche in clinical trial data standardization for regulatory compliance. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology provides excellent distinctiveness but could benefit from explicit trigger guidance.
Suggestions
Add a 'Use when...' clause with trigger phrases like 'Use when preparing clinical trial data for regulatory submission, standardizing to CDISC/SDTM format, or cleaning pharmaceutical study data.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'clean and standardize clinical trial data', 'handles missing values, outlier detection, date standardization', 'generates audit trails', and specifies domains (DM, LB, VS). | 3 / 3 |
Completeness | Clearly answers 'what' with detailed capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied through the domain context. | 2 / 3 |
Trigger Term Quality | Excellent coverage of domain-specific terms users would naturally use: 'clinical trial data', 'CDISC', 'SDTM', 'FDA', 'EMA', 'regulatory submissions', 'audit trails', and specific domain codes (DM, LB, VS). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific regulatory standards (CDISC SDTM), regulatory bodies (FDA/EMA), and clinical trial domain codes. Very unlikely to conflict with other skills due to specialized terminology. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that demonstrates strong technical writing for a complex domain. It efficiently covers CDISC SDTM data cleaning with executable code, clear workflows, explicit validation steps, and appropriate progressive disclosure to reference materials. The input validation section and fallback handling show thoughtful boundary-setting for the skill's scope.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting only necessary information without explaining concepts Claude already knows. Tables, code snippets, and structured sections maximize information density while maintaining clarity. | 3 / 3 |
Actionability | Provides fully executable Python code examples and complete CLI commands with all parameters. The code is copy-paste ready with concrete examples for each capability (validation, missing values, outliers, dates, full pipeline). | 3 / 3 |
Workflow Clarity | Clear 5-step workflow with explicit validation checkpoints, fallback handling for missing parameters, and structured output requirements. Error handling section provides specific guidance for failure scenarios with recovery paths. | 3 / 3 |
Progressive Disclosure | Well-organized with quick start, core capabilities, CLI usage, and parameters as distinct sections. References to external files (sdtm_ig_guide.md, domain_specs.json, etc.) are one level deep and clearly signaled at the end. | 3 / 3 |
Total | 12 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- 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.