Design clinical trial CRFs with proper validation rules
Install with Tessl CLI
npx tessl i github:aipoch/medical-research-skills --skill ecrf-designer44
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
40%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 identifies a specialized clinical domain which provides good distinctiveness, but suffers from incomplete guidance. It lacks explicit trigger conditions ('Use when...') and could benefit from expanded natural language terms and more specific actions beyond just 'design with validation rules'.
Suggestions
Add a 'Use when...' clause with trigger terms like 'case report form', 'CRF design', 'clinical data collection', 'EDC setup', 'trial forms'
Expand the acronym CRF to 'Case Report Forms (CRFs)' and include variations like 'eCRF' for better keyword matching
List additional concrete actions such as 'define edit checks, create skip logic, set data constraints, design visit schedules'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (clinical trial CRFs) and mentions one action (design with validation rules), but doesn't list multiple concrete actions like 'create forms, define skip logic, set data constraints, generate edit checks'. | 2 / 3 |
Completeness | Describes what it does (design CRFs with validation) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'clinical trial', 'CRFs', and 'validation rules' which are relevant but uses technical jargon (CRF) without spelling out 'Case Report Forms'. Missing common variations like 'eCRF', 'data collection forms', 'EDC forms'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'clinical trial' and 'CRFs' creates a clear niche that is unlikely to conflict with other skills. This is a specialized domain with distinct terminology. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a template shell with minimal actionable content. It lists what an eCRF designer skill should do (use cases, parameters, returns) but provides no actual guidance on how to design CRFs, no code examples, no CDISC SDTM patterns, and no validation rule syntax. The majority of the content is boilerplate risk assessment and evaluation criteria that doesn't help Claude perform the task.
Suggestions
Add concrete CRF structure examples showing field definitions, data types, and validation rules in executable format (e.g., JSON schema or Python dataclass)
Provide specific CDISC SDTM domain mappings with examples (e.g., DM domain fields, required variables, controlled terminology)
Include actual validation rule syntax examples (e.g., age range checks, date logic, skip patterns) that Claude can adapt
Remove or drastically reduce the boilerplate sections (risk assessment, security checklist, evaluation criteria) and replace with actionable design guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant boilerplate (risk assessment tables, security checklists, evaluation criteria, lifecycle status) that adds little value for guiding Claude. The core content is sparse but the overall file is padded with template sections. | 2 / 3 |
Actionability | No concrete code, commands, or executable examples are provided. The 'Example' section just says 'Demographics form with edit checks for age range' without showing what that looks like or how to create it. No actual CRF structure, validation rule syntax, or CDISC compliance patterns are demonstrated. | 1 / 3 |
Workflow Clarity | No workflow or process steps are defined. The skill lists use cases and parameters but provides no sequence for how to design a CRF, no validation checkpoints, and no guidance on the actual design process. | 1 / 3 |
Progressive Disclosure | The content is organized into sections, but there are no references to detailed materials. The structure exists but contains mostly empty or boilerplate content rather than meaningful progressive disclosure of CRF design knowledge. | 2 / 3 |
Total | 6 / 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 | |
Table of Contents
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.