ecrf-designer

Design clinical trial CRFs with proper validation rules

1.70x

Quality

27%

Does it follow best practices?

Impact

97%

1.70x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Evidence insights/ecrf-designer/SKILL.md

Quality

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 clear, specialized domain (clinical trial CRFs) which provides good distinctiveness, but suffers from incomplete guidance. It lacks a 'Use when...' clause entirely, making it difficult for Claude to know when to select this skill, and could benefit from expanded trigger terms and more specific capability details.

Suggestions

Add a 'Use when...' clause with trigger terms like 'clinical trial forms', 'CRF design', 'case report form', 'EDC', 'data validation rules'

Expand the acronym CRF to 'Case Report Forms (CRFs)' and include variations like 'eCRF' to improve discoverability

List more specific actions such as 'create form fields, define edit checks, set up skip logic, configure data constraints'

Dimension	Reasoning	Score
Specificity	Names the domain (clinical trial CRFs) and mentions one action (design with validation rules), but lacks comprehensive concrete actions like 'create form fields, define skip logic, set data constraints'.	2 / 3
Completeness	Only addresses 'what' (design CRFs with validation) but completely lacks any 'when' clause or 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 (CRFs) without spelling out 'Case Report Forms' and misses common variations like 'eCRF', 'data collection forms', 'EDC'.	2 / 3
Distinctiveness Conflict Risk	The clinical trial CRF domain is highly specific and unlikely to conflict with other skills; the combination of 'clinical trial' + 'CRF' + 'validation rules' creates a clear niche.	3 / 3
	Total	8 / 12 Passed

Implementation

14%

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 placeholder with metadata but no actual instructional content. It describes what an eCRF designer should do (use cases, parameters, returns) but provides zero guidance on how to accomplish any of it. The extensive boilerplate sections (risk assessment, security checklist, evaluation criteria, lifecycle) consume tokens without adding actionable value.

Suggestions

Add concrete examples of CRF field definitions with validation rules (e.g., age range check: `AGE >= 18 AND AGE <= 120`)

Provide a step-by-step workflow for CRF creation: define visit schedule → map to CDISC domains → create field specifications → add edit checks → generate data dictionary

Include executable code or structured output examples showing what a CRF specification looks like (JSON schema, XML, or EDC-specific format)

Add references to CDISC SDTM domain documentation or include a quick-reference table mapping common data elements to standard domains

Dimension	Reasoning	Score
Conciseness	The content includes substantial boilerplate (risk assessment tables, security checklists, evaluation criteria, lifecycle status) that adds little value for guiding Claude on CRF design. The actual instructional content is minimal, but what exists isn't overly verbose.	2 / 3
Actionability	The skill provides no concrete guidance on how to actually design CRFs. No code examples, no specific validation rule syntax, no CDISC SDTM mapping examples, no field definitions - just abstract categories and a vague example mention.	1 / 3
Workflow Clarity	There is no workflow defined. The skill lists use cases and parameters but provides no sequence of steps for creating a CRF, no validation checkpoints, and no process for ensuring CDISC compliance.	1 / 3
Progressive Disclosure	The content is a flat structure with no references to detailed materials. For a complex domain like clinical trial CRF design with CDISC compliance, there should be links to SDTM domain references, validation rule examples, or EDC-specific guides.	1 / 3
	Total	5 / 12 Passed

Validation

90%

Warnings & errors only

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: 27 days ago

Table of Contents

Discovery Implementation Validation

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.