← Back to Skills Marketplace
114
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ecrf-designer
Description
Design clinical trial CRFs with proper validation rules
README (SKILL.md)
eCRF Designer
Clinical data collection form design.
Use Cases
- Case report form creation
- CDISC SDTM compliance
- EDC system setup
- Data validation rules
Parameters
visit_schedule: Time pointsdata_elements: Variables to collectcdisc_domain: SDTM domain
Returns
- CRF specifications
- Field validation rules
- Logic skip patterns
- Data dictionary
Example
Demographics form with edit checks for age range
Risk Assessment
| Risk Indicator | Assessment | Level |
|---|---|---|
| Code Execution | Python/R scripts executed locally | Medium |
| Network Access | No external API calls | Low |
| File System Access | Read input files, write output files | Medium |
| Instruction Tampering | Standard prompt guidelines | Low |
| Data Exposure | Output files saved to workspace | Low |
Security Checklist
- No hardcoded credentials or API keys
- No unauthorized file system access (../)
- Output does not expose sensitive information
- Prompt injection protections in place
- Input file paths validated (no ../ traversal)
- Output directory restricted to workspace
- Script execution in sandboxed environment
- Error messages sanitized (no stack traces exposed)
- Dependencies audited
Prerequisites
No additional Python packages required.
Evaluation Criteria
Success Metrics
- Successfully executes main functionality
- Output meets quality standards
- Handles edge cases gracefully
- Performance is acceptable
Test Cases
- Basic Functionality: Standard input → Expected output
- Edge Case: Invalid input → Graceful error handling
- Performance: Large dataset → Acceptable processing time
Lifecycle Status
- Current Stage: Draft
- Next Review Date: 2026-03-06
- Known Issues: None
- Planned Improvements:
- Performance optimization
- Additional feature support
Usage Guidance
This package appears coherent and low-risk for its stated purpose, but take these precautions before installing or running it:
- Inspect the included scripts/main.py (you already have it) and confirm it matches your expectations. It only writes a JSON file and prints to stdout.
- SKILL.md mentions path validation, but the script does not sanitize the output path; avoid running it with untrusted output locations and run it in a workspace/sandbox.
- The documentation references R although only Python code is present—confirm there are no missing components you expect.
- Test with non-sensitive sample data first. If you plan to use real clinical data, run in an isolated environment and ensure your own data-handling controls (encryption, access controls) are applied.
- If you need stricter guarantees, add explicit path validation or modify export_json to enforce an allowed output directory and reject parent-directory traversal.
Capability Analysis
Type: OpenClaw Skill
Name: ecrf-designer
Version: 1.0.0
The eCRF Designer skill is a legitimate tool for generating clinical trial Case Report Form templates in JSON format. The core logic in scripts/main.py is straightforward, providing templates for demographics and adverse events without any network activity, obfuscation, or unauthorized file access. The SKILL.md documentation accurately reflects the tool's functionality and includes standard security considerations.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md use-cases, and the included Python script all align: the tool generates CRF templates, prints them, and exports JSON. There are no unrelated binaries, credentials, or installs required.
Instruction Scope
SKILL.md describes only local script execution and file I/O (expected). The Python script writes an output JSON and lists templates; it does not read arbitrary system files or call external endpoints. However, SKILL.md mentions 'Python/R scripts executed locally' while the package only contains a Python script (minor documentation mismatch). Also the security checklist calls for input path validation (no ../ traversal), but main.py does not perform any path sanitization or explicit validation on the output path.
Install Mechanism
No install spec is provided (instruction-only skill) and the only code is a small standalone Python script. Nothing is downloaded from external hosts and nothing will be written to system locations by an installer.
Credentials
No environment variables, credentials, or config paths are requested. This is proportionate for a local CRF generation tool.
Persistence & Privilege
The skill does not request persistent or elevated platform privileges. always is false and there is no behavior that modifies other skills or global agent configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ecrf-designer - After installation, invoke the skill by name or use
/ecrf-designer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of ecrf-designer skill:
- Enables design of clinical trial case report forms (CRFs) with validation rules
- Supports CDISC SDTM compliance and logic skip patterns
- Outputs CRF specifications, field validation, and data dictionary
- Local execution of Python/R scripts; no external API use
- Includes security and risk assessments with checklist
- No extra Python dependencies required
Metadata
Frequently Asked Questions
What is eCRF Designer?
Design clinical trial CRFs with proper validation rules. It is an AI Agent Skill for Claude Code / OpenClaw, with 114 downloads so far.
How do I install eCRF Designer?
Run "/install ecrf-designer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is eCRF Designer free?
Yes, eCRF Designer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does eCRF Designer support?
eCRF Designer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created eCRF Designer?
It is built and maintained by AIpoch (@aipoch-ai); the current version is v1.0.0.
More Skills