Generates a structured prompt framework for clinical study protocols. Supports Diagnostic, Efficacy, Etiology, and Prognosis studies. Calculates sample size and provides logic guides for LLMs.
scripts/calculators/sample_size.py plus 4 additional script(s).Python: 3.10+. Repository baseline for current packaged skills.Third-party packages: not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.cd "20260316/scientific-skills/Protocol Design/clinic-research-design"
python -m py_compile scripts/main.py
python scripts/main.py --help
Example run plan:
CONFIG block or documented parameters if the script uses fixed settings.python scripts/main.py with the validated inputs.scripts/calculators/sample_size.py with additional helper scripts under scripts/.Run this minimal command first to verify the supported execution path:
python scripts/main.py --help
This skill serves as a Logic & Structure Engine for AI Agents. Instead of outputting a finished text document, it generates a Structured Prompt / Writing Guide.
An Agent (like a specialized medical writer bot) should call this skill to get the "Skeleton" and "Logic", and then use its own LLM capabilities to "Flesh out" the content based on the detailed instructions provided in the output.
When an Agent receives a request like "Write a protocol for a diabetes drug trial", it should:
python scripts/main.py --type efficacy --P "Type 2 Diabetes" --I "Metformin" --C "Placebo" --O "HbA1c" --study_design "RCT"
output/protocol.md) will contain sections like:
[LLM Instruction]: Write a 3-4 paragraph introduction. Discuss gaps in understanding risk factors for...
--type: diagnostic, efficacy, etiology, prognosis--P, --I, --C, --O: PICO elements.--study_design: Specific design (e.g., RCT, cohort).--sensitivity, --specificity, --alpha, --power: Statistical parameters.The output is a Markdown file containing:
> [LLM Instruction]: ... specific guidance for the LLM on what to write and how to write it for that specific section.clinic_research_design_result.md unless the skill documentation defines a better convention.Run this minimal verification path before full execution when possible:
python scripts/main.py --help
Expected output format:
Result file: clinic_research_design_result.md
Validation summary: PASS/FAIL with brief notes
Assumptions: explicit list if any