write-protocol

Name: write-protocol
Author: Aperivue

41installs53forks

How to install write-protocol?

aperivue/medsci-skills/write-protocol

$npx -y skills add Aperivue/medsci-skills --skill write-protocol

Installs into the current project.

Summary

IRB/ethics committee research protocol generator. Produces 4 core sections (Background, Study Design, Sample Size, Statistical Plan) with full prose, plus 6 skeleton sections with TODO markers for institution-specific content. Integrates outputs from design-study, calc-sample-siz

Files · 1

View on GitHub

SKILL.md

1	# Write-Protocol Skill
2
3	You are helping a medical researcher draft a research protocol for IRB/ethics committee
4	submission. This skill generates the scientific core of the protocol while providing
5	structured skeletons for institution-specific sections.
6
7	## Scope
8
9	This skill generates 4 core sections with full prose:
10	1. Background and Rationale
11	2. Study Design and Eligibility Criteria
12	3. Sample Size Justification
13	4. Statistical Analysis Plan
14
15	The remaining 6 sections are provided as structured skeletons with `[TODO]` markers,
16	because they vary significantly across institutions, countries, and regulatory frameworks.
17
18	Important: This protocol is a STARTING POINT. Every institution has its own IRB
19	submission form and requirements. The generated protocol must be adapted to your
20	institution's specific format before submission.
21
22	## Reference Files
23
24	- Protocol template: `${CLAUDE_SKILL_DIR}/references/protocol_template.md` -- complete 10-section structure with formatting guidance
25	- Ethics checklist: `${CLAUDE_SKILL_DIR}/references/ethics_checklist.md` -- jurisdiction-specific ethical requirements
26
27	Read both reference files before generating a protocol draft.
28
29	## Cross-Skill Integration
30
31	- Input from design-study: Study design recommendations, analysis unit, comparator design, validation strategy
32	- Input from calc-sample-size: `protocol/sample_size_justification.md` (canonical IRB-ready prose) + `protocol/sample_size_calc.{R,py}` (reproducible code). Embed `sample_size_justification.md` VERBATIM into Methods §Sample Size — do not rephrase numbers (per `~/.claude/rules/numerical-safety.md`).
33	- Input from search-lit: Background references with verified citations
34	- Input from define-variables: `variable_operationalization.md` — literature-grounded definitions, cutoffs, DB-variable mappings for the Methods section. Precondition: if the study is observational and no operationalization artifact exists, call `/define-variables` before drafting Methods. Do not invent phenotype/cutoff definitions from the data dictionary inside this skill.
35	- Pipeline position: search-lit -> design-study -> calc-sample-size -> define-variables -> write-protocol -> manage-project
36
37	When prior skill outputs are available, incorporate them directly. When they are not,
38	prompt the user or call the relevant skill.
39
40	---
41
42	## Communication Rules
43
44	- Communicate with the user in their preferred language.
45	- Use English for all protocol content, statistical terminology, and medical terminology.
46	- Be explicit about what is generated versus what requires institutional input.
47
48	---
49
50	## Required Inputs
51
52	Collect all required inputs before generating. Ask one question at a time if information is missing.
53
54	1. Research question / hypothesis -- specific, testable
55	2. Study type -- retrospective cohort, prospective cohort, cross-sectional, RCT, diagnostic accuracy, case-control, case series
56	3. Target population -- who, where, when
57	4. Primary outcome -- what you are measuring
58	5. Secondary outcomes (if any)
59
60	## Optional Inputs (enhance quality if available)
61
62	6. design-study output -- if `/design-study` was already run, load its recommendations
63	7. calc-sample-size output -- if `/calc-sample-size` was already run, load its results and IRB text
64	8. Key references -- DOIs or search terms for background section
65	9. Institution name -- for header and ethics section guidance
66	10. Regulatory context -- Korea (PIPA), US (HIPAA/Common Rule), EU (GDPR), other
67
68	---
69
70	## Protocol Structure -- 10 Sections
71
72	### Core Sections (Fully Generated)
73
74	#### Section 1: Background and Rationale (400-600 words)
75
76	Generate full prose covering:
77	- Clinical context: disease burden, current practice, knowledge gap
78	- Literature support: call `/search-lit` if key references are not provided; every citation must have a verified DOI or PMID
79	- Rationale: why this study is needed, what it adds to existing evidence
80	- Research question: clear statement of the hypothesis or research question
81
82	Do not use bullet points in the output. Write in full paragraphs with logical flow from
83	clinical context through knowledge gap to research question.
84
85	#### Section 2: Study Design and Eligibility Criteria (300-500 words)
86
87	Generate full prose plus structured criteria lists:
88	- Study design with justification (why this design answers this question)
89	- Setting: single-center vs multi-center, insti

People who liked this also viewed

6 picks

Type

write-protocol

41installs53forks

View on GitHub

How to install write-protocol?

aperivue/medsci-skills/write-protocol

$npx -y skills add Aperivue/medsci-skills --skill write-protocol

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Write-Protocol Skill
2
3	You are helping a medical researcher draft a research protocol for IRB/ethics committee
4	submission. This skill generates the scientific core of the protocol while providing
5	structured skeletons for institution-specific sections.
6
7	## Scope
8
9	This skill generates 4 core sections with full prose:
10	1. Background and Rationale
11	2. Study Design and Eligibility Criteria
12	3. Sample Size Justification
13	4. Statistical Analysis Plan
14
15	The remaining 6 sections are provided as structured skeletons with `[TODO]` markers,
16	because they vary significantly across institutions, countries, and regulatory frameworks.
17
18	Important: This protocol is a STARTING POINT. Every institution has its own IRB
19	submission form and requirements. The generated protocol must be adapted to your
20	institution's specific format before submission.
21
22	## Reference Files
23
24	- Protocol template: `${CLAUDE_SKILL_DIR}/references/protocol_template.md` -- complete 10-section structure with formatting guidance
25	- Ethics checklist: `${CLAUDE_SKILL_DIR}/references/ethics_checklist.md` -- jurisdiction-specific ethical requirements
26
27	Read both reference files before generating a protocol draft.
28
29	## Cross-Skill Integration
30
31	- Input from design-study: Study design recommendations, analysis unit, comparator design, validation strategy
32	- Input from calc-sample-size: `protocol/sample_size_justification.md` (canonical IRB-ready prose) + `protocol/sample_size_calc.{R,py}` (reproducible code). Embed `sample_size_justification.md` VERBATIM into Methods §Sample Size — do not rephrase numbers (per `~/.claude/rules/numerical-safety.md`).
33	- Input from search-lit: Background references with verified citations
34	- Input from define-variables: `variable_operationalization.md` — literature-grounded definitions, cutoffs, DB-variable mappings for the Methods section. Precondition: if the study is observational and no operationalization artifact exists, call `/define-variables` before drafting Methods. Do not invent phenotype/cutoff definitions from the data dictionary inside this skill.
35	- Pipeline position: search-lit -> design-study -> calc-sample-size -> define-variables -> write-protocol -> manage-project
36
37	When prior skill outputs are available, incorporate them directly. When they are not,
38	prompt the user or call the relevant skill.
39
40	---
41
42	## Communication Rules
43
44	- Communicate with the user in their preferred language.
45	- Use English for all protocol content, statistical terminology, and medical terminology.
46	- Be explicit about what is generated versus what requires institutional input.
47
48	---
49
50	## Required Inputs
51
52	Collect all required inputs before generating. Ask one question at a time if information is missing.
53
54	1. Research question / hypothesis -- specific, testable
55	2. Study type -- retrospective cohort, prospective cohort, cross-sectional, RCT, diagnostic accuracy, case-control, case series
56	3. Target population -- who, where, when
57	4. Primary outcome -- what you are measuring
58	5. Secondary outcomes (if any)
59
60	## Optional Inputs (enhance quality if available)
61
62	6. design-study output -- if `/design-study` was already run, load its recommendations
63	7. calc-sample-size output -- if `/calc-sample-size` was already run, load its results and IRB text
64	8. Key references -- DOIs or search terms for background section
65	9. Institution name -- for header and ethics section guidance
66	10. Regulatory context -- Korea (PIPA), US (HIPAA/Common Rule), EU (GDPR), other
67
68	---
69
70	## Protocol Structure -- 10 Sections
71
72	### Core Sections (Fully Generated)
73
74	#### Section 1: Background and Rationale (400-600 words)
75
76	Generate full prose covering:
77	- Clinical context: disease burden, current practice, knowledge gap
78	- Literature support: call `/search-lit` if key references are not provided; every citation must have a verified DOI or PMID
79	- Rationale: why this study is needed, what it adds to existing evidence
80	- Research question: clear statement of the hypothesis or research question
81
82	Do not use bullet points in the output. Write in full paragraphs with logical flow from
83	clinical context through knowledge gap to research question.
84
85	#### Section 2: Study Design and Eligibility Criteria (300-500 words)
86
87	Generate full prose plus structured criteria lists:
88	- Study design with justification (why this design answers this question)
89	- Setting: single-center vs multi-center, insti

People who liked this also viewed

6 picks

Type