borghei/Claude-Skills / research-ops/clinical-research
clinical-research
VerifiedClinical study operations — protocol structure, endpoint selection, eligibility design, sample-size and power planning, site feasibility, and documentation readiness. Use when planning, auditing, or costing a study.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.7 KB |
| assets/protocol-outline-template.md | markdown | 7.3 KB |
| assets/sample_power_spec.json | config | 520 B |
| assets/sample_protocol.json | config | 2.3 KB |
| assets/sample_sites.json | config | 3.0 KB |
| references/protocol-and-endpoint-design.md | markdown | 19.4 KB |
| references/statistical-planning.md | markdown | 16.8 KB |
| scripts/power_formulas.py | script | 10.1 KB |
| scripts/protocol_auditor.py | script | 12.6 KB |
| scripts/protocol_rules.py | script | 3.2 KB |
| scripts/sample_size_calculator.py | script | 8.1 KB |
| scripts/site_feasibility_scorer.py | script | 12.1 KB |
assets/protocol-outline-template.md
View on GitHub# Clinical Study Protocol — [Short Title]
**Protocol ID:** [ID] | **Version:** [n.n] | **Date:** [YYYY-MM-DD]
**Sponsor:** [name] | **Phase:** [n] | **Registration:** [registry + ID, or "to be registered before first enrolment"]
> Structural skeleton covering the ICH E6 protocol elements. Every bracketed
> field must be replaced. Sections deferred to a separate agreement must say so
> explicitly rather than being deleted.
>
> **This template supports document preparation. It is not regulatory advice.
> The completed protocol requires sign-off from qualified biostatistics,
> clinical, and regulatory affairs personnel before submission.**
---
## 1. General information
| Field | Value |
|-------|-------|
| Protocol title | |
| Protocol ID and version | |
| Sponsor name and address | |
| Sponsor medical expert | |
| Principal investigator(s) | |
| Participating sites | |
| Clinical laboratories and other facilities | |
## 2. Background and rationale
- **Investigational product:** [name, description, formulation]
- **Nonclinical findings:** [summary with references]
- **Prior clinical findings:** [summary with references]
- **Known and potential risks and benefits:** [both, explicitly]
- **Justification for route, dose, regimen, and treatment period:**
- **Population and rationale for studying it:**
- **Compliance statement:** This trial will be conducted in compliance with the
protocol, GCP, and applicable regulatory requirements.
- **References:**
## 3. Objectives
| Role | Objective |
|------|-----------|
| Primary | |
| Secondary | |
| Exploratory | |
## 4. Trial design
- **Design:** [parallel / crossover / factorial / single-arm]
- **Schematic:** [diagram of arms, visits, and duration]
- **Randomisation:** [method, allocation ratio, stratification factors]
- **Blinding:** [who is blinded, how maintained, unblinding procedure and who may authorise]
- **Duration of participation:** [screening, treatment, follow-up]
- **Stopping rules:** [harm and futility criteria]
- **Product accountability:** [receipt, storage, dispensing, return, destruction]
- **Source data recorded directly on CRFs:** [which fields]
### Endpoints
| Role | Name | Instrument | Metric | Threshold / contrast | Timepoint | Analysis population |
|------|------|-----------|--------|---------------------|-----------|--------------------|
| Primary | | | | | | |
| Secondary 1 | | | | | | |
| Secondary 2 | | | | | | |
| Exploratory | | | | | | |
| Safety | | | | | | |
### Estimand (primary endpoint)
| Attribute | Definition |
|-----------|-----------|
| Population | |
| Variable | |
| Intercurrent events | [list each: discontinuation, rescue medication, death] |
| Handling strategy per event | [treatment policy / hypothetical / composite / while-on-treatment / principal stratum] |
| Population-level summary | [difference in means / risk difference / hazard ratio] |
## 5. Selection and withdrawal of participants
### Inclusion criteria
| # | Criterion | Reason | Objectively verifiable? |
|---|-----------|--------|------------------------|
| 1 | | | |
| 2 | | | |
### Exclusion criteria
| # | Criterion | Specific risk it addresses | Objectively verifiable? |
|---|-----------|---------------------------|------------------------|
| 1 | | | |
| 2 | | | |
**Total criteria:** [n] — **Projected screen failure rate:** [%]
**Justification if over 25:** [why each additional restriction is necessary]
### Withdrawal
- **Withdrawal from treatment — criteria:**
- **Withdrawal from study — criteria:** [distinct from the above]
- **Procedure for withdrawing a participant:**
- **Follow-up for participants who discontinue treatment:** [participants who
stop treatment should continue endpoint follow-up unless they withdraw consent]
- **Replacement policy:**
## 6. Treatment of participants
- **Treatments administered:** [name, dose, route, schedule, packaging]
- **Permitted concomitant medication:**
- **Prohibited concomitant medication and washout:**
- **Compliance monitoring:**
## 7. Assessment of efficacy
- **Efficacy parameters:**
- **Methods and timing of assessment, recording, and analysis:**
- **Schedule of assessments:** [table — must match the CRF field for field]
## 8. Assessment of safety
- **Safety parameters:**
- **Methods and timing of assessment, recording, and analysis:**
- **AE definition:** [verbatim]
- **SAE definition:** [verbatim]
- **SAE reporting window to sponsor:** [within 24 hours]
- **Reporting pathway per site:**
- **Follow-up duration after an adverse event:**
- **Data safety monitoring board:** [yes / no — if no, justify]
## 9. Statistics
- **Sample size:** [n per arm and total to enrol]
- **Justification:** [effect size, its source, alpha, sidedness, power,
allocation ratio, assumed variance and its source, dropout rate and its source]
- **Level of significance:**
- **Primary analysis method:**
- **Secondary analysis methods and testing hierarchy:**
- **Analysis populations:** ITT [definition] · mITT [definition] · Per-protocol
[definition] · Safety [definition]
- **Missing data strategy:** [pre-specified approach]
- **Sensitivity analyses:** [at least one under a different missingness assumption]
- **Interim analyses:** [number, timing, alpha spending function, boundaries] or
"none planned"
- **Multiplicity strategy:** [or "not applicable — single primary comparison"]
- **Procedure for reporting deviations from this plan:**
- **Statistician sign-off:** [name, date]
## 10. Direct access to source data
The sponsor will ensure that investigators permit trial-related monitoring,
audits, ethics committee review, and regulatory inspection, providing direct
access to source data and documents.
## 11. Quality control and quality assurance
- **Monitoring plan:**
- **Data verification approach:**
- **Audit arrangements:**
## 12. Ethics
- **Ethics committee(s) and submission plan:**
- **Informed consent process:** [who consents, when, in what language, how
documented, re-consent triggers]
- **Vulnerable populations and additional safeguards:**
- **Ethical considerations specific to this trial:**
## 13. Data handling and record keeping
- **Data management plan:**
- **Data protection basis and safeguards:**
- **Record retention period:**
## 14. Financing and insurance
[Arrangements, or a reference to the specific separate agreement.]
## 15. Publication policy
[Policy, or a reference to the specific separate agreement.]
---
## Pre-submission checklist
- [ ] All 15 sections completed or explicitly deferred to a named agreement
- [ ] Exactly one primary endpoint, with all four defining attributes
- [ ] Estimand defined including intercurrent event handling
- [ ] Eligibility criteria justified; none stated twice; all verifiable
- [ ] Withdrawal from treatment and from study defined separately
- [ ] All four analysis populations defined; ITT primary
- [ ] Missing data strategy and sensitivity analysis pre-specified
- [ ] Sample size justified with every input and its source
- [ ] Interim analyses have spending function and boundaries, or none planned
- [ ] SAE reporting window within 24 hours
- [ ] Stopping rules for harm and futility defined
- [ ] Schedule of assessments matches the CRF field by field
- [ ] Registration prepared for submission before first enrolment
- [ ] Biostatistics sign-off obtained
- [ ] Clinical sign-off obtained
- [ ] Regulatory affairs sign-off obtained
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |