Research ProtocolCAUTION

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: research-protocol
description: "Write a structured research protocol or study design document. Use when asked to write a research protocol, study protocol, research plan, methodology section, or research proposal. Produces a complete protocol with objectives, methodology, ethical considerations, and analysis plan."
---

# Research Protocol Skill

Produces structured research protocols for academic, clinical, social science, or market research studies.

## Required Inputs
- **Research type** (clinical trial / observational / qualitative / systematic review / survey)
- **Research question or hypothesis**
- **Setting and population**
- **Proposed methodology**
- **Timeline**
- **Funder or institution** (if applicable)

## Output Structure

---

# Research Protocol: [Study Title]
**Version:** 1.0 | **Date:** [Date] | **PI:** [Name, institution]

---

### 1. Background and Rationale
- What is already known
- What the gap in knowledge is
- Why this study is needed now

### 2. Research Objectives
**Primary:** [One clear answerable question or hypothesis]
**Secondary:** [Additional questions]

### 3. Study Design
- **Design:** [RCT / cohort / qualitative / mixed methods]
- **Setting:** [Where]
- **Duration:** [Total period and recruitment window]
- **Rationale:** [Why this design fits the question]

### 4. Participants

**Inclusion criteria:** [List]
**Exclusion criteria:** [List]
**Sample size:** [n] — Basis: [Power calculation or saturation rationale]
**Recruitment:** [Method and source]

### 5. Methodology / Intervention

For interventional: intervention description, control, randomisation, blinding
For observational/qualitative: data collection methods, tools, data collectors

### 6. Outcomes / Measures
**Primary outcome:** [Measure], assessed by [method], at [timepoint]
**Secondary outcomes:** [Measure], [method], [timepoint]

### 7. Data Management
- Storage: [Where and anonymisation method]
- Access controls: [Who can access]
- Retention: [How long]

### 8. Analysis Plan
Quantitative: [Statistical test], [missing data handling], [software]
Qualitative: [Framework — e.g. Braun & Clarke], [quality assurance]

### 9. Ethical Considerations
- Ethics approval: [Body / reference]
- Informed consent: [Process]
- Confidentiality: [How maintained]
- Risk to participants: [Assessment and mitigation]

### 10. Dissemination Plan
- Target journals: [2-3 relevant]
- Conference presentations
- Public/patient summary

### 11. Timeline

| Phase | Activities | Start | End |
|---|---|---|---|
| Setup | Ethics, approvals, tool development | | |
| Recruitment | | | |
| Data collection | | | |
| Analysis | | | |
| Write-up | | | |

## Quality Checks
- [ ] Primary objective is singular and answerable (not compound)
- [ ] Sample size has a stated basis (power calculation or saturation rationale)
- [ ] Ethical considerations section is complete
- [ ] Analysis plan is pre-specified (not "to be determined")
- [ ] Timeline includes all phases from ethics approval to write-up

## Anti-Patterns

- [ ] Do not write an analysis plan as "to be determined" — the analysis approach must be pre-specified before data collection
- [ ] Do not skip the ethical considerations section — all research involving human participants requires ethical review
- [ ] Do not define research questions so broadly that the study cannot answer them within scope and budget
- [ ] Do not conflate the research question with the hypothesis — state them separately and clearly
- [ ] Do not omit sample size justification — an underpowered study wastes resources and produces inconclusive results

## Example Trigger Phrases
- "Write a research protocol for [study]"
- "Help me design a study to investigate [question]"
- "Write the methodology for my research proposal"

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (5)

templates/pm-discovery-agent/skills/assumption-mapper/SKILL.md

templates/pm-discovery-agent/skills/discovery-interview-guide/SKILL.md

templates/pm-discovery-agent/skills/job-story-mapper/SKILL.md

templates/pm-discovery-agent/skills/user-interview-synthesis/SKILL.md

templates/pm-launch-agent/skills/content-calendar/SKILL.md

Gates applied: no_behavioural_pass.