Scientific Writing
Core skill for producing research manuscripts, evidence-based articles, and publication-quality scientific content with rigorous standards.
Triggers
- User asks to write a research-style article
- User needs IMRAD-structured content
- User wants to write for a scientific audience
- User is drafting content requiring citations and methodology
- User needs to follow reporting guidelines (CONSORT, STROBE, PRISMA)
Two-Stage Writing Process
Stage 1: Outline with Research
- Create section outlines with bullet points
- Use pubmed-database skill for literature gathering
- Identify key citations for each point
- Structure evidence hierarchy
Stage 2: Convert to Prose
Critical: Always write in full paragraphs with flowing prose. Never submit bullet points in the final manuscript.
IMRAD Structure
| Section |
Purpose |
Key Elements |
| Introduction |
Why this matters |
Background, gap, objective |
| Methods |
What you did |
Design, population, analysis |
| Results |
What you found |
Data, statistics, figures |
| Discussion |
What it means |
Interpretation, limitations, implications |
Reporting Guidelines
For Different Study Types
| Study Type |
Guideline |
Checklist Items |
| RCTs |
CONSORT |
Randomization, blinding, flow diagram |
| Observational |
STROBE |
Selection, bias assessment, confounders |
| Systematic reviews |
PRISMA |
Search strategy, screening, synthesis |
| Diagnostic studies |
STARD |
Index test, reference standard, flow |
| Case reports |
CARE |
Timeline, diagnostic reasoning, outcomes |
Citation Standards
Supported Styles
- AMA - Medical journals (JAMA, NEJM)
- Vancouver - Numbered citations
- APA - Psychology, behavioral science
- Nature - Superscript numbered
- IEEE - Engineering/technical
Citation Best Practices
- Cite primary sources, not reviews (unless reviewing)
- Include DOI when available
- Verify accuracy with citation-management skill
- Prefer recent publications (<5 years) when current evidence exists
- Include seminal papers for historical context
Field-Specific Conventions
Cardiology/Medicine
- Report confidence intervals, not just p-values
- Include NNT/NNH for clinical relevance
- Use GRADE for evidence quality
- Specify intention-to-treat vs per-protocol
- Report absolute and relative risk
Statistical Reporting
- Mean (SD) for normal distributions
- Median (IQR) for skewed data
- HR with 95% CI for survival analysis
- OR/RR with 95% CI for binary outcomes
- Specify statistical tests used
Common Rejection Reasons (Avoid These)
- Inadequate statistical descriptions - Always specify tests, assumptions, software
- Over-interpretation of results - Stay within what data supports
- Poorly described methods - Replicability is essential
- Missing reporting checklist items - Use appropriate guidelines
- Weak literature contextualization - Show how work fits existing knowledge
Quality Checklist
Before finalizing scientific content:
1---2name: scientific-writing3description: Scientific Writing4---5# Scientific Writing67Core skill for producing research manuscripts, evidence-based articles, and publication-quality scientific content with rigorous standards.89## Triggers1011- User asks to write a research-style article12- User needs IMRAD-structured content13- User wants to write for a scientific audience14- User is drafting content requiring citations and methodology15- User needs to follow reporting guidelines (CONSORT, STROBE, PRISMA)1617## Two-Stage Writing Process1819### Stage 1: Outline with Research201. Create section outlines with bullet points212. Use pubmed-database skill for literature gathering223. Identify key citations for each point234. Structure evidence hierarchy2425### Stage 2: Convert to Prose26**Critical**: Always write in full paragraphs with flowing prose. Never submit bullet points in the final manuscript.2728## IMRAD Structure2930| Section | Purpose | Key Elements |31|---------|---------|--------------|32| **Introduction** | Why this matters | Background, gap, objective |33| **Methods** | What you did | Design, population, analysis |34| **Results** | What you found | Data, statistics, figures |35| **Discussion** | What it means | Interpretation, limitations, implications |3637## Reporting Guidelines3839### For Different Study Types40| Study Type | Guideline | Checklist Items |41|------------|-----------|-----------------|42| RCTs | CONSORT | Randomization, blinding, flow diagram |43| Observational | STROBE | Selection, bias assessment, confounders |44| Systematic reviews | PRISMA | Search strategy, screening, synthesis |45| Diagnostic studies | STARD | Index test, reference standard, flow |46| Case reports | CARE | Timeline, diagnostic reasoning, outcomes |4748## Citation Standards4950### Supported Styles51- **AMA** - Medical journals (JAMA, NEJM)52- **Vancouver** - Numbered citations53- **APA** - Psychology, behavioral science54- **Nature** - Superscript numbered55- **IEEE** - Engineering/technical5657### Citation Best Practices581. Cite primary sources, not reviews (unless reviewing)592. Include DOI when available603. Verify accuracy with citation-management skill614. Prefer recent publications (<5 years) when current evidence exists625. Include seminal papers for historical context6364## Field-Specific Conventions6566### Cardiology/Medicine67- Report confidence intervals, not just p-values68- Include NNT/NNH for clinical relevance69- Use GRADE for evidence quality70- Specify intention-to-treat vs per-protocol71- Report absolute and relative risk7273### Statistical Reporting74- Mean (SD) for normal distributions75- Median (IQR) for skewed data76- HR with 95% CI for survival analysis77- OR/RR with 95% CI for binary outcomes78- Specify statistical tests used7980## Common Rejection Reasons (Avoid These)81821. **Inadequate statistical descriptions** - Always specify tests, assumptions, software832. **Over-interpretation of results** - Stay within what data supports843. **Poorly described methods** - Replicability is essential854. **Missing reporting checklist items** - Use appropriate guidelines865. **Weak literature contextualization** - Show how work fits existing knowledge8788## Quality Checklist8990Before finalizing scientific content:91- [ ] All claims have citations92- [ ] Statistics include effect sizes and CIs93- [ ] Methods are replicable94- [ ] Limitations acknowledged95- [ ] Conclusions match evidence strength96- [ ] No AI tells or promotional language
drshailesh88