paper-writer
VerifiedMedical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers. Triggers: 'write paper', 'paper-write', 'start manuscript', '論文を書く', '論文執筆', '論文プロジェクト', 'manuscript', 'research paper', '原稿作成'.
templates/limitations-guide.md
View on GitHub# Limitations Section Writing Guide
> Every medical paper needs a Limitations section. It demonstrates scientific rigor and helps readers interpret findings correctly. Reviewers consistently check this section.
---
## Where to Place Limitations
| Paper Type | Placement | Typical Length |
|-----------|-----------|---------------|
| Original Article | Within Discussion (usually penultimate paragraph) | 1-2 paragraphs |
| Systematic Review | Within Discussion (dedicated subsection) | 2 subsections: "Limitations of the evidence" + "Limitations of the review" |
| Case Report | Within Discussion (1 paragraph) | 3-5 sentences |
| Review Article | Within Discussion (penultimate paragraph) | 1 paragraph |
| Letter | Final paragraph (1-2 sentences) | 1-2 sentences |
---
## Categories of Limitations
### 1. Study Design Limitations
| Limitation | How to Write It | Example |
|-----------|----------------|---------|
| Retrospective design | "The retrospective nature of this study limits our ability to establish causality." | Observational studies |
| Single-center | "As a single-center study, generalizability to other settings may be limited." | Hospital-based studies |
| Cross-sectional | "The cross-sectional design precludes assessment of temporal relationships." | Survey studies |
| No control group | "The absence of a control group limits causal inference." | Before-after studies |
| Open-label | "The open-label design may have introduced performance and detection bias." | RCTs without blinding |
### 2. Population / Sample Limitations
| Limitation | How to Write It |
|-----------|----------------|
| Small sample size | "The sample size of N patients may have limited statistical power to detect smaller but clinically meaningful differences." |
| Selection bias | "Patients were recruited from a tertiary referral center, which may limit generalizability to primary care settings." |
| Lack of diversity | "The study population was predominantly [demographic], limiting applicability to other populations." |
| High attrition | "Loss to follow-up of X% may have introduced attrition bias." |
### 3. Data / Measurement Limitations
| Limitation | How to Write It |
|-----------|----------------|
| Self-reported data | "Reliance on self-reported data may have introduced recall bias." |
| Missing data | "Missing data for [variable] (X%) were handled using multiple imputation, but the results may be influenced by unmeasured confounding." |
| No validated instrument | "The [outcome measure] has not been validated in [this population]." |
| Unmeasured confounders | "We could not adjust for [confounder] as this was not captured in the dataset." |
| Short follow-up | "The [N]-month follow-up period may not capture long-term outcomes." |
### 4. Analysis Limitations
| Limitation | How to Write It |
|-----------|----------------|
| Multiple comparisons | "Multiple comparisons increase the risk of type I error; findings from secondary analyses should be interpreted with caution." |
| Post-hoc analysis | "The subgroup analysis was exploratory and should be interpreted as hypothesis-generating." |
| Confounding | "Despite multivariable adjustment, residual confounding cannot be excluded." |
---
## Writing Principles
### DO:
1. **Be specific** — name the exact limitation, don't use vague language
2. **Explain the direction of bias** — does the limitation overestimate or underestimate the effect?
3. **Describe mitigation** — what did you do to minimize the impact?
4. **Acknowledge honestly** — reviewers respect transparency
5. **Connect to strengths** — balance limitations with study strengths
### DO NOT:
1. ~~"This study has several limitations"~~ → Name them specifically
2. ~~Minimize real weaknesses~~ → Be candid
3. ~~List strengths as limitations~~ → "A limitation is that we had a large sample" is NOT a limitation
4. ~~Use limitation as excuse~~ → Present, explain impact, and describe mitigation
5. ~~Overstate limitations~~ → Don't undermine your own findings unnecessarily
---
## Template: Limitations Paragraph
```
This study has [number] main limitations. First, [limitation 1 — specific description].
This may have [direction of bias — overestimated/underestimated the effect / limited generalizability].
However, [mitigation strategy or context]. Second, [limitation 2]. [Impact and mitigation].
[Third, if applicable]. Despite these limitations, [transition to strengths or final interpretation].
```
---
## Template: Strengths and Limitations (Full Subsection)
For papers where the journal requires a dedicated "Strengths and Limitations" subsection:
```
### Strengths and Limitations
This study has several strengths. [Strength 1 — e.g., large sample, multicenter, validated outcomes].
[Strength 2 — e.g., long follow-up, robust statistical methods, diverse population].
However, several limitations should be considered. First, [limitation with direction of bias].
[Mitigation]. Second, [limitation]. [Mitigation]. Third, [limitation].
These limitations should be weighed against the strengths of [key strength] when
interpreting our findings.
```
---
## Systematic Review: Two-Part Limitations
PRISMA 2020 requires BOTH types of limitations:
```
### Limitations
#### Limitations of the Included Evidence
- [Quality of included studies — e.g., "Most studies were rated as high risk of bias
due to lack of blinding"]
- [Heterogeneity — e.g., "Substantial clinical heterogeneity across studies limited
the pooled estimate"]
- [Reporting — e.g., "Several studies did not report ITT analyses"]
#### Limitations of the Review Process
- [Search — e.g., "We searched only English-language databases, potentially missing
relevant studies in other languages"]
- [Selection — e.g., "Grey literature was not systematically searched"]
- [Analysis — e.g., "Meta-analysis was not feasible due to heterogeneity in
outcome definitions"]
```
---
## 日本語テンプレート
```
### 本研究の限界
本研究にはいくつかの限界がある。第一に、[限界1の具体的記述]。このため、
[バイアスの方向性]の可能性がある。ただし、[緩和策]。第二に、[限界2]。
[影響と緩和策]。これらの限界はあるものの、[強みへの接続]。
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |