brycewang-stanford/Auto-Empirical-Research-Skills / skills/06-fuhaoda-stats-paper-writing/stat-writing
stat-writing
UnverifiedEnd-to-end statistical writing assistant for LaTeX - draft title/abstract/keywords, expand outlines into sections, audit manuscripts, write reviewer reports and response letters, and scaffold book manuscripts.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.8 KB |
| references/10-title.md | markdown | 2.8 KB |
| references/11-abstract.md | markdown | 2.9 KB |
| references/12-keywords.md | markdown | 2.0 KB |
| references/20-introduction.md | markdown | 2.7 KB |
| references/21-data.md | markdown | 2.2 KB |
| references/22-methods.md | markdown | 2.4 KB |
| references/23-simulation.md | markdown | 2.6 KB |
| references/24-application.md | markdown | 2.0 KB |
| references/25-discussion.md | markdown | 1.9 KB |
| references/30-other-sections.md | markdown | 2.0 KB |
| references/31-general-style.md | markdown | 2.2 KB |
| references/32-english.md | markdown | 1.8 KB |
| references/40-bibtex-natbib.md | markdown | 2.1 KB |
| references/41-cross-referencing.md | markdown | 1.7 KB |
| references/50-review-report.md | markdown | 2.7 KB |
| references/51-response-to-reviewers.md | markdown | 2.4 KB |
| references/60-outline-to-section.md | markdown | 2.5 KB |
| references/70-project-proposal.md | markdown | 1.7 KB |
| references/71-book-manuscript.md | markdown | 2.4 KB |
| references/80-tooling.md | markdown | 2.0 KB |
references/60-outline-to-section.md
View on GitHub<!--
╔══════════════════════════════════════════════════════════════╗
║ 本文件为开源 Skill 原始文档,收录仅供学习与研究参考 ║
║ CoPaper.AI 收集整理 | https://copaper.ai ║
╚══════════════════════════════════════════════════════════════╝
来源仓库: https://github.com/fuhaoda/stats-paper-writing-agent-skills
项目名称: stats-paper-writing-agent-skills
开源协议: MIT License
收录日期: 2026-04-02
声明: 本文件版权归原作者所有。此处收录旨在为社会科学实证研究者
提供 AI Agent Skills 的集中参考。如有侵权,请联系删除。
-->
# Outline → full section drafting
## Goal
Turn a bullet outline into fluent LaTeX prose that follows statistical-writing norms.
## Ground rules
- Do **not** invent results, data details, or citations.
- If needed, insert ` odo{...}` placeholders.
- Keep notation light unless the outline includes it.
## Workflow
1. **Identify section type** (Intro/Data/Methods/Simulation/Results/Discussion). This determines expected elements.
2. **Convert each bullet group to a paragraph**
- one main idea per paragraph
- topic sentence first
- add a transition sentence to connect to the previous paragraph
3. **Add missing “expected elements”** using placeholders
- Methods: estimand, assumptions, inference
- Simulation: ADEMP fields
- Results: narrative interpretation of tables/figures
4. **Second pass: polish**
- tighten sentences
- check tense
- ensure figure/table references use `~
ef{}`
## Micro-templates
### Methods section skeleton
1. Overview paragraph: what the method does and why.
2. Notation + data structure.
3. Model/estimand.
4. Estimation procedure.
5. Inference/uncertainty.
### Simulation section skeleton (ADEMP)
- Aim
- Data generating mechanism
- Estimand
- Methods compared
- Performance measures
### Results section skeleton
- Restate analysis goal.
- Present key figure/table with interpretation.
- Summarize what is robust / sensitive.
## Output format
Return a LaTeX-ready `\section{...}` or `\subsection{...}` block.
If the user gave only a partial outline, explicitly state what information is missing and leave ` odo{...}` placeholders.
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: 196k | Updated | Claude CodeCodex | Verified | Install |