Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/06-fuhaoda-stats-paper-writing/stat-writing

stat-writing

Unverified

End-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.

references/11-abstract.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。
-->

# Abstract guidance (statistical papers)

## Non‑negotiable constraints (default)
- Target **4–10 sentences** (a common sweet spot is **6–8**).
- The abstract should be **self‑contained**.
- **No citations** in the abstract.
- **No math notation** (no equations, no heavy symbols). Replace with words.

## What the abstract must answer
Think of an abstract as “the whole paper in miniature.” It should make a reader understand:
1) **Why the problem matters** (context + importance)
2) **What is missing** in existing work (gap)
3) **What you contribute** (novelty / contribution)
4) **What you did** (core idea of methods)
5) **What evidence you provide** (theory / simulation / application)
6) **What you found** (main results—no overclaiming)
7) **Why it matters** (impact / recommendation)

## A reliable 7‑sentence template
Use this template unless the venue requires a structured abstract.

1. **Context/importance:** 1 sentence.
2. **Gap:** 1 sentence.
3. **Contribution:** 1 sentence starting with “We propose / develop / study …”.
4. **Method essence:** 1 sentence describing the method at a high level.
5. **Evidence:** 1 sentence: “We evaluate via … (theory/simulation/application).”
6. **Main results:** 1 sentence summarizing the *headline* findings.
7. **Closing/impact:** 1 sentence connecting back to the motivating problem.

### Phrase bank (use sparingly)
- “Existing approaches typically assume …; however, …”
- “We develop a method that … while …”
- “We provide theoretical guarantees / derive …”
- “Simulations show … across … scenarios.”
- “In an application to …, we find …”

## Common failure modes
- Opening with “In this paper we …” without explaining why anyone should care.
- Too much detail: notation, tuning parameters, or step-by-step algorithm.
- Vague claims: “performs well” without stating *how* or *relative to what*.
- Including citations or equations.

## Compliance checklist (return with your abstract)
- [ ] 4–10 sentences (default 6–8)
- [ ] No citations (`
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall