Token导航 LogoToken导航

Agent Skill · 研究检索

stat-writing(统计写作)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

stat-writing 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 62,001。

总安装 343周安装 14GitHub Stars 16下载 111核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:stat-writing(统计写作)
来源仓库:https://github.com/fuhaoda/stats-paper-writing-agent-skills
仓库路径:skills/stat-writing
安装命令:
npx skills add https://github.com/fuhaoda/stats-paper-writing-agent-skills --skill stat-writing
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/fuhaoda/stats-paper-writing-agent-skills --skill stat-writing

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

stat-writing 用于辅助文档、README 和内容稿件的整理与改写,适合在 Codex、Claude、Cursor、Gemini CLI 中提炼结构和统一术语。适用于文档撰写、Markdown 编辑和内容优化等场景,如技术说明、对外文案。

通过 npx skills add 命令从 GitHub 仓库安装,需保留项目已有事实和路径。涉及对外文案时应控制语气,避免过度营销或夸大能力,确保信息准确。使用前建议核验原始内容,防止将未确认信息写成确定结论。

来源仓库内路径:skills/stat-writing

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/fuhaoda/stats-paper-writing-agent-skills --ski…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

stat-writing 怎么安装?

在终端执行 npx skills add https://github.com/fuhaoda/stats-paper-writing-agent-skills --skill stat-wr…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

stat-writing 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

stat-writing 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

stat-writing 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

stat-writing 用的人多吗?

公开数据是累计安装 343 次,近一周安装 14 次,下载 111 次,GitHub 16 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

stat-writing 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
stat-writing

统计写作 · 本页

34316只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Statistical Writing (One Skill)

This is a single "workbench" skill for statistical manuscripts written in LaTeX.

Guidance is split into focused references under references/. Deterministic checks live in scripts/. Ready-to-use templates live in assets/.

Positioning: Hybrid + JDS profile

Default behavior is journal-agnostic. For Journal of Data Science (JDS), apply the JDS profile:

  • Maintain strong literature positioning and explicit novelty.
  • Require clean cross-referencing and cleaned BibTeX.
  • Prefer vector graphics for figures in the manuscript.
  • Enable line numbers for review drafts.
  • Include reproducibility artifacts (code/data/supplement) when possible.

When to use this skill

Use this skill when the user wants to:

  1. Generate compliant front matter (title, abstract, keywords).
  2. Expand outlines into complete sections in LaTeX.
  3. Audit a manuscript for structure, style, references, and reproducibility quality.
  4. Draft reviewer reports.
  5. Draft point-by-point response letters.
  6. Scaffold a book manuscript from a chapter plan.

Inputs to ask for (minimal)

Prefer file paths over pasted text.

  • Manuscript tasks: root TeX file (for example main.tex).
  • Reference checks: BibTeX file(s) (for example refs.bib).
  • Response letters: full reviewer/editor comments + revised text if available.
  • Reviewer report: manuscript or extended abstract being reviewed.
  • Book manuscript: chapter list, audience, tone, and desired notation style.

If details are missing, proceed with placeholders like \todo{...} and ask only critical questions.

Output conventions

Unless the user requests otherwise:

  • Return LaTeX-ready output.
  • For audits: rank issues as HIGH/MED/LOW with concrete fixes.
  • For rewrites: include revised text and short change log.
  • Never invent results or citations. Use \todo{add citation} or \todo{verify result}.

Task routing map

Open only the reference files needed for the task.

  • Title: references/10-title.md
  • Abstract: references/11-abstract.md
  • Keywords: references/12-keywords.md
  • Outline to section drafting: references/60-outline-to-section.md
  • Introduction: references/20-introduction.md
  • Data: references/21-data.md
  • Methods: references/22-methods.md
  • Simulation (ADEMP): references/23-simulation.md
  • Application/Results: references/24-application.md
  • Discussion: references/25-discussion.md
  • Other sections: references/30-other-sections.md
  • General style/storyline: references/31-general-style.md
  • English pitfalls: references/32-english.md
  • BibTeX/natbib: references/40-bibtex-natbib.md
  • Labels/cross-references: references/41-cross-referencing.md
  • Reviewer report: references/50-review-report.md
  • Response to reviewers: references/51-response-to-reviewers.md
  • Research proposal/project cycle: references/70-project-proposal.md
  • Book manuscript workflow: references/71-book-manuscript.md
  • Tooling/reproducibility: references/80-tooling.md

Built-in assets

  • Response letter (LaTeX): assets/response-letter-template.tex
  • Reviewer report (Markdown): assets/reviewer-report-template.md
  • Reviewer report (LaTeX): assets/reviewer-report-template.tex
  • Generic section skeleton: assets/section-skeleton.tex
  • Manuscript starter (LaTeX): assets/manuscript-template.tex
  • Book manuscript starter (LaTeX): assets/book-manuscript-template.tex

Optional scripts (deterministic checks)

  • Manuscript checks: python scripts/check_tex.py path/to/main.tex
  • Citation/BibTeX checks: python scripts/check_bib.py --tex path/to/main.tex --bib path/to/refs.bib
  • Combined run: python scripts/audit_paper.py --tex path/to/main.tex --bib path/to/refs.bib

These checks are heuristic and do not compile LaTeX.

Workflows

Workflow A - Finished paper to abstract + keywords

  1. Read introduction/methods/results/discussion.
  2. Use references/11-abstract.md and references/12-keywords.md.
  3. Draft abstract (default 6-8 sentences, acceptable 4-10, no citations, no math notation).
  4. Draft 6-10 keywords, alphabetized, avoid repeating title terms.
  5. Return:

- \begin{abstract}...\end{abstract} - \keywords{...} (or venue-specific command) - short compliance checklist.

Workflow B - Manuscript audit

  1. Run check_tex.py (and check_bib.py if .bib exists).
  2. Use references/31-general-style.md, references/40-bibtex-natbib.md, and section-specific references.
  3. Return top issues ranked by severity and concrete LaTeX edits.
  4. For JDS profile, explicitly call out line numbers, vector graphics, cleaned BibTeX, and reproducibility supplement readiness.

Workflow C - Reviewer report drafting

  1. Use references/50-review-report.md.
  2. Write summary + overall assessment + numbered major/minor comments.
  3. Keep tone constructive and professional.
  4. If requested, output using assets/reviewer-report-template.tex.

Workflow D - Response to reviewers

  1. Use references/51-response-to-reviewers.md.
  2. Structure by Editor, Associate Editor, Reviewer sections.
  3. For every comment: quote, respond, quote manuscript change, add location.
  4. If requested, render with assets/response-letter-template.tex.

Workflow E - Outline to full section

  1. Identify section type.
  2. Use references/60-outline-to-section.md + relevant section reference.
  3. Expand bullets into coherent paragraphs with transitions.
  4. Use placeholders where information is missing.

Workflow F - Book manuscript scaffolding

  1. Use references/71-book-manuscript.md.
  2. Start from assets/book-manuscript-template.tex.
  3. Build frontmatter/mainmatter/backmatter and chapter map.
  4. Keep notation generic by default; add optional custom notation block only when requested.

Copy/paste prompt patterns

Abstract + keywords

"Use stat-writing. Read main.tex and draft a compliant abstract (default 6-8 sentences, acceptable 4-10; no citations; no math notation) and 6-10 alphabetical keywords. Output LaTeX blocks."

Full audit

"Use stat-writing. Audit main.tex (+ refs.bib). Run scripts if allowed. Return top issues with HIGH/MED/LOW and patch-ready LaTeX fixes."

Response to reviewers

"Use stat-writing. Here are reviewer/editor comments. Write a point-by-point response letter with quoted manuscript revisions and locations."

Reviewer report

"Use stat-writing. Draft a reviewer report with summary, overall assessment, numbered major comments, and numbered minor comments."

Book manuscript

"Use stat-writing. Start a book manuscript from chapter bullets using the book template. Produce frontmatter/mainmatter/backmatter and chapter-by-chapter drafting plan."

平台分布

Codex

37.58%
按下载量换算42

Claude

28.19%
按下载量换算31

Cursor

17.3%
按下载量换算19

Gemini CLI

8.66%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills