Stat Writing logo

Stat Writing

CommunityPopular
brycewang-stanford
stat-writing

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.

Overview

Publisherbrycewang-stanford
RepositoryAuto-Empirical-Research-Skills
Skill namestat-writing
Stars
3.8K
Forks
479
Bundled files
20
LicenseCC0-1.0
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 20 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by brycewang-stanford on GitHub. Read the source before you install it.

Installation

Install the Stat Writing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git /tmp/Auto-Empirical-Research-Skills
mkdir -p .claude/skills
cp -r /tmp/Auto-Empirical-Research-Skills/skills/06-fuhaoda-stats-paper-writing/stat-writing .claude/skills/stat-writing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Stat Writing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Stat Writing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Stat Writing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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 odo{...} 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 odo{add citation} or odo{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:
    • egin{abstract}...nd{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."

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Stat Writing AI skill do?

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.

Why use Stat Writing on TypingMind?

Because you install it once and use it with any model. Stat Writing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Stat Writing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/06-fuhaoda-stats-paper-writing/stat-writing. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Stat Writing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Stat Writing?

As many as you like. As long as a model supports skills, you can use Stat Writing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Stat Writing AI skill free?

Yes. It is published on GitHub by brycewang-stanford under the CC0-1.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
bytedance logo

Systematic Literature Review

bytedance
OrganizationPopular

Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons.…

11.4K
82.6K
6 files
View
ComposioHQ logo

Apify Automation

ComposioHQ
OrganizationPopular

Automate web scraping and data extraction with Apify -- run Actors, manage datasets, create reusable tasks, and retrieve crawl results through the Composio Apify integration.

8.7K
75.2K
Instructions
View
ruvnet logo

Browser Scrape

ruvnet
CommunityPopular

DEPRECATED in v0.2.0 -- use browser-extract instead; this is a thin shim for backward compatibility, removed in v0.3.0

8.6K
72.7K
Instructions
View
code-yeongyu logo

Ulw Research

code-yeongyu
CommunityPopular

Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw'…

5.7K
69.1K
2 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇