Agent skill

Scientific Writing Guide

by wentorai in wentorai/research-plugins

Curated tools and techniques for scientific writing beyond LaTeX

MITAuto-check passedResearch & Science

Install Scientific Writing Guide

skills CLI
$ npx skills add wentorai/research-plugins --skill scientific-writing-guide -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wentorai/research-plugins scientific-writing-guide --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing/composition/scientific-writing-guide .claude/skills/scientific-writing-guide && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
scientific-writing-guide
GitHub stars
298
Used in
1 other repo
Token cost
~2.7k tokens
SKILL.md length
1,201 words
Files
1
Skills in repo
405
Repo updated
First seen
Licence
MIT

At a glance

Curated tools and techniques for scientific writing beyond LaTeX

  • Works in 5 steps: Outline first. Write one sentence per… → Draft figures and tables early. These… → Write Methods before Results. Describing… → …
  • Tasks that involve Scientific writing
  • SKILL.md covers Overview, Structuring a Research Paper, Writing Titles and Abstracts and Authoring Tools and Workflows, plus 6 more sections
  • Calls pandoc

What it does

Scientific Writing Guide is an agent skill from wentorai/research-plugins. Curated tools and techniques for scientific writing beyond LaTeX

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Scientific writing and LaTeX. It works with LaTeX. The repository describes itself as: 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Scientific writing
  • Tasks that involve LaTeX

Example prompts

  • “/scientific-writing-guide”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Outline first. Write one sentence per section summarizing its core message.
  2. Draft figures and tables early. These anchor your results and drive the narrative.
  3. Write Methods before Results. Describing what you did is easier than interpreting outcomes.
  4. Draft the Introduction last. By then you know exactly what contribution to advertise.
  5. Iterate on the Abstract. It is the single most-read part of any paper.

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pandoc

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • microsoft.com
    • americanscientist.org
    • lijunsun.github.io
    • cs.cmu.edu

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Scientific Writing Guide loads about 2.7k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 1,201 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 1,201 words, ~2,658 tokens.

Download SKILL.mdSave it as .claude/skills/scientific-writing-guide/SKILL.md (or your agent's skills folder).
name
scientific-writing-guide
description
Curated tools and techniques for scientific writing beyond LaTeX

Scientific Writing Guide

Overview

Scientific writing is a specialized skill that demands clarity, precision, and adherence to disciplinary conventions. Whether you are drafting a journal article, conference paper, or grant proposal, the quality of your prose directly influences how reviewers and readers perceive your research.

This guide distills best practices from the awesome-scientific-writing community (920+ stars) and supplements them with actionable techniques for structuring papers, writing compelling titles and abstracts, choosing the right authoring tools, and polishing manuscripts to publication quality. The focus is on practical, tool-agnostic advice that works across STEM and social-science disciplines.

Modern scientific writing extends well beyond LaTeX. Markdown-based workflows (Pandoc, Quarto, Jupyter Book), collaborative platforms (Overleaf, HackMD), and reference managers (Zotero, Paperpile) have reshaped how researchers draft and publish. This skill helps you navigate these options and adopt a workflow that fits your team.

Structuring a Research Paper

A well-structured paper guides the reader from problem to contribution with minimal friction. The standard IMRaD (Introduction, Methods, Results, and Discussion) skeleton remains the default for empirical work, but variations exist for theoretical, review, and systems papers.

The IMRaD Skeleton
SectionPurposeTypical Length
TitleConcise summary of contribution8-15 words
AbstractSelf-contained overview150-300 words
IntroductionContext, gap, contribution1-2 pages
Related WorkPosition within the field1-2 pages
MethodsReproducible description2-4 pages
ResultsEmpirical findings2-3 pages
DiscussionInterpretation and limitations1-2 pages
ConclusionTakeaways and future work0.5-1 page
Step-by-Step Drafting Process
  1. Outline first. Write one sentence per section summarizing its core message.
  2. Draft figures and tables early. These anchor your results and drive the narrative.
  3. Write Methods before Results. Describing what you did is easier than interpreting outcomes.
  4. Draft the Introduction last. By then you know exactly what contribution to advertise.
  5. Iterate on the Abstract. It is the single most-read part of any paper.

Writing Titles and Abstracts

Titles

A strong title is specific, informative, and free of jargon abbreviations. Compare:

  • Weak: "A Study of Neural Networks for NLP"
  • Strong: "Attention Is All You Need: Replacing Recurrence with Self-Attention for Sequence Transduction"

Rules of thumb:

  • Include the method and the domain.
  • Avoid questions unless the answer is surprising.
  • Keep it under 15 words for most venues.
Abstracts

Use the four-sentence abstract formula:

  1. Context -- What is the broad problem area?
  2. Gap -- What specific problem remains unsolved?
  3. Approach -- What did you do?
  4. Result -- What did you find, and why does it matter?

Example template:

[Domain] faces the challenge of [problem]. Existing approaches [limitation].
We propose [method], which [key innovation]. Experiments on [benchmarks]
show that [method] achieves [metric improvements], demonstrating [significance].

Authoring Tools and Workflows

Markdown + Pandoc Pipeline

For researchers who prefer plain text and version control:

bash
# Convert Markdown to PDF via LaTeX
pandoc paper.md \
  --citeproc \
  --bibliography refs.bib \
  --csl ieee.csl \
  --pdf-engine=xelatex \
  -o paper.pdf

# Convert to DOCX for collaborators
pandoc paper.md \
  --citeproc \
  --bibliography refs.bib \
  -o paper.docx
Quarto for Reproducible Documents

Quarto extends R Markdown to Python, Julia, and Observable JS:

yaml
# _quarto.yml
project:
  type: manuscript

manuscript:
  article: paper.qmd

format:
  html: default
  pdf:
    template: elsevier.tex
Tool Comparison
ToolBest ForCollaborationVersion Control
OverleafLaTeX teamsReal-timeGit integration
QuartoCode + proseGitNative
Google DocsNon-technical coauthorsReal-timeSuggest mode
TypstFast typesettingGitNative

Grammar and Style Tools

Automated Checking

  • LanguageTool: open-source grammar, style, and spell checker with academic English support
  • Vale: prose linter that enforces writing style guides (Microsoft, Google, academic custom)
  • textlint: pluggable text linting framework with rules for technical writing
  • write-good: naive linter for English prose focusing on common writing issues
  • proselint: linter for prose that checks for jargon, cliches, and logical errors

Style Guides for Science

  • APA Publication Manual: standard for social sciences
  • Chicago Manual of Style: comprehensive general reference
  • ACS Style Guide: standard for chemistry publications
  • IEEE Editorial Style Manual: standard for engineering and computer science
  • Nature's guide for authors: concise scientific style reference

Reference Management

  • Zotero: free, open-source, with extensive plugin ecosystem
  • Mendeley: integrated with Elsevier databases, PDF annotation support
  • JabRef: open-source, BibTeX-native reference manager
  • Paperpile: lightweight, Google Docs and browser integration
  • citeproc: processes citations in any of 10,000+ CSL styles
  • Better BibTeX for Zotero: enhanced BibTeX export with stable citation keys

AI-Assisted Drafting Workflow

  1. Methods -- Most straightforward; describe what you did
  2. Results -- Present findings; closely tied to your figures and tables
  3. Discussion -- Interpret results; requires the most original thinking
  4. Introduction -- Frame the paper; easier to write once you know what you are introducing
  5. Abstract -- Compress the whole paper; write last
  6. Title -- Refine based on the actual content
Prompting Strategy

When using an LLM to draft sections, provide rich context: your outline, detailed notes, target venue, approximate word count, and explicit constraints (e.g., "Do not invent any details not present in my notes"). After generating any section, review for accuracy, completeness, consistency with the rest of the paper, and voice.

Show full SKILL.md (460 more words)Show less
Iterative Revision Prompts
  • Tighten prose: "Reduce this paragraph by 30% while preserving all key information."
  • Strengthen transitions: "Add a transition sentence between these two paragraphs that connects [concept A] to [concept B]."
  • Clarify technical content: "Rewrite this paragraph for a reader who understands [field] but is not familiar with [specific technique]."
  • Hedging calibration: "Review this paragraph and ensure claims are appropriately hedged based on the strength of the evidence."
Self-Review Checklist

Before submitting for peer review or to a journal, verify:

  • Title is specific and informative
  • Abstract contains all four elements (context, gap, approach, result)
  • All figures have descriptive captions
  • All acronyms defined at first use
  • Reference list is complete and correctly formatted
  • No placeholder text remains (search for "TODO", "XXX", "TBD")
  • Page limits and formatting requirements met
  • Author contributions and acknowledgments included
  • Supplementary materials organized and referenced
Common AI Writing Pitfalls
  • Generic hedging: AI models overuse phrases like "It is worth noting that" and "Interestingly." Remove these.
  • Circular definitions: AI sometimes defines a term using the term itself. Check all definitions.
  • False confidence: AI may present uncertain conclusions with unwarranted certainty. Calibrate claims to your evidence.
  • Homogeneous sentence structure: AI-generated text often falls into repetitive Subject-Verb-Object patterns. Vary your sentence structure.
  • Missing specifics: AI may write "significant improvement" without the actual numbers. Always insert your real data.

Common Pitfalls and How to Avoid Them

  1. Passive voice overuse. "The experiment was conducted" vs. "We conducted the experiment." Active voice is shorter and clearer.
  2. Hedging inflation. One "may" per paragraph is enough. Stacking "might potentially possibly" weakens your claims.
  3. Undefined acronyms. Always expand on first use: "Large Language Model (LLM)."
  4. Figure-text mismatch. Every figure must be referenced in the text, and the text must add interpretation beyond what the figure shows.
  5. Citation dumps. "[1-15]" without commentary is unhelpful. Group citations by contribution type: "Prior work on X [1,2] addressed Y, while [3,4] focused on Z."

Best Practices

  • Write every day. Even 30 minutes of daily writing accumulates faster than weekend marathons.
  • Use a reference manager. Zotero or Paperpile with browser extensions save hours of manual BibTeX entry.
  • Get feedback early. Share outlines and rough drafts before polishing prose.
  • Read your paper aloud. Awkward phrasing becomes obvious when spoken.
  • Check venue requirements before submission. Page limits, formatting templates, and supplementary material policies vary widely.
  • Use grammar tools as a second pass. Grammarly, LanguageTool, or Writefull catch errors humans miss, but do not replace human review.

References

© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/writing/composition/scientific-writing-guide of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Scientific Writing Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Scientific Writing Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scientific Writing Guide this skillwentorai/research-plugins2981 repos~2.7kAutomated safety check: PassMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Econ Writehanlulong/econ-writing-skill6512 repos~14kAutomated safety check: PassMIT
NSFC Grant Rationale Writerhuangwb8/ChineseResearchLaTeX2.9k—~945Automated safety check: PassMIT
Paper OrchestraAr9av/PaperOrchestra6791 repos~3.5kAutomated safety check: PassCustom licence
Paper SkillcLin-c/paper-skill119—~2.6kAutomated safety check: PassMIT

Similar skills

  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Econ Write

    hanlulong/econ-writing-skill

    Expert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists.

    651 GitHub starsUsed in 2 repos~14k tokens
    Research & ScienceAuto-check passed
  • NSFC Grant Rationale Writer

    huangwb8/ChineseResearchLaTeX

    Writes, restructures, reviews and polishes the rationale section of NSFC research grant applications in LaTeX, with backups and a diff before every write.

    2.9k GitHub stars~945 tokensUpdated 7 days ago
    Research & ScienceAuto-check passed
  • Paper Orchestra

    Ar9av/PaperOrchestra

    Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines…

    679 GitHub starsUsed in 1 repo~3.5k tokens
    Research & ScienceAuto-check passed
  • Paper Skill

    cLin-c/paper-skill

    End-to-end, Chinese-first academic research and publication workflow for reading papers, literature reviews, research framing, manuscript planning and writing, Chinese-English translation, LaTeX…

    119 GitHub stars~2.6k tokensUpdated 14 days ago
    Research & ScienceAuto-check passed
  • Backward Traceability

    lingzhi227/agent-research-skills

    Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.

    390 GitHub stars~802 tokensUpdated 7 mo ago
    Research & ScienceAuto-check passed

More from wentorai/research-plugins

All 405 skills in this repo
  • Abstract Writing Guide

    wentorai/research-plugins

    Craft structured research abstracts that maximize clarity and journal acceptance

    298 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Academic Citation Manager

    wentorai/research-plugins

    Manage academic citations across BibTeX, APA, MLA, and Chicago formats

    298 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed
  • Academic Paper Summarizer

    wentorai/research-plugins

    Summarize academic papers with structured extraction of key elements

    298 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Academic Study Methods

    wentorai/research-plugins

    Evidence-based study techniques for academic learning and retention

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Academic Tone Guide

    wentorai/research-plugins

    Adjust writing tone and register for academic audiences and venues

    298 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Academic Translation Guide

    wentorai/research-plugins

    Academic translation, post-editing, and Chinglish correction guide

    298 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Works with

Questions about Scientific Writing Guide

What does Scientific Writing Guide do?

Curated tools and techniques for scientific writing beyond LaTeX. Scientific Writing Guide is an agent skill from wentorai/research-plugins.

When should I use Scientific Writing Guide?

Scientific Writing Guide fits situations like: tasks that involve Scientific writing; tasks that involve LaTeX.

How do I install Scientific Writing Guide in Claude Code?

Run `npx skills add wentorai/research-plugins --skill scientific-writing-guide -a claude-code`. Or copy the skill folder (skills/writing/composition/scientific-writing-guide in wentorai/research-plugins) into .claude/skills/scientific-writing-guide in your project. Claude Code loads it when a task matches its description.

How do I install Scientific Writing Guide in Codex?

Run `npx skills add wentorai/research-plugins --skill scientific-writing-guide -a codex`. Or copy the skill folder (skills/writing/composition/scientific-writing-guide in wentorai/research-plugins) into .agents/skills/scientific-writing-guide in your project. Codex loads it when a task matches its description.

Can I use Scientific Writing Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wentorai/research-plugins --skill scientific-writing-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scientific-writing-guide, .gemini/skills/scientific-writing-guide, .github/skills/scientific-writing-guide and .opencode/skills/scientific-writing-guide in your project.

What does Scientific Writing Guide need to run?

Going by SKILL.md and its folder, Scientific Writing Guide needs the command-line tools its instructions call (pandoc).

Does Scientific Writing Guide access the network?

SKILL.md names 5 domains. As links in the text: github.com, microsoft.com, americanscientist.org, lijunsun.github.io and cs.cmu.edu. This is read from the text; nothing was executed.

Is Scientific Writing Guide safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Scientific Writing Guide use?

Scientific Writing Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scientific Writing Guide use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Scientific Writing Guide?

Skills that share tags, products or a category with Scientific Writing Guide: Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars), Econ Write (hanlulong/econ-writing-skill, 651 stars), NSFC Grant Rationale Writer (huangwb8/ChineseResearchLaTeX, 2.9k stars) and Paper Orchestra (Ar9av/PaperOrchestra, 679 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scientific Writing Guide?

wentorai (a GitHub user) maintains it in wentorai/research-plugins, which has 298 GitHub stars. The repository holds 405 skills in this directory. The repository was last updated on June 19, 2026.

Source: wentorai/research-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.