
Scientific Writing
Draft IMRaD-aligned manuscripts, grants, and supplements with BibTeX, LaTeX, tables, and journal-specific compliance instead of free-form prose.
Install
npx skills add https://github.com/itallstartedwithaidea/agent-skills --skill scientific-writingWhat is this skill?
- Enforces IMRaD structure for papers and aligned grant section logic
- BibTeX citation management and LaTeX for equations, figures, and tables
- Journal submission constraints: word limits, figure formats, reference styles
- Evidence-first scientific discourse—not creative or marketing tone
- Handles abstracts, supplementary materials, and statistical notation in tables
Adoption & trust: 1 installs on skills.sh; 18 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
Recommended Skills
Journey fit
Manuscript preparation is the canonical Build docs shelf even when the underlying science began earlier in discovery. Docs is the primary facet because deliverables are submission-ready sections, citations, and LaTeX—not runtime code or launch copy.
Common Questions / FAQ
Is Scientific Writing safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Scientific Writing
# Scientific Writing Part of [Agent Skills™](https://github.com/itallstartedwithaidea/agent-skills) by [googleadsagent.ai™](https://googleadsagent.ai) ## Description Scientific Writing guides the production of research papers, abstracts, grant proposals, and supplementary materials with proper citation management, LaTeX formatting, and journal-specific template compliance. The agent produces manuscript sections that adhere to the conventions of scientific discourse: precise language, logical argument structure, and claims supported by evidence. Scientific writing is not creative writing. Every sentence serves a function: establishing context, presenting evidence, drawing conclusions, or acknowledging limitations. This skill enforces the IMRaD structure (Introduction, Methods, Results, and Discussion), ensures citations follow the target journal's style, and maintains the passive-to-active voice balance expected by modern journals. The skill handles the mechanical aspects of manuscript preparation: BibTeX citation management, LaTeX formatting for equations and figures, table generation with proper statistical notation, and compliance with journal submission requirements (word limits, figure formats, reference styles). These mechanical tasks consume disproportionate researcher time and are ideally suited to agent automation. ## Use When - Writing or editing research manuscript sections - Formatting papers in LaTeX for specific journals - Managing citations and generating bibliographies - Writing abstracts within word count constraints - Preparing supplementary materials and appendices - Converting between citation styles (APA, IEEE, Nature) ## How It Works ```mermaid graph TD A[Research Results] --> B[Select Target Journal] B --> C[Load Journal Template] C --> D[Write IMRaD Sections] D --> E[Introduction: Context + Gap + Hypothesis] D --> F[Methods: Reproducible Protocol] D --> G[Results: Data + Statistics + Figures] D --> H[Discussion: Interpretation + Limitations] E --> I[Citation Integration] F --> I G --> I H --> I I --> J[LaTeX Formatting] J --> K[Compliance Check: Word Limits, Figures] K --> L[Submission-Ready Manuscript] ``` Each section is written according to its rhetorical function. The Introduction narrows from broad context to the specific gap; Results presents data without interpretation; Discussion interprets results in context of existing literature. ## Implementation ```latex \documentclass[twocolumn]{article} \usepackage[utf8]{inputenc} \usepackage{amsmath, amssymb} \usepackage{graphicx} \usepackage[numbers]{natbib} \usepackage{booktabs} \title{Edge-Rendered SEO Pages: A Scalable Approach to Local Search Optimization} \author{Research Team \\ googleadsagent.ai} \date{2026} \begin{document} \maketitle \begin{abstract} We present an edge rendering architecture that generates 18,000+ unique landing pages from a matrix of 116 services and 155 cities, achieving sub-50ms time-to-first-byte globally. Our approach eliminates the build-time scaling limitations of static site generation while maintaining the SEO benefits of server-rendered HTML. Evaluation across 6 months of production traffic demonstrates a 34\% improvement in organic search impressions compared to the previous SSG approach ($p < 0.001$, $d = 0.72$). \end{abstract} \section{Introduction} Local search optimization requires unique, high-quality pages for each service-location combination~\cite{moz2025local}. Static site generation (SSG) approaches face quadratic build time growth as the service-location matrix expands~\cite{vercel2024ssg}. \end{document} ``` ```python class ManuscriptBuilder: SECTION_GUIDELINES = {