Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/scientific-writing-guide
Curated tools and techniques for scientific writing beyond LaTeX
Passed 26 of 26 test cases with the skill, and 22 of 26 without it.
and 2 more in the full report
4 fixed22 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
When writing the main technical sections of an empirical machine learning paper, should I interpret the benchmark experiments in the Results section first while the data is fresh, or draft the Methods section first?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends drafting the Methods section before writing the Results section. | Missed | Passed |
The instructions your model reads when the skill loads.
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.
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.
| Section | Purpose | Typical Length |
|---|---|---|
| Title | Concise summary of contribution | 8-15 words |
| Abstract | Self-contained overview | 150-300 words |
| Introduction | Context, gap, contribution | 1-2 pages |
| Related Work | Position within the field | 1-2 pages |
| Methods | Reproducible description | 2-4 pages |
| Results | Empirical findings | 2-3 pages |
| Discussion | Interpretation and limitations | 1-2 pages |
| Conclusion | Takeaways and future work | 0.5-1 page |
A strong title is specific, informative, and free of jargon abbreviations. Compare:
test cases passed, vs 22 / 26 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.