Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/scientific-writing-wrapper
AI-powered scientific writing workflow from outline to polished draft
Passed 21 of 24 test cases with the skill, and 15 of 24 without it.
and 3 more in the full report
6 fixed15 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
How long should the skeleton outline for the Conclusion section be, and what essential content must it contain?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends a 3-4 sentence summary of contributions. | Missed | Passed |
The instructions your model reads when the skill loads.
Writing a scientific paper is one of the most time-consuming parts of the research process. The Scientific Writing Wrapper skill provides a structured, AI-assisted workflow that takes you from raw research notes and results to a polished manuscript draft. It is not about generating papers from nothing—it is about using AI tools strategically to accelerate each phase of the writing process while maintaining scientific rigor and your own voice.
This skill covers the complete writing lifecycle: outlining, drafting section by section, iterative revision, and final polish. At each stage, it provides specific prompting strategies and quality checkpoints that ensure the AI output meets the standards of peer-reviewed publication. The workflow is designed to keep you in control of the scientific content while delegating the mechanical aspects of prose generation.
The approach is venue-agnostic and works for journal articles, conference papers, and technical reports across all scientific disciplines.
Before generating any prose, assemble your writing inputs:
Create a structured writing folder with the following:
manuscript/
notes/
research_question.md # Your RQ, hypotheses, and scope
key_findings.md # Bullet-point list of all results
figure_descriptions.md # Description of each figure/table and what it shows
related_work_notes.md # Notes on how your work relates to prior literature
data/
results_tables.csv # Raw data for results tables
figures/ # All figure files
references/
bibliography.bib # BibTeX file with all references
drafts/ # Generated drafts will go here
Write a detailed outline before generating any prose:
test cases passed, vs 15 / 24 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.