scientific-writing
This is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill.
Profile →npx skills add sickn33/agentic-awesome-skills --skill scientific-writing --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides the agent to write scientific manuscripts using IMRAD structure, with citations in specified styles, and to produce figures and tables. It mandates a two-stage process: first create section outlines with key points using research-lookup, then convert those outlines into complete paragraphs. It emphasizes full paragraphs (no final bullet lists) and integration of citations, terminology, and reporting standards.
How it works
The skill requires organizing manuscripts into Introduction, Methods, Results, and Discussion, with support for alternative structures and discipline-specific formats. It prescribes Abstracts of 100-250 words, and detailed Methods documentation, results with objective reporting, and a Discussion that synthesizes findings. It enforces the use of proper citation styles (AMA, Vancouver, APA, Chicago, IEEE) and reference management practices. For visuals, it mandates Graphical Abstracts generated before other figures, using a command sequence to generate schematics and images, and requires 3-4 figures total (graphical abstract plus additional schematics/diagrams) created via provided tooling. It specifies extensive use of scientific-schematics and generate-image tools for diagrams and visuals, with examples of diagram types and commands. It also outlines broad core capabilities for structuring and writing, including stage-wise development from outlines to full prose, with emphasis on transitions, integrated citations, and adherence to reporting guidelines (CONSORT, STROBE, PRISMA, etc.).
When to use it
Use this skill when writing or revising any section of a scientific manuscript (abstract, introduction, methods, results, discussion), structuring a paper, formatting citations/references, creating or improving figures/tables, applying study-specific reporting guidelines, drafting abstracts meeting journal requirements, preparing manuscripts for submission, improving clarity and precision, and ensuring correct terminology. It is intended for research papers, reviews, and related scientific documents needing formal structure and visual augmentation.
What it can touch
The skill references various tools for visualization and writing support, including generating graphical abstracts and figures via commands like python scripts/generate_schematic.py and python scripts/generate_image.py, and using the research-lookup capability to gather literature. It specifies use of figures/ and outputs generated by these tools, as part of the manuscript preparation workflow.
Caveats
The skill declares a critical risk level and MIT license. It requires complete paragraphs (no bullet lists in final manuscript) and adherence to graphical abstract and figure requirements. It emphasizes extensive visual content generation, which may increase compute/resource needs and require careful management of figure outputs and file paths. There are explicit formatting and style expectations, including specific citation formats and section structure, with potential limitations if source materials or tools are unavailable.
# Scientific Writing ## Overview **This is the core skill for the deep research and writing tool**—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill. Scientific writing is a process for communicating research with precision and clarity. Write manuscripts using IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, and reporting guidelines (CONSORT/STROBE/PRISMA). Apply this skill for research papers and journal submissions. **Critical Principle: Always write in full paragraphs with flowing prose. Never submit bullet points in the final manuscript.** Use a two-stage process: first create section outlines with key points using research-lookup, then convert those outlines into complete paragraphs. ## When to Use This Skill This skill should be used when: - Writing or revising any section of a scientific manuscript (abstract, introduction, methods, results, discussion) - Structuring a research paper using IMRAD or other standard formats - Formatting citations and references in specific styles (APA, AMA, Vancouver, Chicago, IEEE) - C
- Overview
- When to Use This Skill
- Visual Enhancement with Scientific Schematics
- Graphical Abstract (REQUIRED)
- Additional Figures (GENERATE EXTENSIVELY)
- Core Capabilities
- 1. Manuscript Structure and Organization
- 2. Section-Specific Writing Guidance
- 3. Citation and Reference Management
- 4. Figures and Tables
- 5. Reporting Guidelines by Study Type
- 6. Writing Principles and Style
- 7. Writing Process: From Outline to Full Paragraphs
- 8. Professional Report Formatting (Non-Journal Documents)
python scripts/generate_schematic.py "your diagram description" -o figures/output.png python scripts/generate_image.py "your image description" -o figures/output.png xelatex report.tex
What does the scientific-writing skill do?
This is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill.
How do I install it?
Run `npx skills add sickn33/agentic-awesome-skills --skill scientific-writing --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.