Scientific Writing
Core skill for writing scientific manuscripts with precision and clarity using IMRAD structure.
Critical Principle
Always write in full paragraphs with flowing prose. Never submit bullet points in the final manuscript.
Two-Stage Process
- Create section outlines with key points using research-lookup
- Convert to flowing prose with complete paragraphs
Key Features
- IMRAD Structure: Introduction, Methods, Results, Discussion
- Citation Styles: APA, AMA, Vancouver, Chicago, IEEE
- Figures & Tables: Professional data visualization
- Reporting Guidelines: CONSORT, STROBE, PRISMA
- Journal Requirements: Structured/unstructured abstracts
Combines AI-driven deep research with well-formatted written outputs backed by comprehensive literature search.
Comments
No comments yet. Be the first to comment!
Related Tools
Peer Review Skill
github.com/K-Dense-AI/claude-scientific-writer
Systematic peer review toolkit for evaluating methodology, statistics, design, reproducibility, and ethics.
LaTeX Posters Skill
github.com/K-Dense-AI/claude-scientific-writer
Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter - with AI-generated visuals and poster-optimized formatting.
Research Grants Skill
github.com/K-Dense-AI/claude-scientific-writer
Write competitive research proposals for NSF, NIH, DOE, and DARPA with agency-specific formatting and review criteria.
Related Insights
Skills + Hooks + Plugins: How Anthropic Redefined AI Coding Tool Extensibility
An in-depth analysis of Claude Code's trinity architecture of Skills, Hooks, and Plugins. Explore why this design is more advanced than GitHub Copilot and Cursor, and how it redefines AI coding tool extensibility through open standards.
Complete Guide to Claude Skills - 10 Essential Skills Explained
Deep dive into Claude Skills extension mechanism, detailed introduction to ten core skills and Obsidian integration to help you build an efficient AI workflow
Seven AI Coding CLIs, Six Months: No Matter How Strong the Model, Work Needs Supervision
Claude Code, Codex, opencode, pi, omp and DeepSeek Harness all have personalities. After six months of deep use I run a division of labor: pi for the fastest cheapest reviews, omp for complex PRs, DeepSeek Harness on V4 Flash for high-frequency low-cost review, and Claude Code, Qoder and Cursor for writing. No matter how strong the model, work needs supervision — ideally from an independent third party.