Scientific Writing

If you're writing anything longer than a grant abstract, this skill enforces a two-stage process: build structured outlines with key points first, then convert everything to full paragraphs. Never bullet points in final output. It handles IMRAD structure, multiple citation styles (APA, AMA, Vancouver), and integrates with reporting guidelines like CONSORT and PRISMA. The interesting bit is the mandatory visual requirement: every paper needs at least one AI-generated schematic using the scientific-schematics skill, which you call via a Python script with natural language descriptions. Covers everything from methods documentation to reviewer responses, and includes detailed reference docs for citation styles and figure design.

skills.sh installs: 2K
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill scientific-writing --agent claude-code

Installs into .claude/skills of the current project.

Files

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.