Research Paper Writing

master-cai/research-paper-writing-skills

This is a structured workflow for turning messy academic drafts into reviewer-ready papers, focused on ML/CV/NLP submissions. It enforces one-message-per-paragraph discipline, runs reverse outlining after each section, and includes adversarial self-review checklists before you submit. The approach treats figures and tables as first-class content, not decoration, and maps every major claim in your abstract and intro back to experimental evidence. It's opinionated about paragraph flow (cause, contrast, consequence, refinement) and comes with section-specific guides for introduction, method, experiments, and related work. Use it when you're past the idea stage but your draft still reads like patchwork or when you need to harden claims before sending to reviewers.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 5
skills.sh installs: 1.8K
GitHub stars: 8.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add master-cai/research-paper-writing-skills --skill research-paper-writing --agent claude-code

Installs into .claude/skills of the current project.

Files

Research Paper Writing

Overview

Use this skill to rewrite a research paper into a reviewer-friendly, high-clarity draft. Prioritize first-impression quality (figures/tables/layout), logical flow, and evidence-backed claims.

Core Workflow

Clarify the paper story before sentence-level edits.
Use section-specific guidance in references/.
Rewrite paragraph-by-paragraph with one message per paragraph.
Run reverse outlining after writing each section.
Check every major claim in Abstract/Introduction against experimental evidence.
Run final-paper adversarial review with references/paper-review.md.

Global Principles

Keep one paragraph for one message only.
State the paragraph message in the first sentence.
Make nouns self-contained; define new terms before reusing them.
Maintain sentence-to-sentence flow (cause, contrast, consequence, or refinement).
Iterate with adversarial self-review: read as a skeptical reviewer.
Treat visual quality as core content, not decoration.
Use a clean teaser and pipeline figure.
Use readable, minimal-ink tables.
Keep formatting consistent and tidy.