Research Paper Writing
A skill for writing and revising ML, CV and NLP papers: section structure, paragraph flow and reviewer-style self-review
Install
mkdir -p "$HOME/.claude/skills"
cp -R research-paper-writing "$HOME/.claude/skills/"Run from the cloned repository root. Use .claude/skills for a project install.
This is third-party code. Review the repository files before installing.
What it does
The skill helps rewrite a research paper so a reviewer can follow it easily. It first pins down the paper's story, then works section by section with dedicated guides for abstract, introduction, related work, method, experiments and conclusion. Each paragraph must carry one message stated up front, and flow is checked with reverse outlining. It matches claims in the abstract and introduction against experimental evidence and ends with an adversarial review of the whole paper. It also advises on teaser figures, pipeline diagrams and tables.
Who it is for. For graduate students and researchers writing machine learning papers in English.
Good fit when
- You need to rewrite the introduction or abstract before submission
- You need to check that claimed contributions are backed by experiments
- You want a reviewer-style self-review of the paper
Not a fit when
- You write in a humanities field or not in English
- You need literature search or fact-checking
Example request
Use the research-paper-writing skill to improve my paper's introduction and check paragraph flowLimitations
The method is based on Prof. Peng Sida's open notes and targets English ML, CV and NLP papers. It works on text and does not verify data or experiment code.
How to disable. Remove the research-paper-writing folder from ~/.claude/skills, $CODEX_HOME/skills or ~/.gemini/skills.
Security check
- The skill consists only of instructions and references
README in short
The README credits the source material and describes the package: SKILL.md with the core workflow, section-specific guides and agent metadata. It lists use cases: drafting and revising sections, flow, claim-evidence alignment and pre-submission review. Copy commands are given for Codex, Claude Code and Gemini. MIT licensed.
SKILL.md
--- name: research-paper-writing description: Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures/tables; checking claim-support alignment; or performing self-review before submission. --- # 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 1. Clarify the paper story before sentence-level edits. 2. Use section-specific guidance in `references/`. 3. Rewrite paragraph-by-paragraph with one message per paragraph. 4. Run reverse outlining after writing each section. 5. Check every major claim in Abstract/Introduction against experimental evidence. 6. Run final-paper adversarial review with `references/paper-review.md`. ## Global Principles 1. Keep one paragraph for one message only. 2. State the paragraph message in the first sentence. 3. Make nouns self-contained; define new terms before reusing them. 4. Maintain sentence-to-sentence flow (cause, contrast, consequence, or refinement). 5. Iterate with adversarial self-review: read as a skeptical reviewer. 6. Treat visual quality as core content, not decoration. 7. Use a clean teaser and pipeline figure. 8. Use readable, minimal-ink tables. 9. Keep formatting consistent and tidy.
FAQ
Whose method is this?
It comes from Prof. Peng Sida's open study notes; the repository author organized them and packaged them as a skill.
Do I need to call the skill explicitly?
In Claude Code the author suggests asking for research-paper-writing by name; in Codex use $research-paper-writing.
Related
Microsoft's utility and MCP server that turn PDF, Word, Excel, PowerPoint, HTML and other files into Markdown for models
Anthropic skills
Skills
Anthropic's official skill examples: docx, pdf, pptx and xlsx documents, design, MCP builder and the Agent Skills spec
A skill that builds editable PPTX decks from PDF, DOCX, URLs and Markdown with native shapes, charts and animations
Anthropic's legal plugin suite: contracts, privacy, employment, IP, litigation, AI governance and legal education