About ai-paper-writing
A modular skill bundle for drafting, reviewing, and strengthening AI papers. It guides writers through claims, evidence, experiments, narrative, figures, and limitations, with workflows and templates.
Key features
- 01Extract claims and map supporting evidence
- 02Review novelty and paper positioning
- 03Strengthen experiments, baselines, and ablations
- 04Improve abstracts, introductions, and structure
- 05Guide figures, discussion, and limitations
- 06Use modular workflows and writing templates
Use cases
- 01Turn project results into a paper draft
- 02Audit evidence supporting paper claims
- 03Review a draft for clarity and rigor
- 04Plan stronger baselines and ablations
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/ai-paper-writingin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
ACKNOWLEDGEMENT.mdAGENTS.mdmetadata.jsonmodules/00-overview.md01-compress-to-claims.md02-motivation-impact.md03-novelty-positioning.md04-readteaming.md05-experiments-design.md06-avoid-misleading.md07-structure-abstract.md08-structure-introduction.md09-figures.md10-main-body.md11-related-work.md12-discussion-limitations.md13-writing-process.md14-common-pitfalls.md15-checklists.mdtemplates/abstract-template.mdevidence-audit-template.mdfigure-caption-template.mdintro-template.mdpaper-outline-template.mdDetails
From the project READMEAI Paper Writing
A modular skill bundle distilled from “Highly Opinionated Advice on How to Write AI Papers” (Neel Nanda).
The goal is to help you produce papers where readers understand, remember, and believe the narrative.
North star
An ideal paper is a short, rigorous, evidence-based technical story with a takeaway the reader cares about:
- What? 1–3 concrete claims that contribute to knowledge
- Why? rigorous evidence that supports the claims
- So what? motivation + impact: why the reader should care
How to use
Pick a workflow below, or jump straight to a module. Each module is independent.
Common inputs
- Your paper text (or section)
- Or: a project summary + key results + experiments list
Common outputs
- claim list (1–3 claims + scope + confidence level)
- evidence map (claim → experiments → risks)
- rewritten abstract/intro
- experiment fixes (baselines, ablations, stronger discriminators)
- figure + caption guidance
- limitations + discussion guidance
Workflows
A) Drafting from scratch (recommended order)
- Compress to claims
- Motivation & impact
- Novelty & positioning
- Evidence & red-teaming
- Paper structure overview
- Abstract
- Introduction
- Figures
- Main body layering
- Discussion & limitations
- Related work
B) Reviewing a draft
- Compress to claims (extract what the paper actually claims)
- Evidence & red-teaming
- Avoid misleading evidence
- Abstract
- Introduction
- Common pitfalls
C) Strengthening experiments
D) Tightening narrative + clarity
Templates
- Abstract template
- Intro template
- Paper outline template
- Evidence audit template
- Figure caption template
Modules index
- 00 Overview
- 01 Compress to claims
- 02 Motivation & impact
- 03 Novelty & positioning
- 04 Evidence & red-teaming
- 05 Experiments design
- 06 Avoid misleading evidence
- 07 Structure: Abstract
- 08 Structure: Introduction
- 09 Figures
- 10 Main body
- 11 Related work
- 12 Discussion & limitations
- 13 Writing process
- 14 Common pitfalls
- 15 Checklists
Acknowledgements
This was compiled from Neel Nanda's article (Highly Opinionated Advice on How to Write AI Papers)[https://www.alignmentforum.org/s/5GT3yoYM9gRmMEKqL/p/eJGptPbbFPZGLpjsp]