Ml Paper Writing

This one's for writing papers to submit to NeurIPS, ICML, ICLR, and similar top-tier ML conferences. It walks you through the full process from research repo to camera-ready submission, including LaTeX templates and citation workflows. The standout feature is the citation verification system that pulls from Semantic Scholar, CrossRef, and arXiv APIs instead of letting you hallucinate references. It's opinionated about workflow, pushing you to deliver complete drafts rather than asking permission for every section, which matches how actual paper writing with collaborators works. Built by Orchestra Research, includes support for Exa MCP if you want better paper search. Use it when you've got experimental results and need to turn them into publication-ready prose without inventing citations.

skills.sh installs: 469
GitHub stars: 6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add galaxy-dawn/claude-scholar --skill ml-paper-writing --agent claude-code

Installs into .claude/skills of the current project.

Files

ML Paper Writing for Top AI Conferences

Expert-level guidance for writing publication-ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. This skill combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt) with practical tools: LaTeX templates, citation verification APIs, and conference checklists.

Default operating order

Use this skill in the following order unless the task is unusually narrow:

lock the operating mode from references/OPERATING-MODES.md,
understand the repo or draft context,
use references/citation-workflow.md as the canonical citation authority,
load venue- or template-specific references only after the main writing path is clear.

Google Scholar may still help with manual discovery, but it is not the canonical verification authority in this skill. Default verification should use programmatic sources such as Semantic Scholar, CrossRef, and arXiv.