
Ml Paper Writing
Drafts publication-ready papers for NeurIPS, ICML, ICLR, ACL, AAAI, and COLM by exploring your research repo, understanding results, and delivering complete first drafts rather than asking for permission at every step. The workflow is proactive: Claude reads your codebase and experiments, searches for relevant citations using APIs like Semantic Scholar, then generates full LaTeX drafts you can iterate on. The standout feature is citation verification, never writing BibTeX from memory to avoid the ~40% hallucination rate that plagues AI-generated references. Built by Orchestra Research following writing philosophy from Karpathy, Lipton, and other top researchers. For systems venues like OSDI or SOSP, there's a separate systems-paper-writing skill instead.
- skills.sh installs
- 922
- GitHub stars
- 10.7K
- last updated
- Jul 14, 2026
Install
$ npx -y skills add zechenzhangagi/ai-research-skills --skill ml-paper-writing --agent claude-codeInstalls 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, 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.
For systems venues (OSDI, NSDI, ASPLOS, SOSP), use the systems-paper-writing skill, which provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, and LaTeX templates for systems conferences.
Core Philosophy: Collaborative Writing
Paper writing is collaborative, but Claude should be proactive in delivering drafts.
The typical workflow starts with a research repository containing code, results, and experimental artifacts. Claude's role is to:
Sponsors
Details
- Repository
- github.com/zechenzhangagi/ai-research-skills
- Categories
- Documentation, AI & Agent Building, Data Science & ML
- First seen
- Apr 16, 2026