ml-paper-writing

Write publication-ready ML papers with LaTeX templates and verified citations.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/Its-Atharva-Gupta/forge-researcher --skill ml-paper-writing-its-atharva-gupta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ml-paper-writing
Source: https://github.com/Its-Atharva-Gupta/forge-researcher/tree/main/skills/ml_paper_writing/ml-paper-writing
Command: npx skills add https://github.com/Its-Atharva-Gupta/forge-researcher --skill ml-paper-writing-its-atharva-gupta

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires semanticscholar, arxiv, habanero, requests, and includes references (resource) and assets (resource) components.

What problem does it solve? Drafting ML conference papers is slow and error-prone: researchers struggle with venue-specific formatting, narrative structure, and AI-generated citations that have a ~40% error rate and can cause desk rejection. ## Core Features & Use Cases - Structured Paper Workflows: Step-by-step checklists for drafting abstracts, introductions, methods, experiments, related work, and limitations sections targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. - Citation Verification Pipeline: Programmatic BibTeX retrieval via Semantic Scholar, CrossRef, and arXiv APIs to prevent hallucinated references, with explicit placeholder handling for unverifiable citations. - Official LaTeX Templates & Checklists: Ready-to-compile templates for six ML venues plus conference checklists, reviewer guidelines, and format-conversion workflows for resubmissions. - Use Case: Given a research repository with code and results, produce a complete first draft of an ICML submission with verified citations, then convert it to ICLR format after rejection. ## Quick Start Ask the assistant to read your research repository and draft a complete NeurIPS-style paper with verified citations using this skill.

Frequently Asked Questions about ml-paper-writing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write an ML paper for NeurIPS or ICML from my research code?

Start by exploring the repository to identify the main contribution, then follow the iterative workflow: define a one-sentence contribution, draft Figure 1, write the abstract with the 5-sentence formula, and complete each section with feedback cycles. The skill provides checklists for every step.

How do I prevent AI-hallucinated citations in my paper?

Never write BibTeX from memory. Search Semantic Scholar, verify the paper exists in at least two sources, then retrieve BibTeX programmatically via DOI content negotiation from CrossRef. Unverifiable citations must be marked as explicit placeholders.

What LaTeX templates are included for ML conferences?

Templates are provided for ICML 2026, ICLR 2026, NeurIPS 2025, ACL, AAAI 2026, and COLM 2025, each with official style files and bibliography styles. Copy the entire template directory and verify it compiles before editing.

Can I convert a rejected NeurIPS paper to ICML or ICLR format?

Yes, the skill includes a format conversion workflow: start fresh with the target template, migrate only content sections, adjust for page limit differences, and add venue-specific requirements like ICML's Broader Impact Statement or ICLR's LLM disclosure.

What are the page limits for major ML conferences?

NeurIPS allows 9 pages, ICML 8 pages, ICLR 9 pages, ACL 8 pages for long papers, AAAI 7 pages, and COLM 9 pages. References and appendices are unlimited at all venues, and camera-ready versions typically get one extra page.

When should I use systems-paper-writing instead of this skill?

Use systems-paper-writing for systems venues such as OSDI, NSDI, ASPLOS, and SOSP, which have different structural conventions, templates, and reviewer expectations. This skill covers only ML and AI conferences.