skills.rest
patty-chow
patty-chowCOMMUNITY
Explore all skills by this author →
GitHub

research-paper-writing

Guides end-to-end ML research paper production from experiment design through conference submission.

Updated May 28, 2026
Search Tags:#machine learning#citations#latex#research paper#experiments#neurips#conference submission
One-click install
npx skills add https://github.com/patty-chow/the-stable --skill research-paper-writing-patty-chow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research-paper-writing
Source: https://github.com/patty-chow/the-stable/tree/main/skills/research/research-paper-writing
Command: npx skills add https://github.com/patty-chow/the-stable --skill research-paper-writing-patty-chow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires semanticscholar, arxiv, habanero, requests, scipy, numpy, matplotlib, SciencePlots, and includes references (resource) components.

What problem does it solve? Writing a publishable ML paper involves coordinating literature review, experiment design, statistical analysis, LaTeX drafting, citation verification, and venue-specific formatting—an iterative process where hallucinated citations, missing baselines, and checklist omissions cause desk rejections. ## Core Features & Use Cases - Full Research Lifecycle: Covers eight phases from project setup and literature review through experiment execution, analysis, drafting, self-review, and submission for NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. - Verified Citation Workflow: Fetches BibTeX programmatically via Semantic Scholar, CrossRef, and arXiv APIs with a mandatory 5-step verification process to prevent hallucinated references. - Venue Templates & Checklists: Ships official LaTeX templates for six conferences plus pre-submission checklists covering page limits, reproducibility statements, and ethics requirements. - Use Case: A researcher with experimental results asks the agent to draft an ICML submission—the skill maps claims to experiments, verifies every citation, applies the icml2026 template, and runs a simulated reviewer pass before submission. ## Quick Start Use the research-paper-writing skill to draft an ICML submission from the experiment results in my current repository.

Frequently Asked Questions about research-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 with an AI agent?▼

Follow the eight-phase pipeline: set up the workspace, run an iterative literature search, map claims to experiments, execute with monitoring, analyze with statistical tests, draft in the venue's LaTeX template, self-review as a simulated reviewer, then complete the submission checklist.

How do I prevent hallucinated citations in AI-generated papers?▼

Never generate BibTeX from memory. Use the mandatory 5-step workflow: search Semantic Scholar, verify the paper in two sources, retrieve BibTeX via DOI content negotiation, validate the cited claim appears in the paper, then add it to the bibliography.

What LaTeX templates are included for conference submissions?▼

The templates directory includes official styles for ICML 2026, ICLR 2026, NeurIPS 2025, ACL, AAAI 2026, and COLM 2025, each with the .sty file, bibliography style, and example document, plus compilation instructions for VS Code, command line, and Overleaf.

Does the skill support human evaluation study design?▼

Yes, it covers annotator selection, Likert versus pairwise comparison scales, inter-annotator agreement metrics like Krippendorff's alpha, crowdsourcing quality control, compensation requirements, and IRB guidance for NLP and HCI papers.

When should I use autoreason iterative refinement versus a single pass?▼

Use autoreason for mid-tier models on constrained tasks where the generation-evaluation gap is large. Use single pass for frontier models on unconstrained tasks or template-filling work, since iteration adds no value and can degrade output quality.

What causes desk rejection at major ML conferences?▼

Common causes include missing the NeurIPS paper checklist, exceeding page limits, modified templates (especially at AAAI), broken anonymization, absent limitations sections at ACL, and undisclosed LLM use at ICLR. The checklists reference covers all venue-specific requirements.

Related Skills

Explore More Education & Research Skills→
infinitioninfinition
33

arxiv

Search arXiv papers, fetch citation counts from Semantic Scholar, and generate BibTeX entries.

Community
Intermediate
LeonChaoXLeonChaoX
783

venue-templates

Generate venue-specific LaTeX templates and validate formatting compliance.

Community
Intermediate
GYF0311GYF0311
5

minion-orchestrator

Orchestrate durable background shell jobs and LLM subagent runs with lifecycle controls.

Community
Advanced
typemdtypemd
9

create-blog

Generate Traditional Chinese TypeMD blog drafts and stage markdown files.

Official
Intermediate