research-paper-writing

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

Updated Jun 30, 2026
One-click install
npx skills add https://github.com/zhoulingxiao1216/testworkspace --skill research-paper-writing-zhoulingxiao1216
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research-paper-writing
Source: https://github.com/zhoulingxiao1216/testworkspace/tree/main/all_Skills/research/research-paper-writing
Command: npx skills add https://github.com/zhoulingxiao1216/testworkspace --skill research-paper-writing-zhoulingxiao1216

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Writing a publication-ready ML/AI paper involves coordinating experiments, verified citations, statistical analysis, LaTeX formatting, and venue-specific checklists, and mistakes in any step cause desk rejections or hallucinated references. ## Core Features & Use Cases - Full Research Lifecycle: Covers project setup, literature review, experiment design, execution monitoring, statistical 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 instead of generating citations from memory, with a mandatory 5-step verification process. - Venue Templates & Checklists: Ships official LaTeX templates and mandatory checklist requirements (NeurIPS 16-item checklist, ACL Limitations section, ICLR LLM disclosure) to prevent desk rejection. - Use Case: A researcher with experimental results asks the agent to draft an ICML submission; the skill maps claims to experiments, verifies every citation, generates booktabs tables and colorblind-safe PDF figures, and runs a simulated reviewer pass before submission. ## Quick Start Help me write a NeurIPS paper from the experiment results in my results/ directory, starting with a one-sentence contribution statement.

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 research paper for NeurIPS or ICML?▼

Follow a phased pipeline: define a one-sentence contribution, map every experiment to a paper claim, run baselines with statistical tests, then draft using the venue's official LaTeX template. Finish with a simulated self-review and the venue's mandatory checklist before submission.

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

Never generate BibTeX from memory; fetch it programmatically via DOI content negotiation through CrossRef. Verify each paper exists in at least two sources such as Semantic Scholar and arXiv, and mark anything unverifiable as a placeholder citation.

What LaTeX templates are included for conference submissions?▼

The templates directory includes official style files for ICML 2026, ICLR 2026, NeurIPS 2025, ACL, AAAI 2026, and COLM 2025, each with its .sty and .bst files plus example documents. Compile with pdflatex and bibtex or use latexmk.

Does the NeurIPS paper checklist affect submission acceptance?▼

Yes, NeurIPS submissions missing the 16-item paper checklist face automatic desk rejection. The checklist covers claims alignment, limitations, reproducibility, statistical significance, compute resources, ethics, and LLM usage disclosure, and appears outside the page limit.

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

Iterative refinement like autoreason helps most with mid-tier models on constrained tasks where the generation-evaluation gap is large. Frontier models on unconstrained tasks do better with single-pass or critique-and-revise, since unconstrained iteration causes synthesis drift.

What statistical tests should ML papers report for method comparisons?▼

Report McNemar's test for paired binary outcomes, bootstrapped 95% confidence intervals for key metrics, and effect sizes such as Cohen's h. Always state sample sizes, number of runs, and whether error bars show standard deviation or standard error.