research-paper-writing

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

6|Updated Jul 12, 2026
One-click install
npx skills add https://github.com/josoroma/AppLoop --skill research-paper-writing-josoroma
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research-paper-writing
Source: https://github.com/josoroma/AppLoop/tree/main/.hermes/skills/research/research-paper-writing
Command: npx skills add https://github.com/josoroma/AppLoop --skill research-paper-writing-josoroma

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 like hallucinated citations or missing NeurIPS checklist items cause desk rejections. ## Core Features & Use Cases - Full Research Lifecycle Pipeline: 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 for six conferences plus pre-submission checklists covering page limits, limitations sections, and LLM disclosure rules. - Use Case: A researcher with experimental results asks the agent to draft an ICML submission; the skill maps claims to experiments, builds the experiment log, writes the LaTeX draft using the icml2026 template, and runs a simulated reviewer pass before submission. ## Quick Start Ask the agent to help write a research paper from your existing codebase and results, specifying your target venue such as NeurIPS or ICML.

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 a machine learning paper for NeurIPS or ICML?▼

Follow the phased pipeline: define a one-sentence contribution, map each claim to a supporting experiment, run experiments with incremental result saving, then draft using the official venue LaTeX template. Finish with a self-review pass simulating reviewers and complete the venue's mandatory checklist before submitting.

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

Never generate BibTeX from memory; fetch it programmatically via DOI content negotiation from CrossRef. Verify each paper exists in at least two sources such as Semantic Scholar and arXiv, and mark anything unverifiable as [CITATION NEEDED] for manual review.

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. Page limits range from 7 pages (AAAI) to 9 pages (ICLR, NeurIPS, COLM).

Does the skill support human evaluation studies for NLP papers?▼

Yes, it covers annotator selection, pairwise versus Likert scale design, inter-annotator agreement metrics like Krippendorff's alpha and Cohen's kappa, crowdsourcing platform choices, and IRB guidance. It also lists the reporting details reviewers at ACL and EMNLP expect.

What statistical tests should I report for experiment comparisons?▼

Use McNemar's test for paired binary outcomes between two methods, bootstrapped 95% confidence intervals for key metrics, and Cohen's h for effect size on proportions. Always report sample sizes, number of runs, and whether error bars show standard deviation or standard error.

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

Autoreason works best with mid-tier models on constrained tasks where the generation-evaluation gap is large. For frontier models on unconstrained tasks, use critique-and-revise or a single pass, since autoreason suffers synthesis drift without scope constraints.