research-paper-writing

Coordinates ML research lifecycle from experiment design to publication-ready drafting with BibTeX citations.

Updated Jun 17, 2026

Search Tags:#research #academic #machine learning #citations #latex #experiments #paper writing

Ready to run

npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill research-paper-writing-cxnaive

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-paper-writing
Source: https://github.com/cxnaive/hermes-agent-llbot/tree/main/skills/research/research-paper-writing
Command: npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill research-paper-writing-cxnaive

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the complex, iterative lifecycle of machine learning research, from initial project setup and literature review to experiment execution and final paper drafting.

Core Features & Use Cases

Iterative Research Loop: Manages the feedback cycle between experiment results, analysis, and paper revisions.
Verified Citation Management: Prevents hallucinations by programmatically fetching BibTeX from academic databases.
Use Case: Use this Skill to manage a NeurIPS submission by automating the literature search, tracking experiment compute budgets, and drafting sections grounded in your actual experimental data.

Quick Start

Use the research-paper-writing skill to initialize a new project workspace and perform a literature review for the current research topic.

Frequently Asked Questions about research-paper-writing

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

FAQPage Schema

How do I automate fetching BibTeX citations for machine learning papers to prevent hallucinations?▼

To prevent citation hallucinations in machine learning papers, programmatically fetch verified BibTeX entries by integrating directly with academic databases like Semantic Scholar and arXiv. This ensures citation accuracy throughout the drafting process.

What is the best way to manage the iterative research loop between experiments and paper revisions?▼

Managing the iterative research loop involves coordinating feedback cycles between empirical experiment results, data analysis, and manuscript revisions. This ensures your publication-ready drafts remain grounded in actual experimental data.

How do I draft a publication-ready machine learning paper grounded in actual experimental data?▼

Drafting a publication-ready machine learning paper requires an end-to-end pipeline that executes experiments and feeds empirical results directly into manuscript revisions. This grounds your text in verified data for major AI conferences.

Does this research pipeline support integration with arXiv and Semantic Scholar for literature reviews?▼

Yes, the research pipeline supports programmatic integration with academic databases including arXiv and Semantic Scholar. This enables automated literature searches and verified citation tracking during your initial project setup.

Can I use SciencePlots and matplotlib for generating publication-ready figures in LaTeX?▼

Yes, you can use matplotlib and SciencePlots to generate publication-ready figures for your LaTeX manuscript. These dependencies support formatting empirical experiment results for major AI conference submissions.

How do I ensure reproducibility when executing machine learning experiments for a NeurIPS submission?▼

To ensure reproducibility for a NeurIPS submission, the research pipeline requires programmatic integration with academic databases and version control systems. This tracks experiment compute budgets and grounds your drafting process.