What problem does it solve?
Producing a publication-ready ML research paper involves coordinating experiments, verifying citations, analyzing results, writing narrative, and meeting strict venue formatting requirements—all while maintaining scientific rigor. This skill eliminates the overhead of remembering venue-specific checklists and prevents common pitfalls like hallucinated citations or missing reproducibility statements.
Core Features & Use Cases
- 7-Phase Pipeline: Structured workflow covering project setup, literature review, experiment design, execution, analysis, paper drafting, self-review, and submission for NeurIPS, ICML, ICLR, ACL, AAAI, and COLM.
- Citation Hallucination Prevention: Enforces programmatic citation verification via Semantic Scholar, CrossRef, and arXiv APIs to eliminate AI-generated citation errors.
- Experiment Infrastructure: Provides battle-tested patterns for incremental saving, crash recovery, statistical significance testing, and monitoring long-running batches.
- Venue Compliance: Includes official LaTeX templates and mandatory checklist requirements for major ML/AI conferences to avoid desk rejection.
Quick Start
Use the research-paper-writing skill to produce a complete first draft of your ML paper by pointing it to your experimental results folder and specifying your target conference venue.
