What problem does it solve? Writing a machine learning paper for venues like NeurIPS, ICML, or ICLR involves coordinating experiments, citations, statistics, LaTeX formatting, and venue-specific checklists. This Skill provides a structured pipeline that prevents common failure modes such as hallucinated citations, missing ablations, and desk rejections from formatting or checklist violations. ## Core Features & Use Cases - Full Research Lifecycle: Covers project setup, literature review, experiment design, execution monitoring, statistical analysis, drafting, self-review, and submission as an iterative loop. - 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 ICML, ICLR, NeurIPS, ACL, AAAI, and COLM plus pre-submission checklists covering page limits, reproducibility statements, and ethics requirements. - Use Case: A researcher with experimental results in a codebase asks the agent to draft an ICML submission. The Skill maps claims to experiments, verifies every citation, generates publication-quality figures, applies the ICML 2026 template, and runs a simulated reviewer pass before submission. ## Quick Start Ask the agent to help write a research paper from your existing experiment results, specifying the target venue such as NeurIPS or ICML.
