What problem does it solve? Writing a publishable ML paper involves coordinating experiments, citations, statistical analysis, LaTeX drafting, and submission formatting — a process where hallucinated citations, missing baselines, and weak statistical rigor commonly cause rejections. This Skill provides a structured, iterative pipeline covering the full research lifecycle for NeurIPS, ICML, ICLR, ACL, AAAI, and COLM submissions. ## Core Features & Use Cases - Full Research Pipeline: Eight phases from project setup and literature review through experiment design, execution monitoring, statistical analysis, drafting, self-review, and submission preparation. - Citation Verification Workflow: Enforces programmatic BibTeX retrieval via DOI content negotiation and Semantic Scholar, marking unverifiable references as [CITATION NEEDED] instead of hallucinating them. - Experiment Rigor: Provides claim-to-experiment mapping, baseline design, statistical significance testing (McNemar's test, bootstrapped CIs, Cohen's h), cost tracking, and experiment journals. - Use Case: A researcher with a working codebase asks the agent to turn their results into an ICML submission — the Skill guides literature search, designs ablations, monitors long-running experiments via cron, generates booktabs tables and vector figures, and produces a complete LaTeX draft. ## Quick Start Ask the agent to help write a research paper from your existing experiment codebase, specifying your target venue such as NeurIPS or ICML.
