What problem does it solve? Turning raw research results into a submission-ready academic paper requires coordinating outlining, figure generation, LaTeX writing, compilation, and iterative review — a fragmented, error-prone process. This Skill chains those steps into one automated pipeline with adversarial review gates. ## Core Features & Use Cases - End-to-End Pipeline: Chains paper-plan, paper-figure, paper-write, paper-compile, and an auto-improvement loop into a single workflow producing a polished paper/ directory with LaTeX source and PDF. - Adversarial Quality Gates: Negotiates a testable acceptance contract before writing, then runs proof-checking, claim audits against raw result files, citation audits, and a kill-argument review before declaring the paper submission-ready. - Venue & Style Targeting: Supports ICLR, NeurIPS, ICML, CVPR, ACL, AAAI, ACM, and IEEE venues, plus an optional style-reference mode that matches a reference paper's structural style without copying content. - Use Case: A researcher with a NARRATIVE_REPORT.md containing claims and experiment results invokes the pipeline to get a compiled, twice-reviewed PDF with verified numbers and citations for an ICLR submission. ## Quick Start Run the paper writing pipeline on my NARRATIVE_REPORT.md targeting NeurIPS and generate the full submission-ready PDF.