What problem does it solve? Drafting and revising academic papers for ML/CV/NLP venues often suffers from unclear paragraph flow, unsupported claims, weak section structure, and reviewer-facing presentation issues that lead to rejection. This Skill provides section-by-section writing guidance, templates, and an adversarial review workflow to produce reviewer-friendly drafts. ## Core Features & Use Cases - Section-Specific Guides: Dedicated references for Abstract, Introduction, Related Work, Method, Experiments, and Conclusion, each with templates, sentence skeletons, and quality checklists. - Paragraph Clarity and Flow Checks: Reverse outlining, one-message-per-paragraph rules, and transition guidance to diagnose whether writing flows. - Claim-Evidence Alignment and Adversarial Review: A five-dimension self-review checklist (contribution, writing clarity, experimental strength, evaluation completeness, method design soundness) to catch rejection risks before submission. - Use Case: When revising an Introduction, load the introduction guide, pick a task/challenge/pipeline template, rewrite paragraph-by-paragraph, then map every major claim to experimental evidence before finalizing. ## Quick Start Use the research-paper-writing skill to rewrite my paper's Introduction section with a clear technical challenge and claim-evidence alignment.
