What problem does it solve?
Research teams and individual scientists often struggle to turn code, results, and experimental artifacts into a coherent, submission-ready ML/AI paper for top venues. This Skill reduces the burden of structuring arguments, producing drafts, verifying citations, and formatting for conference templates so teams can focus on science rather than submission mechanics.
Core Features & Use Cases
- Repository-to-Draft Workflow: Explore a research repo, identify main contributions, and produce a full first draft (abstract, introduction, methods, experiments, related work, limitations).
- Citation Verification: Search literature via Semantic Scholar/arXiv/CrossRef, fetch BibTeX programmatically, and mark unverifiable references explicitly as placeholders.
- LaTeX Templates & Format Conversion: Provide and verify official LaTeX templates (NeurIPS, ICML, ICLR, ACL, AAAI, COLM) and convert papers between venue formats while preserving checklists and required sections.
- Reviewer & Checklist Guidance: Include venue-specific checklists, reviewer-expectation heuristics, figure and writing best practices, and reproducibility requirements.
- Use Case Example: Starting from an experiments repo, produce a NeurIPS-style draft, verify every citation via APIs, generate a .bib, and prepare a camera-ready PDF with the correct template.
Quick Start
Draft a complete NeurIPS-style first draft from this repository, verify all citations programmatically, and prepare a LaTeX submission using the neurips2025 template.