Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and

ML Paper Writing for Top AI Conferences Expert level guidance for writing publication ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM . This skill combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt) with practical tools: LaTeX templates, citation verification APIs, and conference checklists. Default operating order Use this skill in the following order unless the task is unusually narrow: 1. lock the operating mode from references/OPERATING MODES.md , 2. understand the repo or draft context, 3. use references/citation workflow.md as the canonical citation authority , 4. load venue or template specific references only after the main writing path is clear. Google Scholar may still help with manual discovery, but it is not the canonical verification authority in this skill. Default verification should use programmatic sources such as Semantic Scholar, CrossRef, and arXiv. Claim ledger gate Before a project plan, experiment note, or literature summary becomes manuscript prose: identify the Claim Candidate or Evidence Record that supports the sentence, preserve allowed wording and forbidden stronger wording, keep project plans as hypotheses unless experiment artifacts or verified papers support them, do not turn related work motivation into evidence for the paper's own result, mark unsupported claims as [CLAIM NEEDS EVIDENCE] instead of polishing them. If the repo context is clear enough for a first draft, still apply this gate before stating contributions, results, related work contrasts, or rebuttal facing claims. Core Philosophy: Collaborative Writing Paper writing is collaborative, but Claude should be proactive in delivering drafts. The typical workflow starts with a research repository containing code, results, and experimental artifacts. Claude's role is to: 1. Understand the project by exploring the repo, results, and existing documentation 2. Deliver a complete first draft when confident about the contribution 3. Search literature using web search and APIs to find relevant citations 4. Refine through feedback cycles when the scientist provides input 5. Ask for clarification only when genuinely uncertain about key decisions Key Principle : Be proactive. If the repo and results are clear, deliver a full draft. Don't block waiting for feedback on every section—scientists are busy. Produce something concrete they can react to, then iterate based on their response. ⚠️ CRITICAL: Never Hallucinate Citations This is the most important rule in academic writing with AI assistance. The Problem AI generated citations have a ~40% error rate . Hallucinated references—papers that don't exist, wrong authors, incorrect years, fabricated DOIs—are a serious form of academic misconduct that can result in desk rejection or retraction. The Rule NEVER generate BibTeX entries from memory. ALWAYS fetch programmatically. Action ✅ Correct ❌ Wrong Adding a citation Search API → verify → fetch BibTeX Write BibTeX from memory Uncertain about a paper Mark as [CITATION NEEDED] Guess the reference Can't find exact paper Note: "placeholder verify" Invent similar sounding paper When You Can't Verify a Citation If you cannot programmatically verify a citation, you MUST: Always tell the scientist : "I've marked [X] citations as placeholders that need verification. I could not confirm these papers exist." Recommended: Install Exa MCP for Paper Search For the best paper search experience, install Exa MCP which provides real time academic search: Claude Code: Cursor / VS Code (add to MCP settings): Exa MCP enables searches like: "Find papers on RLHF for language models published after 2023" "Search for transformer architecture papers by Vaswani" "Get recent work on sparse autoencoders for interpretability" Then verify results with Semantic Scholar API and fetch BibTeX via DOI. Workflow 0: Starting from a Research Repository When beginning paper writing, start by understanding the project: Step 1: Explore the Repository Look for: README.md Project overview and claims results/ , outputs/ , experiments/ Key findings configs/ Experimental settings Existing .bib files or citation references Any draft documents or notes Step 2: Identify Existing Citations Check for papers already referenced in the codebase: These are high signal starting points for Related Work—the scientist has already deemed them relevant. Step 3: Clarify the Contribution Before writing, explicitly confirm with the scientist: "Based on my understanding of the repo, the main contribution appears to be [X]. The key results show [Y]. Is this the framing you want for the paper, or should we emphasize different aspects?" Never assume the narrative—always verify with the human. Step 4: Search for Additional Literature Use web search to find relevant papers: Then verify and retrieve BibTeX using the citation workflow below. Step 5: Deliver a First Draft Be proactive—deliver a complete draft rather than asking permission for each section. If the repo provides clear results and the contribution is apparent: 1. Check the claim ledger gate for contribution and result claims 2. Write the full first draft end to end only for supported claims 3. Mark unsupported or speculative claims explicitly 4. Present the complete draft for feedback 5. Iterate based on scientist's response If genuinely uncertain about framing or major claims: 1. Draft what you can confidently 2. Flag specific uncertainties: "I framed X as the main contribution—let me know if you'd prefer to emphasize Y instead" 3. Continue with the draft rather than blocking Questions to include with the draft (not before): "I emphasized X as the main contribution—adjust if needed" "I highlighted results A, B, C—let me know if others are more important" "Related work section includes [papers]—add any I missed" When to Use This Skill Use this skill when: Starting from a research repo to write a paper Drafting or revising specific sections Conducting literature reviews and finding related work Discovering recent papers in your research area Finding and verifying citations for related work Formatting for conference submission Resubmitting to a different venue (format conversion) Iterating on drafts with scientist feedback Always remember : First drafts are starting points for discussion, not final outputs. Workflow: Literature Research & Paper Discovery When conducting literature reviews, finding related work, or discovering recent papers, use this workflow to systematically search, evaluate, and select ML papers. Workflow 5: Finding and Evaluating Papers Step 1: Define Search Scope Identify specific research areas, methods, or applications: Technique focused : transformer architecture , graph neural networks , self supervised learning Application focused : medical image analysis , reinforcement learning for robotics , language model alignment Problem focused : out of distribution generalization , continual learning , fairness in ML Step 2: Search arXiv Use arXiv search with targeted keywords: Tips: Combine keywords with + for AND Filter by categories: cs.LG , cs.AI , cs.CV , cs.CL Sort by announced date first for recent papers Use Chrome MCP tools when available for automation Step 3: Screen Papers Quick screening by title and abstract: Relevance to research topic Novelty of contribution Venue/reputation of authors Code availability (check for GitHub links) Step 4: Evaluate Quality Use the 5 dimension quality criteria: Dimension Weight Evaluation Focus Innovation 30% Novelty and originality Method Completeness 25% Clarity and reproducibility Experimental Thoroughness 25% Validation depth Writing Quality 10% Presentation clarity Relevance & Impact 10% Domain importance Scoring : Rate each dimension 1 5, calculate weighted total Step 5: Select and Extract Rank papers by total score Select top papers for detailed review Extract metadata: title, authors, arXiv ID, abstract Note code repository links Step 6: Verify Citations For selected papers, verify citations using Semantic Scholar API: Fetch BibTeX programmatically via DOI Mark unverified citations as [CITATION NEEDED] Store in bibliography with verification status When to Use Literature Research Use this workflow when: Starting a new project : Find related work and baselines Writing Related Work section : Discover recent papers in your area Staying updated : Track recent publications in your field Finding baselines : Identify state of the art methods for comparison Literature review : Comprehensive survey of research area Quality Thresholds Excellent : 4.0+ (include definitely) Good : 3.5 3.9 (include if relevant) Fair : 3.0 3.4 (include if highly relevant) Poor : <3.0 (exclude unless essential) Reference Files For detailed literature research guidance: references/literature research/arxiv search guide.md arXiv search strategies and URL patterns references/literature research/paper quality criteria.md Detailed 5 dimension evaluation rubrics Knowledge Base: Paper Miner Installed Writing Memory This skill consumes the active installed writing memory maintained by paper miner : references/knowledge/paper miner writing memory.md This memory belongs to the active installed skill home, not to the source checkout copy. Even when paper miner is invoked while working inside a specific repository, it still writes mined writing knowledge only into the active installed skill memory. It does not maintain project local writing memory unless the user explicitly requests that. Canonical memory structure The maintained memory contains these sections: Section Purpose Writing patterns mined Reusable rhetorical and claim evidence patterns Structure signals Section flow, paragraph progression, and paper organization signals Reusable phrasing Transition phrases, framing templates, and concise wording Venue specific signals Visible venue facing style and convention cues How this helps our writing Practical guidance for future drafts, reports, and rebuttals Source index Source attribution for mined papers How the memory is maintained The paper miner agent reads papers and merges reusable writing knowledge into this one file: When to use this memory Use the active installed paper miner memory when you need: structure inspiration for intros, methods, results, or discussion, reusable transition phrases or framing templates, venue facing writing signals, rebuttal phrasing and response structure ideas, examples of how strong papers support and sequence claims. Default read order When drafting or revising with ml paper writing , read this memory before writing if the task involves: introduction framing, related work organization, method exposition style, results narration, discussion framing, venue facing polishing. Use this read order: 1. references/knowledge/paper miner writing memory.md 2. repo local evidence and experiment artifacts 3. cited papers or notes if needed 4. venue template and formatting constraints Read narrowly, not exhaustively: first scan How this helps our writing , then check Writing patterns mined and Structure signals , then inspect Reusable phrasing only for concrete wording help, use Venue specific signals when targeting a known venue. Contribution rule Every paper mined by paper miner should improve the same active installed memory. Do not scatter newly mined knowle

ml-paper-writing