ML Paper Writing
技能 已验证 活跃Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
To empower researchers to write high-quality, publication-ready ML/AI papers efficiently and effectively, by providing expert guidance, reusable templates, and robust workflows for every stage of the process.
功能
- Expert guidance on paper writing philosophy
- LaTeX templates for major AI conferences
- Workflows for drafting and structuring arguments
- API-driven citation verification to prevent hallucinations
- Guidance on conference-specific requirements and submission formats
使用场景
- Starting a new paper draft from a research repository
- Drafting or revising specific sections of an ML paper
- Finding, verifying, and formatting citations for related work
- Converting papers between different conference formats
- Preparing camera-ready submissions and adhering to conference checklists
非目标
- Generating entire papers autonomously without human input
- Replacing the core research or experimental work
- Providing legal advice on intellectual property
- Conducting new research or experiments
工作流
- Understand the research project and its contribution
- Draft sections iteratively, starting with Figure 1, Abstract, and Introduction
- Search for, verify, and format citations programmatically
- Adhere to conference-specific requirements and formatting
- Review and refine the paper based on feedback, addressing limitations and ethical considerations
- Prepare camera-ready version and ensure all checklist items are met
实践
- Academic Writing
- Research Methodology
- Citation Management
- Technical Documentation
先决条件
- Access to Claude Code environment
- Python 3.8+ environment (for API interactions, optional but recommended)
- Optionally, Exa MCP installed for enhanced paper search
安装
npx skills add davila7/claude-code-templates通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
ML Paper Writing
98Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.
Alterlab Hypothesis Gen
95Part of the AlterLab Academic Skills suite. Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.
AlterLab Paper Writer
95Part of the AlterLab Academic Skills suite for faculty and researchers. Academic paper writing skill with 12-agent pipeline. v2.4: LaTeX output formatting hardening — mandatory apa7 class, text justification fix, table column width formula, bilingual abstract centering, standardized font stack, PDF must compile from LaTeX. Supports IMRaD, literature review, theoretical, case study, policy brief, and conference paper structures. APA 7.0 (default), Chicago, MLA, IEEE, Vancouver citation formats. Bilingual abstracts (zh-TW + EN). Multi-format output (LaTeX, DOCX, PDF, Markdown). Triggers on: write paper, academic paper, paper outline, write abstract, revise paper, check citations, convert to LaTeX, guide my paper, parse reviews, revision roadmap, 寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 檢查引用, 引導我寫論文, 帶我規劃論文, 逐章規劃, 論文架構, 審查意見, 修訂路線圖.
Alterlab Scientific Writing
100Part of the AlterLab Academic Skills suite. Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
ARA Research Manager
100Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.