awesome-ai-research-writing
Elevate your AI research writing, no more tedious polishing ✨
awesome-ai-research-writing is a curated collection of production-ready prompts and MCP-compatible agent skills designed to streamline academic paper writing workflows. Developed through surveys of researchers at top institutions (MSRA, Seed, Shanghai AI Lab, Peking University, USTC, SJTU), it offers battle-tested prompt templates for translation, polishing, logic checking, and experiment analysis, plus agent skills for automated paper generation in LaTeX and Word formats. The toolkit integrates with Claude Code and Cursor via the OpenSkills framework, enabling researchers to focus on science rather than prompt engineering.
Key Features
Use Cases
- 01Translate Chinese research notes to publication-ready English LaTeX with proper character escaping and formula preservation
- 02Generate complete ICLR/NeurIPS paper drafts from GitHub repository structure and experimental logs
- 03Convert scattered experimental results into booktabs-formatted tables with best-value bolding and metric arrows
- 04Migrate accepted paper from NeurIPS to ICML format while enforcing page limits and Broader Impact sections
- 05Audit pre-submission drafts against conference checklists for anonymity, citation completeness, and ethics statements
- 06Remove AI writing artifacts (leverage/delve/tapestry) and mechanical transitions from generated text
Related Agents
View moreunsloth
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
codegraph
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
system_prompts_leaks
Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.
awesome-ai-research-writing — FAQ
What is awesome-ai-research-writing?+
It is an open-source toolkit combining reusable prompt templates for academic writing tasks and MCP-compatible agent skills for automated LaTeX/Word paper generation, optimized for AI/ML conference submissions.
How do I install the agent skills in Cursor or Claude Code?+
Install Node.js 20.6+, then run 'npx openskills install zechenzhangAGI/AI-research-SKILLs' to auto-place skills in .claude/skills/. Cursor discovers them automatically on startup.
Which AI clients work with these prompts and skills?+
Prompts work with any chat interface (Claude, ChatGPT, Gemini). Agent skills require Cursor or Claude Code with OpenSkills support.
Do I need API keys or external services?+
Prompts require only access to an LLM (Claude 3.5 Sonnet or GPT-4 recommended). Skills may invoke citation APIs but flag unverified references as placeholders.
Is this free to use?+
Yes, the repository and skills are open-source. You pay only for underlying LLM API usage (e.g., Claude/OpenAI credits).
Can I use this for Chinese-language papers or Word submissions?+
Yes. Dedicated prompts handle Chinese-to-Chinese polishing and Word-specific formatting; the docx skill edits .docx templates directly with tracked changes.
How do I install awesome-ai-research-writing?+
Open the source repository on GitHub and follow its README. awesome-ai-research-writing is a agent — MCP Agents Market links you directly to the official repo.
Is awesome-ai-research-writing free?+
awesome-ai-research-writing is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.