Claude Skill
tsingyuai/scientify
Scientify is an AI-powered research workflow automation tool for OpenClaw, built with TypeScript. Automate repetitive tasks, boost productivity, and streamline your research process.
Overview
Repository
Install this Skill
pnpm add -g openclaw # 或: npm install -g openclawRegistry
pnpm add -g openclaw # 或: npm install -g openclawgit clone https://github.com/tsingyuai/scientify.gitgit clone https://github.com/user/scientify.git
Summary
Scientify is an AI-powered research workflow automation tool designed for OpenClaw, built with TypeScript. It streamlines research processes by leveraging artificial intelligence to automate repetitive tasks, enabling researchers to focus on high-value analysis and discovery.
基于AI的OpenClaw研究工作流自动化。
Key features
- AI-driven automation for research workflows
- Built with TypeScript for reliability and scalability
- Designed specifically for OpenClaw platform integration
- Streamlines repetitive research tasks
- Enhances researcher productivity
Use cases
- Automating literature review and data extraction
- Accelerating experiment documentation and analysis
- Integrating with OpenClaw for seamless research management
- Reducing manual effort in research data processing
- Supporting collaborative research workflows
README excerpt
<h1 align="center">Scientify</h1> <p align="center"> <em>持续新陈代谢的 AI 科研系统</em> </p> <p align="center"> <a href="https://www.npmjs.com/package/scientify"><img src="https://img.shields.io/npm/v/scientify?style=for-the-badge&logo=npm&logoColor=white" alt="npm version"></a> <a href="https://github.com/tsingyuai/scientify"><img src="https://img.shields.io/github/stars/tsingyuai/scientify?style=for-the-badge&logo=github" alt="GitHub stars"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge" alt="MIT License"></a> <a href="https://github.com/openclaw/openclaw"><img src="https://img.shields.io/badge/OpenClaw-plugin-00FF9F?style=for-the-badge" alt="OpenClaw plugin"></a> </p> <p align="center"> <a href="https://scientify.tech">官网</a> · <a href="./README.en.md">English</a> · <a href="https://github.com/tsingyuai/scientify/issues">Issues</a> </p> --- ## 它能做什么 > [!IMPORTANT] > Scientify 不是一个"问一次答一次"的 AI 工具。它像一个真正的研究伙伴——**持续思考、持续积累、持续交付**。 ### 1. 新陈代谢:持续思考,而非一次性回答 现有 AI 科研工具的工作方式是**批处理**——给个问题,跑一遍 pipeline,输出报告,结束。下次再问同一个方向,从零开始。跑 10 次和跑 1 次没有本质区别。 但人类研究者不是这样工作的。你每天在读、在跑、在想。昨天的失败改变了今天的阅读,上周的对话改变了这周的实验设计。 Scientify 采用**新陈代谢模式**——持续地摄入、消化、沉淀、再摄入: - **持续摄入**:每天自动跟进前沿论文,不需要你手动触发 - **消化沉淀**:将新知识与已有积累关联,写入持久化知识库 - **假设进化**:淘汰无效假设,进化有效路径,每一轮失败都是下一轮的养料 - **主动交付**:发现值得关注的进展后自动验证,验证通过主动推送给你 用得越久,它研究越深入。 <p align="center"> <img src="docs/assets/showcase/3.png" width="50%" alt="Scientify 通过飞书主动推送研究进展"> <br> <sub>Scientify 通过飞书主动向研究者推送最新发现,并结合知识库产生思考</sub> </p> #### 它有多大优势?我们做了一项受控研究 新陈代谢模式不只是一个工程选择——它带来的是质的不同。我们在 **50 个研究主题、892 条生成假设** 上对照测试了新陈代谢与传统批处理范式,论文:[arXiv:2604.12243](https://arxiv.org/abs/2604.12243)。 <p align="center"> <img src="docs/assets/showcase/metabolism-vs-batch.zh.svg" width="100%" alt="新陈代谢 v
Topics
No topics yet.