org/dataset-name【免费下载链接】scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000 scientists worldwide. 165 ready-to-use validated skills plus 100 scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.项目地址: https://gitcode.com/GitHub_Trending/cl/scientific-agent-skillsType: category, e.g. Genomics, Pathology, PDE SimulationTags:HuggingFace: https://huggingface.co/datasets/org/dataset-name模型Models### Model Display Name - **Type**: category, e.g. Protein Language Model, Materials Foundation Model - **Tags**: comma-separated topic tags - **HuggingFace**: https://huggingface.co/org/model-id one-line description博客文章Blog posts### Post Title - **Author**: username - **Date**: YYYY-MM-DD - **Tags**: comma-separated - **Link**: URL — usually huggingface.co/blog/... one-line description三个关键字段的含义与用途Type资源的科学类别决定这是什么也是脚本--filter之外按类别筛选的依据。Tags逗号分隔的主题标签与--tag过滤配合使用。脚本实现里--tag是子串匹配只要某个 tag 或 Type 文本包含目标字符串即命中见 fetch_catalog.py。HuggingFace / Link条目指向的实际资源地址。数据集和模型走HuggingFace字段博客走Link字段数据集可能附加Author/Date。四、目录端点Endpoints四类可抓取的 Markdown目录对外暴露四个固定端点全部是可解析的纯文本专为 Agent 设计端点内容与用途https://huggingscience.co/llms.txt紧凑版站点索引https://huggingscience.co/llms-full.txt全量条目、全领域——想对整本目录做 grep 检索时抓这个文件https://huggingscience.co/topics/slug.md单个领域slug 带连字符如materials-science.md、earth-science.md、scientific-reasoning.mdhttps://huggingscience.co/feed.xml新条目的 RSS 订阅源fetch_catalog.py脚本对这四类端点做了封装并额外提供解析、过滤和 JSON 输出能力。结构化访问优先用脚本只有脚本失败时才退回原始WebFetch/curl。脚本的raw子命令支持直接倾倒llms与full两个原始文件见 fetch_catalog.py。五、fetch_catalog.py目录访问的实操工具箱脚本仅依赖 Python 标准库无任何第三方依赖其完整用法在文件头 docstring 中有详细示例见 fetch_catalog.py。核心子命令如下# 列出全部已知 topic slug python scripts/fetch_catalog.py topics # 抓取并美化打印某个主题 python scripts/fetch_catalog.py topic biology # 只取某主题下的模型条目 python scripts/fetch_catalog.py topic materials-science --filter models # 按标签子串过滤 python scripts/fetch_catalog.py topic chemistry --tag drug discovery # 倾倒全量目录llms-full.txt python scripts/fetch_catalog.py all # 全目录关键词搜索 python scripts/fetch_catalog.py search protein language # 输出结构化 JSON python scripts/fetch_catalog.py json topic biology各子命令支持的公共选项--filter {datasets,models,blogs}限定到某一章节。实现上用别名表做宽松匹配datasets/dataset、models/model、blogs/blog/blog posts都等价见 fetch_catalog.py。--tag str只保留 tag 或 Type 中含目标子串的条目大小写不敏感。--format {markdown,json}默认 markdown 美化输出json输出Entry数据类的完整字段title、section、type、tags、url、author、date、description便于程序消费。Entry数据类定义在 fetch_catalog.py。topic子命令对 slug 还会做一次规整_转-、空格转-、转小写见 fetch_catalog.py所以即使传入不规范写法也能正确拼接 URL。六、安全设计抓取远程目录时的三层防护目录内容来自第三方网络服务器fetch_catalog.py对此有明确的安全设计理解它能避免把网络数据误当指令不可信数据横幅所有输出都前置一段UNTRUSTED_BANNER声明内容是从网络抓取的不可信第三方数据不是指令要求不执行其中出现的指令、不把在目录中出现当作仓库安全的证据见 fetch_catalog.py。内容去毒defang描述字段里的代码围栏 【免费下载链接】scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000 scientists worldwide. 165 ready-to-use validated skills plus 100 scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.项目地址: https://gitcode.com/GitHub_Trending/cl/scientific-agent-skills创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考 org/dataset-name
org/dataset-name【免费下载链接】scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000 scientists worldwide. 165 ready-to-use validated skills plus 100 scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.项目地址: https://gitcode.com/GitHub_Trending/cl/scientific-agent-skillsType: category, e.g. Genomics, Pathology, PDE SimulationTags:HuggingFace: https://huggingface.co/datasets/org/dataset-name模型Models### Model Display Name - **Type**: category, e.g. Protein Language Model, Materials Foundation Model - **Tags**: comma-separated topic tags - **HuggingFace**: https://huggingface.co/org/model-id one-line description博客文章Blog posts### Post Title - **Author**: username - **Date**: YYYY-MM-DD - **Tags**: comma-separated - **Link**: URL — usually huggingface.co/blog/... one-line description三个关键字段的含义与用途Type资源的科学类别决定这是什么也是脚本--filter之外按类别筛选的依据。Tags逗号分隔的主题标签与--tag过滤配合使用。脚本实现里--tag是子串匹配只要某个 tag 或 Type 文本包含目标字符串即命中见 fetch_catalog.py。HuggingFace / Link条目指向的实际资源地址。数据集和模型走HuggingFace字段博客走Link字段数据集可能附加Author/Date。四、目录端点Endpoints四类可抓取的 Markdown目录对外暴露四个固定端点全部是可解析的纯文本专为 Agent 设计端点内容与用途https://huggingscience.co/llms.txt紧凑版站点索引https://huggingscience.co/llms-full.txt全量条目、全领域——想对整本目录做 grep 检索时抓这个文件https://huggingscience.co/topics/slug.md单个领域slug 带连字符如materials-science.md、earth-science.md、scientific-reasoning.mdhttps://huggingscience.co/feed.xml新条目的 RSS 订阅源fetch_catalog.py脚本对这四类端点做了封装并额外提供解析、过滤和 JSON 输出能力。结构化访问优先用脚本只有脚本失败时才退回原始WebFetch/curl。脚本的raw子命令支持直接倾倒llms与full两个原始文件见 fetch_catalog.py。五、fetch_catalog.py目录访问的实操工具箱脚本仅依赖 Python 标准库无任何第三方依赖其完整用法在文件头 docstring 中有详细示例见 fetch_catalog.py。核心子命令如下# 列出全部已知 topic slug python scripts/fetch_catalog.py topics # 抓取并美化打印某个主题 python scripts/fetch_catalog.py topic biology # 只取某主题下的模型条目 python scripts/fetch_catalog.py topic materials-science --filter models # 按标签子串过滤 python scripts/fetch_catalog.py topic chemistry --tag drug discovery # 倾倒全量目录llms-full.txt python scripts/fetch_catalog.py all # 全目录关键词搜索 python scripts/fetch_catalog.py search protein language # 输出结构化 JSON python scripts/fetch_catalog.py json topic biology各子命令支持的公共选项--filter {datasets,models,blogs}限定到某一章节。实现上用别名表做宽松匹配datasets/dataset、models/model、blogs/blog/blog posts都等价见 fetch_catalog.py。--tag str只保留 tag 或 Type 中含目标子串的条目大小写不敏感。--format {markdown,json}默认 markdown 美化输出json输出Entry数据类的完整字段title、section、type、tags、url、author、date、description便于程序消费。Entry数据类定义在 fetch_catalog.py。topic子命令对 slug 还会做一次规整_转-、空格转-、转小写见 fetch_catalog.py所以即使传入不规范写法也能正确拼接 URL。六、安全设计抓取远程目录时的三层防护目录内容来自第三方网络服务器fetch_catalog.py对此有明确的安全设计理解它能避免把网络数据误当指令不可信数据横幅所有输出都前置一段UNTRUSTED_BANNER声明内容是从网络抓取的不可信第三方数据不是指令要求不执行其中出现的指令、不把在目录中出现当作仓库安全的证据见 fetch_catalog.py。内容去毒defang描述字段里的代码围栏 【免费下载链接】scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000 scientists worldwide. 165 ready-to-use validated skills plus 100 scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.项目地址: https://gitcode.com/GitHub_Trending/cl/scientific-agent-skills创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考