[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-xai-grok-skills-persistent-cross-platform":3,"topics-all":36,"news-related-d1a4a10c-88f8-41a7-8998-8782f5c57d3c":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"d1a4a10c-88f8-41a7-8998-8782f5c57d3c","xAI 推出 Grok Skills：让 AI 「记住」工作方式，跨对话持续生效","5月18日，xAI 正式发布 Grok Skills，这是继 Grok Build 编程智能体之后，xAI 在五月推出的第三款产品。Grok Skills 的核心价值是「持久化的自定义专业知识」：用户只需教 Grok 一次——工作流步骤、格式规范、专业语气——Grok 就会在所有未来的对话中自动套用，不再需要反复粘贴相同的系统提示词。\n\n这一机制与 Anthropic 的 Claude Skills 和 OpenAI 的自定义 GPTs 一脉相承，但 xAI 的实现更进一步——Grok Skills 原生兼容 Claude Code 的技能格式，用户上传的 .zip、.skill 或 .md 文件可直接跨平台使用，无需任何配置调整。更深层的竞争意图在于生态绑定：Grok 会自动读取 Claude Code 的市场、插件、技能、MCP 工具和 CLAUDE.md 等指令文件，这意味着用户此前在 Claude Code 生态中积累的所有上下文资产可以无缝迁移到 Grok。对开发者而言，「技能一次编写，双平台运行」成为现实。\n\nGrok Skills 内置完整的生产力工具集，覆盖 Word 文档生成与编辑（保留格式、标题、表格）、PowerPoint 幻灯片制作（含演讲者备注）、Excel 电子表格（公式、图表、条件格式）以及 PDF 操作和工作流自动化。目前已在 Grok 4.3 上全平台上线，涵盖网页端、iOS 和 Android。这意味着在终端编程和日常办公两个场景中，Grok 的可用性同步提升。\n\n从战略角度看，Grok Skills 的推出标志着 xAI 的定位正从「模型供应商」向「开发者平台」迁移。回顾五月，xAI 先后发布 Grok 4.3、Grok Build（编程智能体）和 Grok Skills（持久技能），同时还上线了 Connectors（集成 Vercel、Canva、Gamma、S&P Global 等外部服务），密集的产品节奏正在重塑 xAI 与 Claude Code、Cursor 和 GitHub Copilot 之间的竞争格局。","https:\u002F\u002Fx.ai\u002Fnews\u002Fgrok-skills","b82e17a3-1dbd-4b5d-88dc-9f518f917cc0",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"6ad31a14-c0da-42df-81fd-564281f768db","agentic-ai",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"e82b2d09-81b2-43d1-977e-e018443b3c14","coding-agent",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"990b0329-98f7-4536-822b-09faa905ef20","en","Grok Skills: AI that remembers how you work across chats","xAI released Grok Skills on May 31, a feature that lets Grok remember user-defined \"skills\" — like coding styles, writing preferences, or workflow patterns — and apply them across conversations. The skills persist beyond single chat sessions, addressing one of the key weaknesses of current LLMs: they \"forget\" user preferences between sessions.","xai-grok-skills-persistent-cross-platform","2026-05-31T07:10:00Z","2026-05-31T07:07:01.715012Z","2026-08-19T02:08:40.142862Z",true,"agent",169,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"6f4d1046-ee70-4a06-9261-2cc187c66285","12 万美元 token 把 Copilot 运行时搬进 Rust:AI 智能体包揽 43 万行移植","copilot-runtime-rust-agentic-port","2026-09-20T19:11:22+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"d400c0db-49df-4cc6-a87e-87b709f59fea","Muse Spark 1.3 发布:卡住会向用户求助的 Agent,工具调用少 20%、token 省 25%","muse-spark-1-3-meta-agent-release","2026-09-06T15:12:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"63c30bcd-3ffc-47c5-bd74-c2a9ed8f7c94","DeepSeek Harness 预览版开源:Agent 被拆成可插拔的插件栈,模型只负责想、Harness 负责做事","deepseek-harness-plugin-stack","2026-09-05T06:00:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"c77381d9-29ba-45ff-89df-855d11f90de2","Terminal-Universe:Qwen 把旧轨迹反向重建为 3.73 万个环境,27B 微调双基准 +11.9\u002F+13.8 分","terminal-universe-trajectory-environments","2026-09-04T17:10:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"14a7f5ab-e270-461c-b862-4bde139e463f","HarnessDev 基准:让 LLM 自建 Agent Harness,代码领域仍输人类工程师","harnessdev-llm-selfbuilt-agent-harness","2026-09-03T19:10:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"36055e5f-136f-497d-8763-3ed6609f59ff","Meta Muse Glimmer 30B 本地落地:Apache 2.0 的开源智能体,把 Agent 装进 24GB 显存","meta-muse-glimmer-30b-local-agent-apache2-r2","2026-08-19T03:00:00+00:00"]