04-19 08:04 · 技术迭代,生态扩展,内容生成,多模态AI,平台能力
根据文字描述或参考图片生成视频的技能
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
AI视频生成与编辑，使用火山引擎 Doubao Seedance 模型。支持文生视频、图生视频、有声视频。当用户要求生成视频、制作视频、文生视频、图生视频时使用此 skill。
Like a lobster shell, security has layers — review code before you run it.
通过火山引擎 Doubao Seedance API 生成视频。
▸ 展开全文
04-19 08:03 · Clawhub,OpenClaw,技能,微博,技术
OpenClaw微博发帖自动化技能，支持格式校验、定时发帖等功能
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
发微博（新浪微博）。当用户说"发微博"、"发条微博"、"发到微博"、"发一条微博"、"帮我发微博"、"发到微博"时触发。使用浏览器自动发微博。
Like a lobster shell, security has layers — review code before you run it.
找到发微博的文本框ref=e35，以及发送按钮（初始 disabled，填入内容后变为可点击）
⚠️ 内容中换行用\n，不要用真正的换行符
必须是#标签#（前后各一个 #），不是 #标签
✅ 正确：#黄仁勋# #英伟达# #太空数据中心#❌ 错误：#黄仁勋 #英伟达 #太空数据中心（少了右边的 #）
▸ 展开全文
04-19 08:02 · 办公自动化,平台集成,生态竞争,企业服务,SaaS
飞书文档、云盘、知识库等集成技能，支持自动化办公
飞书深度集成技能。不是简单的消息桥接，而是你的数字指挥中枢。专为中国企业高压协作环境设计，理解“分寸”与“效率”两套并行规则，把消息、审批、会议、文档、多维表格、日程与邮箱，压缩成有优先级、可执行的行动链。
Like a lobster shell, security has layers — review code before you run it.
这不是一个简单的飞书桥接工具，而是你的数字指挥中枢。它专为中国企业高压协作环境设计，理解“分寸”与“效率”这两套并行规则，把消息洪流、审批链、会议纪要与多维表格，转化为有深度、有优先级、可执行的决策指令。
早上八点四十五分。你打开飞书，看到的是这样一幅景象：
群消息 247 条未读，散布在 14 个群里。其中有 3 条需要你今天回复，但它们被淹没在项目讨论、日常闲聊和转发的行业文章中间。你不知道哪 3 条是重要的，除非你把 247 条全部看完。
4 条审批等你处理。其中一条是三天前提交的报销，提交人已经在私信里委婉地问了两次“方便看一下吗”。
你有 6 个会议，其中两个时间冲突。上周五的产品评审会你缺席了，会议纪要还没人写，但今天下午的跟进会需要基于上次的结论继续讨论。
你的 OKR 本周需要更新，但你已经三周没更新了，因为每次打开那个文档你都需要先花二十分钟回忆过去一周到底做了什么。
多维表格里的项目看板显示 4 个任务逾期，但其中 2 个实际上已经完成了只是没人更新状态，另外 2 个你需要去找对应的同事确认进展。
这就是一个普通中国企业中层管理者的周一早晨。不是因为工作量太大，而是因为信息散落在飞书的每一个角落。把它们捡起来、拼成全貌、做出判断、采取行动——这个过程本身就吞噬了你一天中最清醒的两个小时。
飞书技能要做的事情只有一件：让这个周一早晨从“信息焦虑”变成“行动清单”。
洞察：高权限能力必须建立在明确授权之上。本技能采用“双轨运行模式”，并在首次调用时强制完成握手。
如果用户尚未明确选择模式，本技能必须默认处于参谋模式，不得擅自执行任何写操作。
当用户首次调用本技能，或上下文中尚未确定模式时，智能体应先发出如下提示，再继续后续动作：
飞书中枢已接入。为保障协作安全与权限边界，请选择当前运行模式：[1] 参谋模式（默认）：我负责读取、分析、草拟，所有写操作需你确认。[2] 执行模式：我可在授权范围内执行常规写操作，但高敏动作仍需二次确认。你可直接回复1或2，也可以随时用“切换飞书模式”重新设定。
飞书中枢不会把所有问题都当成“执行问题”。
在进入摘要、草拟、催办、同步、协调之前，它应先判断当前协作摩擦真正发生在哪一层。
在识别出摩擦类型后，再决定应该在哪一层处理、采取哪种动作。
飞书中枢的价值，不是“做更多动作”，
而是选择最高杠杆、最低摩擦的动作。
只有先判断问题属于哪一层，
飞书中枢才决定应该摘要、草拟、提醒、协调、同步，还是暂停并请求确认。
洞察：群消息不是信息问题，而是注意力排序问题。
飞书里的群聊是中国企业协作的主动脉，也是效率黑洞。真正消耗你的，不是消息量，而是你必须自己完成“筛选、归类、判断、响应”这四步。
它不仅能提取消息，还会补足上下文。你不用重新翻 80 条历史记录，才能明白这一条“你看下”到底在说什么。
洞察：审批流不是单纯流程，它是企业内部资源流动的闸门。
很多审批不是因为“没人看到”而卡住，而是因为信息不完整、责任模糊、催办方式失分寸。
这个技能不会只提醒你“有审批待处理”，它会先做预审：
它的目标不是让你“更快点通过”，而是让审批链整体更少空转。
洞察：会议的成本不在会议本身，而在“会前没人准备、会后没人执行”。
大多数会议不是缺讨论，而是缺结构。飞书会议录音和转写本身并不稀缺，稀缺的是：
会议的价值，不应停在“开过”。而应停在“形成行动”。
洞察：多维表格不是数据仓库，而应成为轻量决策系统。
这个技能把多维表格从被动记录器，变成主动协同层。
它不只是帮你“填表”，而是帮你让表成为组织的第二大脑。
如果一个人的日历完全由别人决定，那他的深度工作时间只会越来越碎。这个技能会用“优先级、冲突、精力结构”来看待日程，而不是只看空档。
它不只是帮你安排时间，而是在替你守住高价值时间。
洞察：知识的价值不在存储，而在被正确召回。
飞书文档最常见的问题不是“没有写”，而是“写了以后找不到、看不完、用不上”。
这个技能会把文档从静态容器变成动态知识流：
洞察：在中国企业里，效率决定结果，分寸决定你还能不能继续高效。
这个技能不是简单“帮你发话”。它要先判断：
这个技能不是“查一下”，而是“代理执行逻辑链”。
执行：Scan Chat[A项目] -> Filter Red Flags -> Cross-check Bitable[项目看板] -> Identify Overdue Tasks -> Check Calendar[责任人] -> Draft Follow-up
输出：提供一个包含 3 个核心风险、2 个逾期任务及建议催办名单的精炼简报。
输入：“查一下谁的审批卡住了，帮我催一下，语气委婉点。”
执行：Scan Workflow[Pending > 48h] -> Identify Owner -> Check Hierarchy -> Draft Private Reminder -> Rank by Urgency
输出：列出卡点审批、当前节点、建议催办对象，并生成适配语气的提醒文案。
输入：“帮我起草这周周报，重点写 A、B 两个项目。”
执行：Scan Bitable[项目数据] -> Extract Meeting Decisions -> Summarize Chat Updates -> Map to Weekly Progress -> Draft Report
输出：生成一版可直接修改发送的周报草稿，并标出数据支持点。
输入：“我们上次讨论用户留存的结论在哪个文档里？”
执行：Search Docs[关键词=用户留存] -> Rank by Relevance -> Extract Conclusions -> Return Source Links
输出：返回最相关文档、关键结论摘要，以及原文位置。
这个技能只处理你已有权限范围内的飞书数据。它不会越权读取你没有权限的群、文档、审批或表格。
飞书中的数据属于组织，权限属于角色，而这个智能体只是把这些碎片重新编译成可执行的协作指令。
飞书不是消息入口。它应该成为你的决策中枢。
本技能为纯指令型编排器，不包含任何网络请求代码、安装脚本或二进制文件。
为实现“数字指挥中枢”能力，推荐关联的飞书应用具备以下最小权限范围：
说明：以上为推荐权限范围，并非本技能自行申请的权限。实际访问范围应以宿主平台连接器和用户授权结果为准，并遵循最小权限原则。
在执行任何高权限动作前，智能体应先完成以下检查：
先识别 → 再建议 → 后确认 → 再触发
飞书中的数据属于组织，权限属于角色。这个技能的职责不是越权代替人，而是把碎片化协作重新编译成更清晰的行动链。
为了实现“数字指挥中枢”能力，推荐将权限理解为两层：
即使处于 Extended，仍应遵循高敏动作二次确认原则。
先识别 → 再建议 → 后授权 → 再执行
本技能的价值，不在于替人越权行动，而在于把碎片化协作重新编译成更清晰、更有分寸的行动链。
▸ 展开全文
04-19 08:02 · AI,技术,HackerNews,AI
Show HN: AI Subroutines – Run automation scripts inside your browser tab
Most web agents solve the wrong half of the problem. You can get an LLM to post on X, DM on Instagram, or send a LinkedIn connection request — once. The moment you need to do it a thousand times, the economics break: tokens per invocation, latency per invocation, non-determinism per invocation. On outreach, CRM updates, and bulk posting, "the agent clicked the wrong button this time" is not a quirk. It's a failure mode.
The obvious fix is to skip the UI and call the site's internal API directly. That's correct, and it's where most "just call the API" projects die. Because the hard problem isn't the endpoint. It's auth.
Authenticated web requests carry some combination of cookies, rotating CSRF tokens, session tokens, bearer headers, anti-replay nonces, fingerprint-bound parameters, and request-signing hashes computed in the site's own JS at request time. Some are set by the server. Some are derived in the browser. Some rotate per request.
Out-of-process scrapers — Node workers, Playwright workers, cloud functions — have to rebuild all of that out of band. That's the thing that breaks the moment a site rotates a header or ships a new signing scheme. Most HAR-replay tooling ends its useful life right here.
In rtrvr, both the recording and the replay happen inside the user's browser, from within the webpage itself.
No Puppeteer driver. No headless worker. No separate TLS stack. The browser does what it always does: attach the cookies, run the site's own JS to compute the headers, ship the request.
Auth, CSRF, signing, and fingerprinting all propagate for free.The agent never touches any of it. No key extraction, no session rebuild, no proxy rotation.
This sounds like a footnote. It's the whole architecture.
There's a second problem hiding inside "just record the network." A typical minute of browsing fires dozens to hundreds of requests per tab — analytics beacons, RUM pings, feature-flag polls, third-party pixels, prefetches, media chunks, hot-module reload pokes. TheactualAPI call you care about is often 3 requests out of 300.
You cannot hand all of that to an LLM to figure out which one is the tool. It does not fit in the context window, and even if you paid to stretch it, the signal drowns in the noise.
So before the generator sees anything, we rank and trim the capture. Requests are scored on a handful of weighted signals:
Concretely: a first-party mutatingPOSTthat fires 80ms after a click with a 200 response and a body lands around +83. A generic analytics beacon is −80. Everything in between gets ordered and the top five survive. Those five plus the DOM interactions around them get rendered into a 12 000-character context for the generator; if it overruns, we drop visited URLs first, then network candidates, then DOM hints, and re-render until it fits.
Even after ranking, a strong candidate is not automatically replay-worthy. If the top request carries a volatile operation identifier — X'squeryId, Meta'sdoc_id, any GraphQL operation hash pinned to the current deploy — the planner forces a DOM-only tool regardless of score, and the generator is instructed not to surface those values in the first place (Do NOT expose or discover queryId/doc_id/operationHash values). This is the single most useful failure case to catch early: network replay looks great in a demo and breaks quietly a week later when the site ships.The docsgo deeper on how the DOM / network / hybrid decision is made and thertrvr.*helper namespace the generated code uses.
This is the unglamorous step that makes recording→Subroutine actually work. In-page execution solves auth for free; ranked trimming — with the volatile-ID circuit breaker — is what lets the generator reliably pick the right request to templatize.
A recorded task — aSubroutine— is registered as a callable tool in the agent's tool set, next tosearchandfetch:
Point the agent at a sheet of 500 rows. It picks parameters per row. The Subroutine runs. The LLM is invoked exactly once per row — for parameter selection — and the action itself is a script.
A Subroutine is a small async JavaScript function that runs in the tab. The parameters the agent passes — the row from the sheet, the target URL, the message body — are injected asconstdeclarations above your code. Inside the body, anrtrvr.*helper namespace covers the common moves you need on real sites without dropping down to brittle selectors or hand-rolledfetchscaffolding:
A minimal LinkedIn "connect" Subroutine:
DOM when the UI is the stable contract,rtrvr.requestwhen the endpoint is. The generator mixes them as needed, and because everything runs in the page, cookies and CSRF tokens are just there — you read them, you don't rebuild them.
A few non-obvious implementation details worth knowing:
We record HTTP. Sites that do real work over WebSockets, WebRTC, or heavy mid-flow client-side derivation need DOM actions interleaved into the Subroutine. That path is slower and less reliable — we treat it as a fallba
▸ 展开全文
04-19 08:01 · AI,Google,长上下文,大模型,AI
Google发布Gemini 2.0，支持200万tokens上下文，在处理长文档方面优势明显
AI for every
developer
Unlock AI models to build innovative apps and transform development workflows with tools across platforms.
Explore models in Google AI StudioStart building
Get started building with cutting-edge AI models and tools
Own your AI with Gemma open models
Build custom AI solutions and retain complete control. Tailor Gemma models, built from the same research and technology as Gemini, with your own data.
Build with GemmaRun AI models on-device with Google AI Edge
Build and deploy edge ML solutions across mobile, web, and embedded applications, from simple APIs to custom pipelines, with support across all major frameworks.
Explore Google AI EdgeBoost productivity with AI code assistance
Agents
Gemini empowers you to be more productive by acting as your coding agent. It can plan and execute tasks, freeing you to focus on what matters most.
Analysis and insights
Improve code quality and fix issues with code analysis. Get insights, suggestions, and code snippets within your existing development environment.
Code generation
Gemini adds AI-powered code completion with natural language understanding to create entire code blocks from your descriptions, revolutionizing your development workflow.
Code chat
Ask development questions and receive responses that help you reduce errors, solve problems, and become a better developer. Gemini understands the context of your environment to give you the best responses for your questions.
Explore apps built with the Gemini API
Join the community
Tap into the power of our community forum. Get answers, build together, and be part of the conversation.
▸ 展开全文
04-19 08:01 · 技术迭代,平台生态,AI技能,内容生成,竞争加剧
基于文字描述的图片生成技能，支持多种风格和模型
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Like a lobster shell, security has layers — review code before you run it.
This skill generates images using the best AI model for each use case.Model selection is the most important decision— read the dispatch logic carefully before generating.
Always select the model based on the user's actual need, not just the request surface.
UseNano Bananawhenever the user's request involves:
Nano Banana uses Google's Gemini 3 Pro multimodal architecture, which understands context holistically rather than keyword-matching. It supports up to 14 reference images for maintaining character and scene consistency.
exec timeout: Set at least120 secondsfor Midjourney and Nano Banana; 30 seconds is sufficient for Flux Schnell.
Always use sync mode (no--async). The script waits internally until complete.
CRITICAL — image field meanings:
"放大第N张" / "要第N张" / "give me image N" = sendimageUrls[N-1]directly. Do NOT call generate.js again.
🎨 生成完成！这是 4 张图的预览：预览图你喜欢哪一张？回复 1、2、3 或 4，我直接发给你高清单图。
When user picks image N:
Use for storyboards, character series, and any context-dependent multi-image generation.
How to build a storyboard series:
Example storyboard workflow:
SendimageUrldirectly to the user (no grid, single image).
Best for photorealistic standalone images. Output format same as Nano Banana (singleimageUrl).
Best for images containing text (logos, posters, signs).
Best for vector-style, icons, flat design.
For Midjourney: Addcinematic lighting,ultra detailed,--v 7,--style raw. Legnext supports all MJ parameters.
For Nano Banana: Use natural language descriptions. Describe the character consistently across frames (hair color, clothing, expression). Mention "same style as reference" or "consistent with previous frame".
For Flux: Addmasterpiece,highly detailed,sharp focus,professional photography,8k.
For Ideogram: Be explicit about text content, font style, layout, and color scheme.
For Recraft: Specifyvector illustration,flat design,icon style,minimal.
User: "帮我画一只赛博朋克猫"
→ Single artistic image →Midjourney→ Tell user "🎨 正在用 Midjourney 生成，约 30 秒..."
→ Send grid preview, ask which one they want
User: "帮我生成一套分镜图，讲述一个女孩在魔法森林的冒险"
→ Multiple frames with story continuity →Nano Banana→ Tell user "🎨 这类有上下文关联的分镜图用 Gemini 生成，能保持角色一致性..."
→ Generate frame by frame, using previous frames as reference images
User: "要第2张" / "放大第2张" (after Midjourney generation)
→ SendimageUrls[1]directly. No need to call generate.js again.
User: "做一个 App 图标，蓝色系扁平风格"
→ Vector/icon →Recraft
User: "生成一张带有'欢迎光临'文字的门牌图"
→ Text in image →Ideogram
User: "快速生成个草稿看看效果"
→ Speed priority →Flux Schnell(<2s)
User: "生成一张产品海报，白色背景，一瓶香水"
→ Photorealistic product →Flux Pro
▸ 展开全文
04-19 08:01 · AI,微软,Copilot,AI
微软宣布Copilot AI助手全面集成到Windows 12操作系统
使用 Microsoft 365 充分利用每一天
只要购买一项计划，即可享受在线保护、安全的云存储空间和多款创新应用，满足你的各种需求。
Xbox 控制器
Elite 品质，无线连接，随处适用 - 无论你的游戏风格如何，这款控制器都能满足你的需求。
Xbox Elite 无线控制器 2 代 黑色
全新 Xbox Elite 无线控制器 2 代针对竞技型玩家所设计
Microsoft Edge
浏览过程中，可体验出色性能，隐私性更强、效率和价值更高。
商业版
全新
来认识一下最新的 Surface 商用版 Windows 11 AI+ PC
便携、性能强劲，且具备世界级安全防护—这就是搭载 Snapdragon® 处理器的 12 英寸 Surface Pro 商用版以及 13 英寸 Surface Laptop 商用版。
获取适合你的业务的 Microsoft Teams
联机会议、聊天、实时协作以及共享云存储，尽在一处。
加入 AI 时代
使用最新的 Microsoft AI 解决方案进行创建、沟通和编码。
面向企业的 Windows 11
专为混合办公而设计。为员工提供强大支持。为 IT 提供一致体验。全面的安全保障。
▸ 展开全文
04-19 08:00 · 平台更新,功能增强,工具集成,技能扩展,用户服务
获取当前天气和天气预报的实用技能
Get current weather and forecasts (no API key required).
Like a lobster shell, security has layers — review code before you run it.
Two free services, no API keys needed.
Format codes:%ccondition ·%ttemp ·%hhumidity ·%wwind ·%llocation ·%mmoon
Free, no key, good for programmatic use:
Find coordinates for a city, then query. Returns JSON with temp, windspeed, weathercode.
Docs:https://open-meteo.com/en/docs
▸ 展开全文
04-19 08:00 · AI,技术,HackerNews,AI
Dad brains: How fatherhood rewires the male mind
Dad brains: How fatherhood rewires the male mind
From before their babies are born, men undergo serious hormonal changes that can powerfully influence their behaviour – with consequences for their child's wellbeing.
In the months before my son was born, my partner and I attended an active birth workshop, a breastfeeding session and the hospital-run antenatal course, read a small pile of pregnancy and baby books and scrolled through loads of websites. Our notepads quickly filled up.
Among my notes of that time are details of the many ways women's bodies prepare for birth and motherhood: hormones rise and drop, organs move, brains reshape.
No one, however, told me that my brain and body were also readying for fatherhood.
My son was over a year old when I first came across that idea in Father Time, a book by primatologist Sarah Blaffer Hrdy in which she argues that men have all the necessary biological wiring to be "every bit as protective and nurturing as the most committed mother".
This piqued my curiosity. I am a resolute believer in active fathering, but I had imagined this was a cultural decision by my generation of men. Hrdy's book, however, introduced me to an entire academic field saying that our approach is rooted in biology, just dormant and waiting to be triggered.
After interviewing Hrdy and other experts and delving into the studies, I came to a simple conclusion: fatherhood changes men in ways that echo how motherhood transforms women. The more involved a father is with their baby's care, the deeper this transition becomes. These shifts in our endocrine and neural system show that the nurturing father is not a modern aberration, but a deeply rooted biological trait.
Falling testosterone
The earliest research on how fathers are physically changed by babies came from observations of other animals. These late 20th-Century studies found that many mammalian males – including other primates – show clear hormonal shifts, including rises and drops in hormones like testosterone, vasoprin and prolactin, typically associated with motherhood, as they engage in active parental care.
When the American anthropologist Lee Gettler, then an undergrad student, heard about these findings in the early 2000s, he was hooked.
"I asked [my lecturer] whether anyone was studying these questions in human fathers, and the answer at that point was largely no", says Gettler, now the director of the Hormones, Health, and Human Behavior Laboratory at the University of Notre Dame in Indiana.
The first-ever study demonstrating hormonal changes in men had just been published in 2000 by two Canadian scholars – Katherine Wynne-Edwards and Anne Storey. By the time Gettler looked into this field, it was already an established fact that fathers had lower testosterone that men without kids.
"But there's a chicken and the egg problem there, right?" Gettler explained to me. "Are low testosterone men more likely to become fathers? Or does the transition to fatherhood kind of lead to this cascade of biological changes in men?"
To answer this question and others, Gettler teamed up with the scientists running a decades-long project in Cebu City, Philippines.
In 2005, this team collected saliva samples from 624 men, with an average age of 21 years old and without partners, and tested them for testosterone, then four years later tested them again. They wanted to answer two questions: would men that become fathers in the interim have lower testosterone, and would it be even lower in fathers that spent more hours doing childcare?
When the results came back, the answer to both questions was "yes". The men that had babies showed significantly lower levels of testosterone compared to non-fathers. And the men that had spent longer looking after babies showed the largest drops in testosterone. Those that shared a bed with their infants also had lower levels.
"I think it was the first clear message in the scientific literature that men have this capacity to prepare for fatherhood," Gettler told me. In a way, he explains, this is their biology preparing them for caregiving.
Their findings are not unique. Other teams have also found that drops in testosterone during their partner's pregnancy are also linked with higher investment, commitment and satisfaction after birth, and that this hormone’s level was even linked to the men's reactions to baby cries: it made them more alert and responsive. In 2018, a team in Gettler's lab also concluded that fathers with lower levels of testosterone tend to be more involved in caring for babies and toddlers.
But when does this happen? The question of whether it's before or after birth was bubbling in the mind of James K Rilling, the director of the Laboratory for Human Social Neuroscience at Emory University in the US.
"My assumption," Rilling told me, "was that it would happen during the postnatal period after fathers spent some time interacting with their infants."
What they found surprised them. When they tested exp
▸ 展开全文
04-19 08:00 · AI,硬件,英伟达,AI
英伟达发布Blackwell架构AI芯片，性能提升显著，支持更大模型训练
Data Center
The NVIDIA inference platform powers the highest performance across a broad range of workloads to scale AI factory revenue.
Energy
Major power producers support new AI factories built with NVIDIA Vera Rubin DSX architecture to accelerate deployment and strengthen the U.S. power grid.
Explore the Best of GTC 2026 Sessions
NVIDIA Extreme Co-Design Delivers New MLPerf Inference Records
DLSS 4.5 Now Available
NVIDIA and Emerald AI Accelerate Power-Flexible AI Deployment
Make Autonomous Agents More Secure by Design With NVIDIA OpenShell
NVIDIA Vera Rubin Opens Agentic AI Frontier
▸ 展开全文