Top Rated

飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。

飞书 / Lark 通讯录:按姓名 / 邮箱解析成 open_id,或按 open_id 反查姓名 / 部门 / 邮箱 / 联系方式 / 个人状态 / 签名,以及按关键词搜索当前用户可见的机器人 / 智能体(agent)。当用户提到一个名字要下一步发消息 / 排日程,或拿到 open_id 想查具体信息时使用。不负责部门树遍历、按部门列员工、组织架构图,这类需求走原生 OpenAPI。

用代码制作以图形、文字或界面动画为主的短视频（常见 5–60 秒，纯音乐片最长约 2 分钟），输出 MP4 和可编辑源码：产品宣传短片、动效作品集、UI 动效演示、动态排版与金句卡点、Logo 演绎与片头、生成艺术循环、年代回顾短片。配乐可选：代码合成，或按用户提供的曲子卡点。用户想做这类短视频或动效时使用，例如「做个 15 秒动效视频」「做个 Logo 动画 / 片头」「做个产品宣传短片」「用代码做视频」。不用于：口播讲解类长视频、网页与交互原型、写实人物或实拍内容、剪辑已有视频。

Use this skill to create home screen widgets using Jetpack Glance Canonical

把一个名词或概念写成可使用的理解：先用普通话讲清它是什么、与相邻概念差在哪里，再说明它怎样运作、会改写什么判断，最后给出面对它时的行动抓手。USE WHEN 用户问 X 是什么、怎么理解、意味着什么、为什么重要、以后怎样判断或使用；尤其适合技术概念、制度、产品、角色、方法、规范与实践。NOT FOR 单纯查事实、公式证明、逐步操作教程、纵向因果深挖（用 ljg-think）或母题结构（用 ljg-structure）。

Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex

影片与视频编辑和内容创作者必备！当需要制作《三体》主题视频时，自动化完成选题策划、视觉设计、音频生成到成片合成，多智能体协作流程，3小时搞定72小时工作量。

Understand the PM-to-Director transition through altitude and horizon thinking

Run a product sunset end to end — decide, align, plan, prepare, announce, close

Run a go/no-go assessment for retiring a product or feature, then right-size the effort

Diagnose where a product sits in its lifecycle and which play fits — extend, replace, or retire

Evaluate SaaS unit economics and capital efficiency

Create a six-frame storyboard that shows a user's journey from problem to solution

Add, integrate, or build Preline UI components and blocks into HTML files via the Preline MCP server

Create a dark monochrome procedural background with enlarged square pixels and visible Bayer-style ordered dithering

Use when you need to add or debug professional web animations with GSAP (timelines, ScrollTrigger, stagger, transforms) in HTML/CSS/JS/React. Includes patterns for smooth motion, performance, and common pitfalls.

Extracts Airbnb accommodation search results from a destination query via SSR-embedded data, returning listing ID, URL, name, coordinates, rating, price, photos, and badge info for each result, plus pagination cursors for multi-page retrieval

Extract seller or merchant profile data from marketplace platform seller pages. Returns seller name, rating, review count, positive feedback percentage, joined date, and return policy. Works on Amazon seller pages, eBay seller pages, and any e-commerce site with seller profiles

Fetches comments from an Instagram post including comment text, username, timestamp, like count and reply count

Use when diagnosing PPT Skill setup or failures involving source parsing, Playwright or Chromium rendering, HTML-to-PPTX export, Workbench startup, or bundled search and image-tool configuration.

Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install. ALWAYS use this skill when the user says any of: "update SenseNova skills", "update SN skills", "更新 sensenova skills", "更新 sn skills", "刷新 sn-*", "升级 sn-* skills", or names a specific sn-* skill to update (e.g.

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/M…

中文简历与目标岗位驱动的面试预测、模拟追问和复练技能：提取需要验证的经历 Claim，按面试轮次建立问题与评分契约，通过一次一问、证据反馈和弱项复练检查真实掌握程度；当用户输入“/interview”、要求面试预测、模拟面试、简历追问、压力面、场景设计题或检查面试掌握程度时使用。

Production-grade Bayesian causal inference with PyMC, CausalPy, and DoWhy. Enforces DAG-first thinking, mandatory user checkpoints for assumptions, design-specific refutation, and defensible reporting with causal language guardrails.

Defamiliarization audit for empirical output. Systematically interrogates every feature of a figure, table, or set of results — not just the main finding. Named for Jason Fletcher, who asked about the spike at t=1 when everyone else was looking at t=2