skill-router-nexus

⚠️ MANDATORY ENTRY POINT — ALWAYS read this file FIRST before: (1) planning any task (plan / blueprint / roadmap / how to implement), (2) reviewing a plan (review / audit / stress-test), (3) executing a task (implement / build / run), (4) verifying completion (done / verify / submit / PR / confirm finished), (5) accessing, querying, or adding any sub-skill. Do NOT load or look up any sub-skill directly. Every agent, every task, and every skill query must route through this file first. | ⚠️ 強制入口 — 以下情境必須先完整讀取本檔再行動：(1) 制定計畫（計畫、規劃、plan、blueprint、怎麼做）；(2) 計畫審查（review、審查、壓力測試）；(3) 執行任務（執行、implement、build）；(4) 驗證完成（驗證、done、verify、確認完成、submit、PR）；(5) 存取、查詢或新增任何 skill。嚴禁直接載入或查詢子 skill、嚴禁繞過本檔。

Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to-im", "bridge", "消息推送", "消息转发", "桥接", "连上飞书", "手机上看claude", "启动后台服务", "诊断", "查看日志", "配置". Subcommands: setup, start, stop, status, logs, reconfigure, doctor. Do NOT use for: building standalone bots, webhook integrations, or coding with IM platform SDKs — those are regular programming tasks.

基于文档内容自动生成配图。AI 智能分析文档结构，归纳核心要点， 为每个主题生成符合特定风格的配图。支持封面图生成和自定义图片比例。 使用场景：当用户需要为文档、文章、笔记生成配图时。 关键词：配图、插图、illustration、generate images、document images

基于 AI 自动生成高质量 PPT 图片和视频，支持智能转场和交互式播放。用于从文档生成 PPT 图片、Nano Banana/PPT 生成、可灵 AI 转场视频和演示播放器。

Reusable HTML slide template library with 34 complete visual systems. Use when the user wants a beautiful HTML slide deck, presentation, PPT-style web deck, pitch deck, talk slides, or template-driven slide design and wants the agent to pick, preview, clone, and adapt a strong template from a curated gallery.

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

用 19 套内置中文 PPT 模板（或用户自带的 .pptx 模板）生成与编辑 PowerPoint 演示文稿：只替换文字、不破坏原排版/配色/字号，内置按文本框尺寸的出框检测与同级标题字号一致校验；也支持完全原创的简洁版式。当用户要"做 / 生成 / 制作 / 编辑一份 PPT / 演示文稿 / 幻灯片 / .pptx"，或需要工作汇报、年终与季度总结、述职竞聘、项目复盘、开题答辩、商务提案、教学课件、数据可视化等成品 PPTX 时使用。Use when the user wants to create or edit a PowerPoint / PPT / slides / .pptx deck, pick from built-in templates, or apply their own template without breaking the layout.

AI-driven multi-format SVG content generation system. Converts source documents (PDF/DOCX/URL/Markdown) into high-quality SVG pages and exports to PPTX through multi-role collaboration. Use when user asks to "create PPT", "make presentation", "生成PPT", "做PPT", "制作演示文稿", or mentions "ppt-master".

用于「造skill」「蒸馏XX」「女娲」「造人」「XX的思维方式」「做个XX视角」「更新XX的skill」等人物或思维方式 Skill 生成需求；也用于模糊需求下推荐并蒸馏合适的人物视角。

Drive a physical e-ink desk card (M5Paper 540×960) sitting next to the user's monitor. Use whenever the user wants to: - show / push / display ANYTHING on their card / 卡片 / 副屏 / 墨水屏 / e-ink display / desk card / glanceable display / secondary display - set up the device for the first time (flash firmware, pair, provision Wi-Fi) — phrases like "刚拿到 M5Paper", "怎么装卡片", "first-time setup", "刷固件", "卡片没反应" - schedule recurring pushes / "每小时刷一次" / "工作时间显示日历" / "auto-refresh every 30 min" - configure what the card shows (weather, todos, calendar, inbox, PR queue, AI status, focus, scratch, deadlines, messages, now-playing, git-status, system, next-meeting, break-reminder, ai-tasks) - put the device to sleep / show business card / "息屏" / "睡眠" Single Skill, agent-agnostic: probes current state, then routes to the right sub-flow. Never asks "is the daemon running" — it checks.

为访谈视频添加综艺特效（花字、卡片、人物条、章节标题等）。支持 4 种视觉主题，先分析字幕内容生成建议供用户审批，再渲染视频。

为 Seedance 2.0 视频生成模型撰写产品宣传动画提示词（Motion Graphics Prompt）。 生成 15 秒一镜到底的动态影像提示词，支持 4 种美学风格（Apple/Microsoft/Bauhaus/Vercel）。 支持垫图（参考图）模式，自动标注图片占位符。 生成提示词后可通过即梦 Dreamina CLI 直接生成视频（自动检测安装状态）。 TRIGGER when: 用户需要生成 Seedance 视频提示词、产品宣传动画提示词、motion graphics prompt， 或提到 "Seedance"、"视频提示词"、"产品动画"、"宣传视频提示词"、"video prompt"。 Keywords: Seedance, 视频提示词, video prompt, motion graphics, 产品动画, 宣传动画, 垫图, Dreamina

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects and fixes inflated symbolism, promotional language, vague attribution, em dash overuse, rule of three, AI vocabulary, passive voice, negative parallelisms, and filler.

检查和清理中英文文本里的 AI 套路，适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求；按场景控制力度，同时保留事实、术语、语域和责任主体。

写作工作流总导演；用于帮我写、写文章、写一篇、创作、写作、产出、起草等写作请求，要求先询问用户选择 A/B/C 模式。

Use when Codex needs to open, inspect, navigate, click, type, screenshot, test, or debug a web page or browser-based workflow and multiple UI automation surfaces are available. Enforces Codex tool priority: use the Chrome plugin first, fall back to Computer Use only when Chrome cannot handle the task, and use the Browser plugin only as the last fallback or when the user explicitly requests Browser.

Build pure frontend ONNX WebGPU tools for large browser-hosted models. Use when implementing or documenting ONNX Runtime Web, WebGPU, OPFS model caching, HTTP Range downloads, Hugging Face model loading, progress UI, and browser-only inference workflows.

Use MMSkills for GUI, computer-use, visual-agent, OSWorld, Ubuntu desktop, macOS, Minecraft, or Mario tasks where reusable multimodal skill packages can guide planning, state recognition, or verification. Also use when installing, downloading, searching, or adapting MMSkills packages for Codex, OpenClaw, Claude Code, or other agent products.

Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead, FlashList, native modules, or debugging jank and frame drops.

Search for the requested text through VS Code's search UI or find widget, then replace only the intended value and verify the post-replacement state rather than stopping at an open search panel. Use this when the search surface itself matters: search panel, results tree, find widget, and replace verification. Do not collapse these flows into generic editor editing.

Create a new Thunderbird message, fill headers and body content, optionally format the body, and send it.

Create a chart on the requested destination sheet while honoring an exact chart title and chart family.

Apply sorts, auto-filters, and range filters to Calc tables and verify the visible filtered rows or ordering on the sheet.

Enter direct Calc formulas or wizard-selected functions in the correct target cell, verify the first result, and only then fill the intended range.

Open Writer's Find and Replace dialog, fill the search and replacement fields or replacement formatting, run the replacement, and verify the replace count or changed document state.

Use Writer's output surfaces to save a copy, confirm an export target such as PDF, or store the current document as a reusable template.

Use this skill when a user requests to create, modify, analyze, visualize, or work with spreadsheet files (`.xlsx`, `.xls`, `.csv`, `.tsv`) with formulas, formatting, charts, tables, and recalculation.

Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.

Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components.

Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components.

Save editable GIMP workfiles and preserve layered project state before handing off to export when needed.

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.

HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书 图文, or any kind of multi-slide pitch/report/sharing document that should look tasteful and be usable with keyboard navigation. Triggers include keywords like "presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "分享稿", "小红书图文", "talk slides", "pitch deck", "tech sharing", "technical presentation".

Insert a media object on the intended slide, optionally configure click behavior, and verify the requested result before leaving the slide.

Select the correct slide, use slide-level controls, and verify navigator or canvas changes before leaving the slide structure workflow.

HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书 图文, or any kind of multi-slide pitch/report/sharing document that should look tasteful and be usable with keyboard navigation. Triggers include keywords like "presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "分享稿", "小红书图文", "talk slides", "pitch deck", "tech sharing", "technical presentation".

Create, edit, render, verify, and export PowerPoint slide decks. Use when Codex needs to build or modify a deck, presentation deck, slide deck, slides, PowerPoint, PPT, or visually ambitious editable .pptx file.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, or generate or update marketplace entries for plugin ordering and availability metadata.