AI-Prompts

Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG. Trigger on: "画图" "帮我画" "生成图" "做个图" "架构图" "流程图" "可视化一下" "出图" "generate diagram" "draw diagram" "visualize" or any system/flow description the user wants illustrated.

专为 Seedance 2.0 生成视频提示词。适用场景：有参考素材（图片/视频/音频）进行复刻、编辑、延长或基于素材生成新视频，或纯文本15秒内简短视频生成。当用户提到「生成视频提示词」「Seedance」「seedance」「即梦」「即梦平台」「视频提示词」「视频生成」「AI视频」「广告视频」「视频延长」「视频编辑」「动漫视频」「科幻视频」「电影特效」「商业广告」「品牌宣传」或讨论视频prompt工程、AI视频工作流时，务必使用此技能。

将任何剧本或想法生成多段 Seedance 2.0 分镜提示词，专为长视频（超过15秒）设计。支持全能参考和首尾帧两种生成模式，确保多段视频之间角色一致性和叙事连续性。当用户想要生成长视频、制作多段分镜、创作故事短片，或在 Seedance/即梦/剪映 AI 视频平台制作有连贯叙事的视频时调用此技能。

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 10 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".

Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.

AI image generation with OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links. Use when user asks for "markdown to html", "convert md to html", "md转html", "微信外链转底部引用", or needs styled HTML output from markdown.

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "贴图/图文/文章".

Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, uses an upgraded Defuddle pipeline with better web-component handling and YouTube transcript extraction, and automatically falls back to the pre-Defuddle HTML-to-Markdown pipeline when needed. If local browser capture fails entirely, it can fall back to the hosted defuddle.md API. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.

A professional Sudoku coach that generates valid puzzles (3-6 grid sizes) with adjustable difficulty (1-5 stars) and provides printable card prompts.

Generate comprehensive video script storyboards from a script or specific scenes. Use this skill when the user provides story content, a script, or a screenplay and requests a storyboard, shot list, or AI image generation prompts for a video.

Generate beautiful English vocabulary learning cards (英语单词信息图卡片) based on movie/anime/TV show themes. Supports multiple visual styles including watercolor (水彩手绘), 3D clay (3D软陶), crayon doodle (蜡笔涂鸦), and anime styles. Use when the user wants to create English vocabulary cards for a specific movie or anime, generate word learning images based on a TV show theme, select a visual style for vocabulary card generation, or add new visual styles to the card generator.

短剧剧本转AI视频提示词生成器。将用户上传的短剧剧本文档智能拆解为可直接用于AI视频生成的完整提示词体系。输出包括：角色设定提示词、场景设定提示词、逐镜头分镜提示词。支持批量处理、多格式导出、一致性校验。当用户说"剧本转视频提示词"、"拆解剧本生成分镜"、"短剧转AI视频"、"批量生成分镜提示词"、"剧本可视化"时触发。

Generate complete video production packages including hooks, voiceover scripts, storyboard shot lists, on-screen text overlays, and thumbnail prompts. Use when users need to create short-form or long-form video content plans, generate AI video/image generation prompts for each shot, or produce structured storyboards for video production. Triggers on requests like "generate a video script", "create a storyboard", "plan a short video about X", or any video content creation task.

卡尔数学思维出题教练。为5-12岁（幼儿园中班到小学六年级）儿童生成趣味数学思维训练题。每次生成一道题目（含答案解析），并可输出适合A4打印的图片生成Prompt。当用户提到以下场景时使用本技能：(1) 需要给孩子出一道数学思维题, (2) 需要生成儿童逻辑训练/数学启蒙题目, (3) 提到"卡尔数学"、"思维训练"、"逻辑题"等关键词, (4) 需要生成可打印的儿童数学题图片。

Recommend suitable prompts from 6000+ Nano Banana Pro image generation prompts based on user needs. Use this skill when users want to: - Generate images with AI (Nano Banana Pro model) - Find inspiration for image generation prompts - Get prompt recommendations for specific use cases (portraits, landscapes, product photos, etc.) - Create illustrations for articles, videos, podcasts, or other content - Translate and understand prompt techniques

Creates and updates Excalidraw diagrams representing application architecture by analyzing codebases, identifying components, services, and their relationships. Use when users request architecture visualization, system diagrams, or need to document application structure visually.

Package skills into web-compatible bundles. Converts any skill directory into a single .txt file containing all resources, making it usable in web-based AI chatbots. Validates skill structure and warns about script compatibility. Triggers when user mentions "skill-web-bundle", "打包skill", "web bundle", or wants to create web bundles of skills for external use.

List all available skills configured in AGENTS.md. Scan and display skills with their names, descriptions, and trigger commands. Triggers when user mentions "列出技能", "list skills", "可用技能", "show skills", "技能列表", or uses command /skill-list.