jimliu/baoyu-skills
22 skills531k installs533k starsGitHub
Install
npx skills add https://github.com/jimliu/baoyu-skillsSkills in this repo
1Baoyu Post To WechatSkill for posting content to WeChat Official Accounts (微信公众号) via API, Chrome browser automation, or remote API methods. Supports markdown, HTML, and plain text input with automatic metadata generation. Includes image-text posting (贴图/图文), multi-account management, and flexible theme/color customization.32kinstalls2Baoyu Image GenAI image generation skill supporting OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, and Replicate APIs. Handles text-to-image, reference images, aspect ratios, and batch generation from saved prompt files.30.4kinstalls3Baoyu Markdown To HtmlConverts 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. --- name: baoyu-markdown-to-html description: 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. version: 1.56.1 metadata: openclaw: homepage: https://github.com/JimLiu/baoyu-skills#baoyu-markdown-to-html requires: anyBins: - bun - npx --- # Markdown to HTML Converter Converts Markdown files to beautifully styled HTML with inline CSS, optimized for WeChat Official Account and other platforms. ## User Input Tools When this skill prompts the user, follow this tool-selection rule (priority order): 1.29.7kinstalls4Baoyu InfographicThis skill applies instructional design principles to infographic creation. It guides analysis of source material, identifies learning objectives, classifies content type, and matches it to optimal layouts and styles. Use it before creating infographics to ensure clarity and effectiveness.29.6kinstalls5Baoyu Cover ImageThis skill generates elegant cover images for articles with fine-grained customization across dimensions like color, rendering style, and mood. It works with Codex imagegen, Codex CLI, or other backend image services. Use it when you need to produce consistent, branded cover images at scale.29.3kinstalls6Baoyu Article Illustratorbaoyu-article-illustrator converts technical articles, specifications, or documentation into hand-drawn cartoon-style 16:9 infographic illustrations. Developers use it to turn complex written concepts into approachable visual summaries that readers can scan quickly. The output maintains a consistent mono-ink aesthetic with semantic accent colors, keeping information hierarchy clear while forcing all text into hand-drawn lettering style.29.1kinstalls7Baoyu Xhs ImagesGenerates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when user mentions "小红书图片", "小红书种草", "小绿书", "微信图文", "微信贴图", "image cards", "图片卡片", baoyu-xhs-images, or wants social media infographic series. --- name: baoyu-xhs-images description: Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when user mentions "小红书图片", "小红书种草", "小绿书", "微信图文", "微信贴图", "image cards", "图片卡片", baoyu-xhs-images, or wants social media infographic series. version: 2.0.1 metadata: openclaw: homepage: https://github.com/JimLiu/baoyu-skills#baoyu-xhs-images --- # Image Card Series Generator Break down complex content into eye-catching image card series with multiple style options. ## User Input Tools When this skill prompts the user, follow this tool-selection rule (priority order): 1.28.7kinstalls8Baoyu Slide Deckbaoyu-slide-deck transforms source content into slide decks designed for reading and social sharing rather than live presentations. It builds a message hierarchy with a core takeaway, 3-5 supporting points, and actionable call-to-action, tailored per audience type. Developers use it to structure presentations efficiently before creating any design assets.28.4kinstalls9Baoyu Url To MarkdownBaoyu URL to Markdown is a utility skill that converts URLs to markdown format. Developers use it to extract content from web pages and convert to structured markdown for documentation or content processing. It simplifies web content capture for knowledge bases and reference docs.27.9kinstalls10Baoyu ComicKnowledge Comic Creator generates original educational comics from topics or source materials. Use when user asks to create knowledge comics, tutorial comics, biography comics, or Logicomix-style visual narratives with flexible art style and tone combinations.27.3kinstalls11Baoyu Post To XPost to X publishes content and articles to X via real Chrome browser. Use when user asks to post to X, tweet, or publish long-form articles. Supports three execution modes - Codex Chrome plugin, Chrome Computer Use, or CDP script - with automatic mode selection.26.7kinstalls12Baoyu Compress Imagebaoyu-compress-image is a terminal skill that compresses images in a file or folder to WebP, PNG, or JPEG using whichever local compressor is available. It auto-selects among sips, cwebp, ImageMagick, and Sharp, and supports quality control, recursive traversal, keep-original, and JSON output. A developer runs it before deploy to shrink public/ or asset directories. It reports input size, output size, and reduction ratio per file.25.9kinstalls13Baoyu Danger X To MarkdownConverts X (Twitter) tweets and articles to markdown with YAML front matter. Uses reverse-engineered API requiring user consent. Use when user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion. --- name: baoyu-danger-x-to-markdown description: Converts X (Twitter) tweets and articles to markdown with YAML front matter. Uses reverse-engineered API requiring user consent. Use when user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion. version: 1.117.3 metadata: openclaw: homepage: https://github.com/JimLiu/baoyu-skills#baoyu-danger-x-to-markdown requires: anyBins: - bun - npx --- # X to Markdown Converts X content to markdown: - Tweets/threads → Markdown with YAML front matter - X Articles → Full content extraction ## User Input Tools When this skill prompts the user, follow this tool-selection rule (priority order): 1. **Prefer built-in user-input tools** exposed by the current agent runtime - e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.25.9kinstalls14Baoyu Danger Gemini WebInteracts with Gemini Web to generate text and images. Supports text generation from prompts and image generation with aspect ratio and quality controls. Requires Gemini API credentials.25.8kinstalls15Baoyu Format MarkdownFormats 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. --- name: baoyu-format-markdown description: 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. version: 1.57.0 metadata: openclaw: homepage: https://github.com/JimLiu/baoyu-skills#baoyu-format-markdown requires: anyBins: - bun - npx --- # Markdown Formatter Transforms plain text or markdown into well-structured, reader-friendly markdown. The goal is to help readers quickly grasp key points, highlights, and structure - without changing any original content. **Core principle**: Only adjust formatting and fix obvious typos. Never add, delete, or rewrite content. ## User Input Tools When this skill prompts the user, follow this tool-selection rule (priority order): 1.25.7kinstalls16Release SkillsUniversal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, GitHub Releases, annotated tags, historical release backfill, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送", "release notes", "GitHub Release", or "回填 Release". --- name: release-skills description: Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, GitHub Releases, annotated tags, historical release backfill, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送", "release notes", "GitHub Release", or "回填 Release". --- # Release Skills Universal release workflow supporting any project type with multi-language changelog. ## User Input Tools When this skill prompts the user, follow this tool-selection rule (priority order): 1. **Prefer built-in user-input tools** exposed by the current agent runtime - e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the ch.23.4kinstalls17Baoyu Translate>- --- name: baoyu-translate description: >- This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化", "refined translation", "精细翻译", "proofread translation", "快速翻译", "快翻", "这篇文章翻译一下", or provides a URL/file with translation intent. Supports three modes (quick/normal/refined) with custom glossary support. version: 1.59.0 metadata: openclaw: homepage: https://github.com/JimLiu/baoyu-skills#baoyu-translate requires: anyBins: - bun - npx --- # Translator Three-mode translation skill: **quick** for direct translation, **normal** for analysis-informed translation, **refined** for full publication-quality workflow with review and polish. ## User Input Tools When this skill prompts the user, follow this tool-selection rule (priority order): 1. **Prefer built-in user-input tools** exposed by the current agent runtime - e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each questi.22.6kinstalls18Baoyu Post To Weibobaoyu-post-to-weibo is a skill that posts content to Weibo using Chrome browser automation. Software engineers use it to publish text, images, videos, and long-form articles to Weibo without bot detection. It supports both regular feed posts and headline article publishing with Markdown input.19.5kinstalls19Baoyu Youtube TranscriptDownloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面", "视频封面", "video thumbnail", "video cover image", or provides a YouTube URL and wants t --- name: baoyu-youtube-transcript description: Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面", "视频封面", "video thumbnail", "video cover image", or provides a YouTube URL and wants the transcript/subtitle text or cover image extracted. version: 1.1.0 metadata: openclaw: homepage: https://github.com/JimLiu/baoyu-skills#baoyu-youtube-transcript requires: anyBins: - bun - npx --- # YouTube Transcript Downloads transcripts (subtitles/captions) from YouTube videos.18kinstalls20Baoyu DiagramBaoyu-diagram creates publication-ready SVG diagrams across nine types: architecture, flowchart, sequence, structural, mind map, timeline, illustrative, state machine, and data flow. Developers invoke it when visualizing system components, process logic, interactions, or conceptual structures. The tool outputs a single self-contained .svg file with embedded styling (dark theme, semantic color palette, JetBrains Mono typography) and optional @2x PNG conversion via bundled script. Reference files guide layout algorithms per diagram type; strict spacing rules and component patterns prevent overlaps and ensure professional appearance.12.3kinstalls21Baoyu Wechat SummarySummarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks t --- name: baoyu-wechat-summary description: Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles".7.6kinstalls22Baoyu Electron Extractbaoyu-electron-extract unpacks installed Electron desktop applications by extracting app.asar bundles and rebuilding readable source when embedded JavaScript source maps exist. A Bun or npx-driven script discovers macOS and Windows installs, unpacks ASAR archives, restores original file trees from sourcesContent in .js.map files, and runs Prettier on minified JavaScript when maps are missing or external-only. It skips node_modules, copies app.asar.unpacked native assets, emits extract-report.json with counts and warnings, and writes to ~/Downloads/<AppName>-electron-extract/ by default. Users invoke it to extract Electron apps, decompile bundles, inspect how Codex, Cursor, Discord, VS Code, or ChatGPT desktop clients are built, or pass absolute .app, install directory, or .asar paths. Dry-run previews discovery, --force overwrites populated output, and --json returns machine-readable summaries. Readable restored paths collapse bundler-relative segments like ../../src/main.ts into restored/src/main.ts instead of hashed placeholders.5.6kinstalls