@jimliu

baoyu-url-to-markdown fetches urls via chrome cdp with site-specific adapters (x, youtube, hn) and converts to markdown. handles login and captcha via interaction modes, media download, and output path generation. requires first-time setup of media and output preferences.

baoyu-format-markdown transforms plain text and markdown into well-structured, reader-friendly documents by analyzing content, optimizing headings and formatting, and applying typography fixes via bundled scripts.

baoyu-post-to-weibo automates weibo content publishing via chrome cdp, supporting text, images, videos, and markdown articles. user reviews content in browser before manual publication.

baoyu-diagram generates dark-themed svg diagrams across nine types (architecture, flowchart, sequence, structural, mind map, timeline, illustrative, state machine, data flow). outputs are self-contained svg files with embedded styling and responsive scaling.

baoyu-post-to-weibo publishes text, images, videos, and markdown articles to weibo via chrome cdp. supports both regular posts and long-form headline articles with manual review before publishing.

extracts youtube transcripts in multiple formats and languages, with intelligent caching and fallback mechanisms when direct api access is blocked.

baoyu-post-to-x publishes text, images, videos, and markdown articles to x via chrome in three modes: codex plugin, computer use, or cdp fallback. mode selection is explicit and required before execution.

baoyu-compress-image converts images to webp or png using available system tools (sips, cwebp, imagemagick, sharp). supports batch processing, quality tuning, and configurable output paths via cli flags and extend.md.

baoyu-danger-gemini-web wraps a reverse-engineered gemini web api for text and image generation with multi-turn conversation support. requires browser-based auth and explicit user consent before first use.

baoyu-compress-image converts images to webp or png by selecting the best available compression tool on the system. supports batch processing, quality control, and extensible preferences via external config files.

baoyu-slide-deck generates professional slide deck images from user-supplied content, optimizing for readability and social-media sharing rather than live presentation. requires outline creation with style instructions, then delegates individual slide rendering to image generation backends.

baoyu-format-markdown restructures plain text and markdown files with strategic formatting (headings, bold, lists, tables) while preserving original content. generates or optimizes frontmatter and runs typography scripts for spacing and emphasis fixes.

baoyu-wechat-summary extracts structured digests from wechat group chats via wx-cli, maintaining cross-session history and user profiles, with heavy reliance on external references for procedural detail.

baoyu-comic generates educational comics with configurable art styles and tones, supporting batch workflows and partial edits. includes preset shortcuts for tutorials, martial arts, and romance genres with automatic storyboard generation.

baoyu-article-illustrator identifies visual aid opportunities within article content and generates contextual illustrations by composing type (infographic, flowchart, timeline, etc) with style choices. supports batch and granular control via flags.

baoyu-image-gen covers multi-provider ai image generation with text-to-image, reference images, batch processing, and quality presets across openai, google, openrouter, dashscope, jimeng, seedream, and replicate.

baoyu-translate offers three translation modes (quick, normal, refined) with markdown-aware chunking and glossary enforcement, but lacks concrete procedural steps and failure handling details.

baoyu-diagram generates dark-themed svg diagrams in nine types (architecture, flowchart, sequence, structural, mind map, timeline, illustrative, state machine, data flow). produces self-contained files with embedded styling. lacks actionable procedure detail and error handling guidance.

baoyu-post-to-x publishes text, images, videos, and long-form markdown articles to x via browser automation. implementation path selection (codex chrome, computer use, cdp) is documented but procedural steps remain incomplete.

baoyu-post-to-wechat covers posting articles to wechat official accounts via api or chrome cdp. the provided fragment addresses only user input tooling and runtime conventions, omitting the core skill logic entirely.

baoyu-image-cards generates cartoon infographic series across 12 styles and 8 layouts, with detailed configuration options for presets, palettes, and batch generation. the documentation covers tool integration, confirmation flows, and reference image handling but lacks actionable step-by-step procedures and failure mode guidance.

baoyu-design wraps a design methodology for producing self-contained html artifacts. it delegates to per-harness tool references and a system prompt but lacks concrete procedural steps, trigger examples, and failure handling.

baoyu-xhs-images generates cartoon infographics for xiaohongshu via style/layout combinations and preset bundles. content auto-detection and reference anchoring maintain consistency across multi-card series, but procedures lack clarity and edge case handling is absent.

skill generates infographic image cards with configurable styles and layouts, but lacks concrete implementation details, failure handling, and actionable steps for execution.

Extracts resources and JavaScript from any installed Electron app (`.asar` bundle), restoring original sources from `.js.map` files when available or…

AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs.…

Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, GitHub Releases, annotated tags,…

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input,…

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…

Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts,…

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic…

Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates…

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, Mermaid (rendered to PNG via headless Chrome), PlantUML,…

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...

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, Mermaid (rendered to PNG via headless Chrome), PlantUML, fo...

Extracts resources and JavaScript from any installed Electron app (`.asar` bundle), restoring original sources from `.js.map` files when available or formatt...

AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Suppo...

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identifica...