Skills by jimliu

This skill automates posting to X by launching a real Chrome instance and running local scripts. It executes local commands (e.g., `npx -y bun`), interacts with `https://x.com`, and uses persistent profiles like `~/.local/share/x-browser-profile` and env vars such as `X_BROWSER_CHROME_PATH`.

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.

This skill posts articles to WeChat Official Accounts via API or browser automation. It reads and stores `WECHAT_APP_ID`/`WECHAT_APP_SECRET` in `.baoyu-skills/.env`, spawns subprocesses (e.g. `npx`, `osascript`, `xdotool`) and makes requests to `https://api.weixin.qq.com` and other external endpoints.

Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 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".

This skill converts X (Twitter) tweets and articles to Markdown and can download media, saving prefs to `~/.baoyu-skills/…/EXTEND.md` and `consent.json`. It launches Chrome (`spawn(chrome, args)`), reads `X_AUTH_TOKEN`/`X_CT0` and other env vars, and issues requests to `https://x.com` and `https://abs.twimg.com`.

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

Provides CLI image generation using `scripts/main.ts`, calling external APIs (`https://api.openai.com/v1`, `https://generativelanguage.googleapis.com`, `https://dashscope.aliyuncs.com`). It reads API keys from env vars like `OPENAI_API_KEY`/`GOOGLE_API_KEY`, loads `<cwd>/.baoyu-skills/.env` and `~/.baoyu-skills/.env`, and includes shell usage examples (`npx -y bun ...`).

Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送".

This skill is a Gemini Web client that generates text and images via a reverse‑engineered Gemini Web API. It spawns Chrome (`child_process.spawn`), reads and writes cookie/session files (`~/Library/Application Support/baoyu-skills/gemini-web/consent.json`, `sessions/<id>.json`, `cookies.json`) and calls `https://gemini.google.com` and related Google endpoints.

Generates professional infographics with 20 layout types and 17 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", or "可视化".

This skill converts webpages to markdown by launching Chrome via CDP and saving output to `url-to-markdown/<domain>/<slug>.md`. It spawns Chrome (`spawn`), connects to `http://127.0.0.1:${port}/json/version` and opens arbitrary `<url>`, and reads config env vars `URL_CHROME_PATH`, `URL_DATA_DIR`, `URL_CHROME_PROFILE_DIR`.

Converts Markdown to styled HTML (WeChat-compatible) and includes scripts to render themes, code highlighting, PlantUML, and image handling. It executes CLI commands (`npx -y bun ...` / `spawnSync('npx', args)`), reads env vars like `MD_THEME_CONFIG_PATH`/`MD_THEME_DIR`, and fetches remote resources (e.g., `https://cdn-doocs.oss-cn-shenzhen.aliyuncs.com/npm/highlightjs/${HLJS_VERSION}`, `https://www.plantuml.com/plantuml`).

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.