mage-skills-lab
mage-skills-lab contains 8 collected skills from jaydenxiao2016, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
RSS digest (90 Karpathy blogs) + AI filter → dedicated HTML (no .md, no mage-md-to-html). Zero-context: node scripts/run-full-daily.mjs in SKILL_DIR (24h + WeChat draft + email). Flags: --week (72h), YYYYMMDD. Triggers: daily digest, /digest, 今日精选, RSS digest, 公众号简报, mage-ai-daily-digest.
Runs an end-to-end article production pipeline: topic framing, source gathering, markdown drafting, Humanizer-zh rewriting, cover generation, article illustrations, watermarking, WeChat HTML conversion, WeChat draft publishing, Feishu archival, and review notification. Use when users ask to automate blog writing, auto-produce公众号文章, or build a full article workflow.
AI image generation with OpenAI, Google, DashScope, and Seedream APIs. Supports text-to-image, reference images, aspect ratios, provider selection, and reusable preferences. Sequential by default; parallel generation available on request. Use when user asks to generate, create, draw, render, or iterate on images.
Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, and infographics. Use when user asks for "markdown to html", "convert md to html", "md转html", or needs styled HTML output from markdown.
Publishes content to WeChat Official Account (微信公众号) through API or browser automation. Supports article publishing with HTML, markdown, or plain text input, and image-text posting with multiple images. Use when the user asks to 发布公众号、发微信公众号文章、发贴图/图文、post to wechat, or send WeChat Official Account content.
Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts through a guided workflow: preferences, analysis, two confirmations, outline variants, and sequential image generation. Use when user asks for "小红书图片", "XHS images", "RedNote infographics", knowledge-card carousels, tutorial slides, save-worthy checklists, or multi-image social graphics for Chinese platforms.
Analyzes article structure, identifies the positions that truly need visuals, and generates article illustrations with a Type × Style workflow. Use when users ask to illustrate an article, add images into article sections, generate visuals for an article, or 为文章配图.
Generates article cover images with 6 design dimensions, 9 color palettes, 6 rendering styles, optional references, and flexible aspect ratios. Use when users ask to generate a cover image, article cover, hero image, visual header, or cover artwork.