article▌

获取、解析并保存微信公众号文章，支持单篇和批量下载、元数据提取、图片下载和 Markdown 转换。

Automated WeChat article writing workflow with research, drafting, headline generation, and formatting optimization. \n \n Four-step pipeline: web research across multiple sources, article composition (1000–1500 words), generation of five viral-optimized headlines, and layout recommendations \n Reads user's CLAUDE.md file to match writing style, tone, and signature closing; structures content with emotional storytelling, problem-solution-summary flow \n Headline generation focuses on pain points

\n First, divide the article into sections based on its headings. Think about the main points you want to make during those sections. \n \n Consider that information is a directed acyclic graph, and that pieces of information can depend on other pieces of information. Make sure that the order of the sections and their contents respects these dependencies. \n Confirm the sections with the user. \n \n For each section: \n \n 2a. Rewrite the section to improve clarity, coherence, and flow. Use maxi

Craft distinctive long-form content that matches a specific voice or brand style, not generic AI output. \n \n Captures and applies existing voice patterns from articles, newsletters, or style guides to maintain consistency across blog posts, guides, tutorials, and launch announcements \n Enforces concrete-first writing: leads with examples, screenshots, code, or data before explanation, avoiding generic openings and filler transitions \n Bans hype language and unsourced claims; requires factual

Publish Markdown or HTML articles to WeChat Official Account drafts via API. \n \n Supports both Markdown and HTML file formats with automatic conversion; HTML preserves original formatting \n Two article types available: standard news format and image-focused newspic (小绿书) mode \n Requires WECHAT_API_KEY environment variable and authorized WeChat account on wx.limyai.com \n Publishes to drafts only (user manually publishes in WeChat admin panel); includes account listing and error handling for

Parse WeChat Official Account articles to extract metadata, content, and account information. \n \n Extracts article metadata (title, author, publish time, cover image) and account info (name, avatar, alias) from WeChat URLs and HTML \n Supports multiple article types: posts, videos, images, voice messages, text, and reposts \n Configurable extraction options for content, raw metadata, repost info, embedded links, and tags \n Handles error cases including deleted content, expired links, rate lim

X Article Publisher Skill \n Overview \n Publish articles to X/Twitter \n When to Use This Skill \n Use this skill when you need to work with publish articles to x/twitter. \n Instructions \n This skill provides guidance and patterns for publish articles to x/twitter. \n For more information, see the source repository .

This skill extracts the main content from web articles and blog posts, removing navigation, ads, newsletter signups, and other clutter. Saves clean, readable text.

Guides structure, SEO, and UX for individual article pages — layout, metadata, schema, technical. For article body content (intro, body, conclusion, writing), see article-content. Distinct from blog-page-generator, which covers the blog index/listing page.

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.