菜单
Extract WeChat (mp.weixin.qq.com) articles to Markdown with images, headings, lists, and formatting preserved.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Integration testing for AI Agent CLI systems — PTY-driven conversation simulation, tool chain verification, OpenSpec-driven test design, and real-API validation.
Extract web article content from WeChat MP, blogs, and other platforms, converting text, images, formatting, and tables to clean Markdown.
Configure, extend, or contribute to Hermes Agent.
Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
| name | wechat-article-extraction |
| category | research |
| description | Extract WeChat (mp.weixin.qq.com) articles to Markdown with images, headings, lists, and formatting preserved. |
| trigger | Extract content from WeChat (微信公众号/mp.weixin.qq.com) articles, convert to Markdown, preserve images and formatting. |
Extract articles from mp.weixin.qq.com/s/<id> and convert to clean Markdown with images, headings, lists, and tables preserved.
curl -s -L -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" "https://mp.weixin.qq.com/s/<article_id>" > /tmp/wechat_article.html
Extract article content using Python + BeautifulSoup (run via terminal with conda Python, NOT execute_code sandbox):
id="js_content" div<img> with data-src), and styled <section> elementsfont-weight: bold or font-size: 16px+ inline styles**bold**, *italic*, lists, blockquotes to Markdownstyle="url(...)" declarationsalt text as Markdown image alt attributesImage placement: Process images in document order — each <img> is placed at its natural position relative to surrounding text, NOT batched at the top.
Cleanup: Remove JavaScript artifacts (var first_sceen__time, etc.), stray UI text (预览时标签不可点), and excessive blank lines.
zse-ck anti-bot blocks all non-browser requests. Workaround: ask user to provide content manually, or search cached/mirrored versions.<section> > <figure> > <span> > <img>. Must recurse into sections and handle <img> before recursing into text children.font-weight, font-size) rather than <h1>-<h6> tags. Must check style attributes, not just tag names.bs4 (BeautifulSoup) is NOT available in the execute_code sandbox. Use terminal with conda-activated Python instead.references/vocabulary-glossary-guide.md — How to create plain-language glossaries for technical articlesreferences/hermes-context-explanation-guide.md — How to explain abstract concepts using the user's own project as analogy