skills/wechat-mp-scraper/SKILL.md
抓取和拆解微信公众号文章页。只要用户提到“微信公众号网页”“公众号文章”“mp.weixin.qq.com/s/”“抓 HTML”“导出素材”“分析公众号动画/实现方式/图片资源”这类场景,就应该使用这个 skill。它适用于公开可访问的公众号文章页,负责抓原始 HTML、提取资源、下载素材、整理动画线索,并生成结构化报告。
npx skillsauth add shuliuzhenhua-sys/shuliu-skills wechat-mp-scraperInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Important: All scripts and references are located inside this skill directory.
Agent Execution Instructions:
SKILL.md file's directory path as SKILL_DIR${SKILL_DIR}/scripts/scrape_wechat_mp.py${SKILL_DIR}/references/output-format.md${SKILL_DIR} placeholders in this document with the actual installed path这个 skill 用于处理 公开可访问 的微信公众号文章页,不支持登录态页面、受限内容或需要账号权限的场景。
它不只是做分析,也负责把正文内容完整抓下来。
当用户要做下面任一事情时,直接使用本 skill:
mp.weixin.qq.com/s/... 链接生成报告content.md、content.json、report.md、urls.json 和 snippets/。优先直接调用脚本:
python3 ${SKILL_DIR}/scripts/scrape_wechat_mp.py "<文章链接>" --output-dir "<输出目录>"
如果用户没给输出目录,默认建议放到:
~/wechat-mp-scraper-runs
脚本会生成如下内容:
<output-dir>/<slug>/
├── article.html
├── content.md
├── content.json
├── report.md
├── urls.json
├── assets/
│ ├── 001.png
│ ├── 002.jpg
│ └── ...
└── snippets/
├── animation-snippets.txt
└── matched-blocks.html
需要解释实现方式时,重点看:
content.mdcontent.jsonurls.jsonsnippets/animation-snippets.txtsnippets/matched-blocks.html如果用户问“这段动画怎么做的”,优先回答:
opacity、transform、@keyframes、<animate> 还是轮播切换不要泛泛而谈“可能是 JS 动画”,要尽量引用抓到的具体片段和素材路径。
如果需要了解输出字段,读取:
${SKILL_DIR}/references/output-format.md
content-media
小红书创作平台“文字配图”自动化技能。用户只要提到小红书创作平台、文字配图、科技主题、换配色、9444 端口、CDP、自动生成图片、自动下载图片、基于已有预览图换主题/换颜色,或者想先看看各个主题长什么样子,都应该使用这个技能。它会连接已登录的浏览器会话,生成图片,默认下载当前图片,支持继续切主题或换配色,也支持直接给出已经整理好的主题预览总览图和单张样例。
development
Generate videos using Sora via lnapi.com.
data-ai
Generate images via geekai.co image endpoints. Use when the user wants text-to-image generation through GeekAI, needs to choose between nano-banana-2 and gemini-3-pro-image-preview, or wants batch image generation with aspect ratio and size control.
development
Use when 用户提到“飞书授权”“OAuth”“Device Flow”“open_id”“重复弹授权窗”“复用 token”“补授权 scope”“飞书 token 存哪儿了”这类场景,需要复用本地已有用户 token、只补缺失 scopes,或排查 token 的实际存储位置。