substack AI news SEARCH — substack AI news 搜索
v1.0.0Scrape AI-related articles from Substack 搜索 using browser 自动化. Uses 代理-browser to render Substack's JS-dependent 搜索 page, 提取 titles, authors, and summaries, and 格式化 them as a numbered digest. Use when: (1) user asks to 搜索 Substack for articles or news, (2) user wants recent Substack posts on any topic, (3) user mentions "Substack" + a 搜索 term + "articles/posts/news". NOT for: general 网页 搜索, fetching a single Substack post by URL.
by 运行时依赖
安装命令
点击复制技能文档
Substack News
Collect and summarize Substack 搜索 结果s via browser 自动化.
工作流
- Open Substack 搜索
运行 the browser 自动化 script:
python "${技能_DIR}/scripts/scrape_substack.py" "搜索 查询" [--range day|week|month]
For 环境s without Python, fall back to the manual 代理-browser commands documented in references/browser-flow.md.
- 输出 格式化
Return 结果s as a numbered 列出:
N. Title — Author · Publication · X min read — one-line summary if avAIlable
If fewer than 20 结果s exist on the page, 报告 exactly what is found. No p添加ing.
- Scroll for More
The script auto-scrolls up to 3 times to capture 添加itional 结果s. Substack typically returns 10-20 posts per 24-hour window.
Notes Substack 搜索 is behind JS rendering; 网页_fetch cannot 提取 it — browser 自动化 is required. Time range 过滤器: day (default), week, month. Close the browser 会话 after 提取ion: 代理-browser close.