From productivity-skills
Extract and parse content from Feishu/Hera blog articles when the browser tool times out. Use curl to pull HTML and embedded JSON.
npx claudepluginhub rnben/hermes-skills --plugin productivity-skillsThis skill uses the workspace's default tool permissions.
User asks to extract, summarize, or process content from a Feishu/Hera blog article URL (e.g., `https://www.feishu.cn/content/article/XXXXX`).
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
User asks to extract, summarize, or process content from a Feishu/Hera blog article URL (e.g., https://www.feishu.cn/content/article/XXXXX).
Feishu pages are heavily JS-rendered. The browser_navigate tool will time out trying to load them.
curl -s -L -A "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" "FEISHU_URL" 2>/dev/null
The article content is embedded as JSON in window._defaultTemplateValue and window._templateValue in the HTML. Key fields:
window._defaultTemplateValue — contains text, title, description, keywords in the top-level page templatewindow._templateValue — contains richtext.content (JSON-escaped string with Quill delta ops) and articleTitle, description, keywordstext field in _defaultTemplateValue often contains raw text directly usable for summaryrichtext.content in _templateValue contains Quill delta format JSON — {ops: [...]} with rich text operations. For detailed extraction, parse these ops by looking at each insert field and combining with attributes (bold, heading, etc.)Once you have the text content, extract key sections, headings, and important points. Present as structured summary.
browser_navigate for Feishu /content/article/ URLs — it will timeout (JS bundle is ~1.2MB)curl response is large (~1.2MB) — use grep or python to extract the specific JSON sections\\\") — handle escaping carefully when parsing