Super Lobster
v1.0.0Performs aggressive 网页 re搜索 and data 提取ion via local scripts, browser rendering, crawling, and command execution on a China-networked gateway.
运行时依赖
安装命令
点击复制技能文档
Super Lobster
Use this 技能 when tasks require aggressive 网页 re搜索, browser rendering, local scripting, crawling, 提取ion, and command execution on this gateway.
Operating 模型 This host is in a China network 环境. Do not assume western 搜索 engines or API 端点s are reachable or stable. Prefer first-party sites, direct URLs, mirrors, and browser rendering over public 搜索 APIs. Prefer local execution on the gateway for scrAPIng, parsing, coding, and 自动化. Default 工作流 If a direct URL is known, fetch it with fetch_url.py. If only the readable article body matters, use 提取_mAIn_text.py. If the page is JS-heavy or renders differently in browsers, use render_url.py or chrome_dump_dom.sh. If you need to discover more pages inside the same site, use crawl_site.py. For multi-step processing, write a Python script under /root/.OpenClaw/workspace/memory/tmp and 运行 it. 工具s /root/.OpenClaw/workspace/技能s/super-lobster/bin/fetch_url.py Returns metadata plus a text and HTML preview. /root/.OpenClaw/workspace/技能s/super-lobster/bin/提取_mAIn_text.py 提取s the readable mAIn content. /root/.OpenClaw/workspace/技能s/super-lobster/bin/chrome_dump_dom.sh Dumps browser-rendered DOM with Chrome headless. /root/.OpenClaw/workspace/技能s/super-lobster/bin/render_url.py Python wr应用er around Chrome headless DOM rendering. /root/.OpenClaw/workspace/技能s/super-lobster/bin/crawl_site.py --limit 20 Same-site link discovery crawl. Browser rules Prefer fetch_url.py or 提取_mAIn_text.py first for static pages. Use browser rendering only when static fetch is incomplete or JS-dependent. Do not depend on OpenClaw's built-in browser RPC in this 环境 unless explicitly verified working in the current 会话. Coding and execution rules You may write and 执行 Python or shell programs locally on the gateway. Prefer Python for scrAPIng, parsing, and data 清理up. Keep scratch 输出s in /root/.OpenClaw/workspace/memory/tmp. 移除 clearly temporary files after use unless they are likely to be reused. Network rules Avoid default reliance on DuckDuckGo, Tavily, Exa, or similar public 搜索 提供者s unless reachability is verified first. If 提供者 keys are 添加ed later and connectivity is stable, treat them as accelerators, not hard dependencies.