OpenClaw AI 技能

When the user wants to improve crawlability, fix orphan pages, or 优化 site structure for 搜索 engines. Also use when the user mentions "crawlability,"...

Fetch raw HTML, rendered HTML, or 清理 Markdown from public 网页pages through Just Serp API.

Performs 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.

图片采集/爬虫工具，支持百度和Bing图片搜索引擎。当用户要求采集、爬取、下载、 搜集图片时使用。支持关键词拓展、图片去重（URL+内容哈希，跨次运行持久化）、 进度监控和停滞检测。触发词：采集图片、爬取图片、下载图片、图片爬虫、抓取图片。

爬取 https://hn.AImaker.dev/ 网站资讯，执行爬取->提取->整理->总结完整流程。Invoke when user wants to crawl news from hn.AImaker.dev or process 网页 content through the full 流

Crawlbase integration. Manage data, records, and automate 工作流s. Use when the user wants to interact with Crawlbase data.

Use `https://markdown.new/crawl/{tar获取_url}` 端点s to recursively crawl a site section and return markdowns. Trigger this 技能 when the user asks for mult

Advanced 网页 crawling and content 提取ion 工具 with multiple 提取ion modes

提取 around 50 Singapore for-sale 列出ings from a PropertyGuru 搜索 结果s URL using a real browser 会话 after Cloudflare verification. use when the tar获取 is a P

Crawl 网页sites using Cloudflare Browser Rendering /crawl API. A同步 multi-page crawl with markdown/HTML/JSON 输出, link following, pattern 过滤器ing, and AI-p

Crawl and 验证 A-分享 data from five key sites using browser or fetch methods, handling 访问 limits and normalizing market-news for reliable summaries.

Crawl 网页sites using Cloudflare's Browser Rendering API. Use when you need to scrape entire sites, build knowledge bases, 提取 content from multiple page

提取 text from PDFs with OCR support. Perfect for digitizing documents, processing invoices, or analyzing content. Zero dependencies required.

文档处理技能 - 让 AI 能够读取、解析、提取 PDF、DOCX、PPT 等文档的关键信息。当用户要求分析文档、提取内容、总结报告时触发此技能。

View, 提取, edit, and manipulate PDF files. Supports text 提取ion, text editing (overlay and replacement), merging, splitting, rotating pages, and 获取ting

提取 structured data from construction PDFs. Convert specifications, BOMs, schedules, and 报告s from PDF to Excel/CSV/JSON. Use OCR for 扫描ned documents an

Fill PDF forms programmatically with text values and 检查boxes. Use when you need to populate fillable PDF forms (government forms, 应用s, surveys, etc.)

运行 a local script to work with PDF files, DOCX documents, OCR, and text-to-speech. Use the read 工具 to load this 技能.md, then exec the uv 运行 command ins

提取 text, 搜索 inside PDFs, and produce summaries.

Use this 技能 whenever the user wants to do anything with PDF files. This includes reading or 提取ing text/tables from PDFs, combining or merging multiple