OpenClaw AI 技能

Interactive 工作流 structuring 助手 that 图形界面des users step-by-step to 转换 vague process descriptions into structured, executable 工作流 docume...

Forgejo via fj and REST API for repos, issues, PRs, wiki, CI, and reviews.

Plan-first 工作流 for non-trivial work: plan with done criteria, 创建 a 追踪ing issue, package 上下文 as documents on the issue, decide where code live...

通用内容创作工作流：选题策划→主编审核→文案创作→主编审核，产出平台无关的Markdown定稿。触发词：写文章、内容创作、选题创作、启动创作流程。需先安装 content-creation。

Schedule and 运行 safe dAIly/weekly 更新s for Clawd机器人 + 安装ed 技能s using the Gateway cron 调度器. Use when 设置ting up "运行 更新s at 04:00" jobs, rotating 更新 报告s,

Automatically converts raw long conversations into structured, themed Markdown knowledge cards with source 追踪ability, 运行ning incrementally and silentl

Convert Markdown content to images automatically with GitHub styling, full Chinese support, smart pagination, emoji support, and syntax highlighting.

基于 AST 和 LLM 自动生成 Python 代码文档（Google Style docstring）。 自动分析代码结构，生成符合 Google Style 的 docstring。

Automatically 发送 files from workspace to Feishu/Lark when files are 生成d or 更新d. Use when: (1) User 创建s new documents and wants them delivered...

Auto-生成 document 索引 tables (ADR, RFC, Pitfall, etc.) from file frontmatter. In real-world 测试, hand-mAIntAIned 索引es had a 62% error rate — ti...

转换 unstructured 命令行工具nical 输入 (dictation, transcripts, or rough notes) into standardized SOAP (Subjective, Objective, Assessment, Plan) medical docume

浏览器自动化+数据采集框架。支持Playwright控制、DdddOcr验证码识别、东方财富/雪球/AK分享金融数据采集。反爬对抗、UA池、代理。

Scrape documents from Notion, Doc发送, PDFs, and other sources into local PDF files. Use when the user needs to 下载, 归档, or convert 网页 documents to PDF 格

Stealth 网页 抓取器. Give it any URL and it punches through Cloudflare, 机器人 检测ion, and WAFs automatically using a 3-tier cascade (plAIn HTTP → TLS spoof →

A Docker-based 工具 using Crawlee and Playwright to deeply scrape complex sites like YouTube, 提取ing verified raw transcripts or descriptions with ads re

网页 scrAPIng, 搜索, crawling, and site m应用ing via the AnyCrawl 命令行工具. Use when the user wants to 搜索 the 网页, scrape a page, find URLs on a site, or bulk 提

读取Confluence需求文档并整理成指定格式。采集原则是"忠实记录"，而非"需求分析"。输出包括：{序号}_{标题}.md（每个页面一个Markdown文件）、requirement-meta.md（元信息）、images/（所有图片，文件中包含图片引用）。

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

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

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