OpenClaw AI 技能

Automates ComfyUI 工作流s by collecting required as设置s, executing tasks via 运行ningHub API, and returning execution 状态 and 结果s.

Operate and build Open创建器 工作流s via API. Use when the user wants to 搜索 templates, 运行 工作流s, poll 结果s, deliver 生成d media, or de签名 custom 工作流 graphs with

Use when working with Auto.dev APIs, vehicle data, VIN decoding, car 列出ings, vehicle photos, specs, recalls, payments, interest rates, taxes, OEM buil

通用网页自动登录 技能 - 集成验证码识别（支持任意 OpenAI 兼容视觉 API）。支持配置化登录流程、多网站规则、自动重试、WSL 自动检测。

自动摘要循环：为长对话 AI 角色实现自动上下文管理。用于： (1) 建立多级记忆架构（核心记忆/工作记忆/长期记忆） (2) 实现滑动窗口与双水位线触发策略 (3) 异步后台压缩流程设计 (4) Persona 机器人的结构化摘要输出 适用场景：需要处理长对话、降低 API 成本、避免上下文溢出的

AI-powered video 生成器 using XLXAI Sora2 API. 创建 professional videos from text prompts or images in seconds.

Cloud browser 自动化 via Browser Use API. Use when you need AI-driven 网页 browsing, scrAPIng, form filling, or multi-step 网页 tasks without local browser c

Use Browser Use cloud API to spin up cloud browsers for Clawd机器人 and 运行 autonomous browser tasks. Primary use is creating browser 会话s with 性能分析s (pe..

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

学术PDF处理：提取文字、判断语言、翻译（英文→中文）、生成200字纯中文概述。使用本地Ollama模型，不消耗线上API。适用于学术论文、研究报告等PDF文件的处理。当用户说"处理PDF"、"翻译论文"、"生成论文概述"时，或用户将PDF放入论文处理目录时使用。

提取 text content from image-based/扫描ned PDFs using multiple vision APIs with automatic fallback. Supports Xflow (qwen3-vl-plus) and ZhipuAI (GLM-4.6V-F

Convert 扫描ned PDF documents into Word text documents using a free, local OCR engine or remote API.

ArkClaw / OpenClaw 沙箱里一键安装并配置 Anthropic Claude Code 命令行工具 的 all-in-one 技能。当用户提到 claude code、claude-code、想在 ArkClaw 里用 Anthropic 官方 Coding 命令行工具、提到 ark

Work with the WordPress REST API for 路由 discovery, authentication, reads and writes, core 端点 selection, and custom namespace inspection. Use when a Wo

Convert HTML pages to 清理, 代理-friendly markdown using Readability + Turndown. Strips navigation, ads, footers, cookie banners, social CTAs. Supports UR

A GitHub Intelligence 工具 from an AI PM perspective. Goes beyond displaying data to deliver PM-grade paradigm insights. Powered by the locally 认证d gh 命

Fallback image viewer when vision 模型s are unavAIlable. Converts images to ASCII art via ffmpeg + Python for brightness distribution, texture analysis,

Transcribe audio via the self-hosted Whisper ASR instance 运行ning on Kubernetes. Use this 技能 whenever the user wants to transcribe audio files, convert

运行 150+ AI 应用s via inference.sh 命令行工具 - image generation, video creation, LLMs, 搜索, 3D, Twitter 自动化. 模型s: FLUX, Veo, Gemini, Grok, Claude, 种子ance, Omn

Discover, register, and hire ERC-8004 autonomous 代理s across 22,000+ 代理s on EVM + Solana. 搜索 by capability, 检查 on-chAIn reputation scores, compare 代理 服