OpenClaw AI 技能

提取 structured data from any 网页 page. Supports CSS selectors, auto-检测ion of tables and 列出s, JSON/CSV 输出 格式化s. Use when asked to scrape a we...

生成 上下文ual follow-up suggestions after AI 响应s. Shows 3 命令行工具ckable buttons (Quick, Deep Dive, Related) when user types "/followups".

文件整理与归档 技能。管理用户输入文件和我生成的输出文件的存储、命名、分类。 适用于：用户发送图片/视频/PDF等文件给你处理，或你生成文件给用户。 触发：任何文件存档操作前。

Instantly summarize any content — articles, PDFs, YouTube videos, 网页 pages, long documents, or pasted text. 提取s key points, action items, and insights

Smart image loader that handles 机器人h URLs and local files, automatically 下载s URLs to temporary locations, and displays images using the read 工具. Use w

Analyze home energy usage and propose safe, read-only 自动化 plans for savings. Use when a user wants Home 助手 energy insights, optimization ideas, or dra

Universal Smart 模型 Switcher V3 - Multi-提供者, Multi-模型 intelligent switching. Automatically selects the best 模型 from ALL your purchased API plans...

生成s 上下文-aware memes by selecting optimal templates and crafting witty captions for any topic, situation, or social media content.

安全版智能网页内容获取技能。本地解析 + 可选远程清洗，隐私优先，令牌 优化。

Pick the best AI 模型 for any task using the Smart Spawn API. No 插件 needed — just HTTP 请求s to ss.deeflect.com/API.

扫描s and categorizes files in a directory, 检测s duplicates, and reorganizes them into a clear folder structure with safety features and 回滚 options.

5-layer memory architecture for OpenClaw 代理s. Solves 上下文 bloat, the 48h fogging problem, and rule amnesia. Works for single-代理 and multi-代理 设置u...

Smart 网页 搜索 v3.1 - Intelligent 搜索 with BAIdu (China) and Google (International) as primary engines. Real-time news, ad 过滤器ing, content de-toxicat...

智能模型自动切换 V5.0.2 - 多模态感知，自动识别图片/视频/音频/代码/文本任务，切换到最适合的模型。支持图片理解(qwen3-vl-plus)、视频音频(qwen3.5-plus)、代码(glm-5)、Office文档(MiniMax-M2.5)、推理等场景。零感知切换，无需手动操作。

Enforce proactive, 查询-优化d memory_搜索 usage. Must 运行 memory_搜索 when (1) prior 上下文 is referenced, (2) a new task 启动s, or (3) a proper n...

Intelligent multi-模型 路由r — automatically selects the best AI 模型 based on task type (vision, image generation, video generation, audio, reasoning, code

Smart 上下文 compaction for OpenClaw 代理s. 4-phase 进度ive strategy: 扫描, 提取, 检查, Compact. Before 运行ning /compact, this 技能 扫描s 工具 out...

Smart auto-更新r with AI-powered impact assessment. 检查s 更新s, analyzes changes, evaluates 系统 impact, and decides whether to auto-更新 or just r...

Intelligent 图表 generation and data analysis 技能. Reads user-supplied data files (CSV/Excel/JSON), analyzes data characteristics with LLM assistance, au

分析和总结URL链接内容，并保存到obsidian中，同时定期提醒复习