自动分析视频内容，提取关键帧进行AI视觉分析。支持 Windows、macOS 和 Linux。首次使用自动从GitHub下载对应平台的工具脚本。
--- name: wechat-skill version: 1.0.0 description: Windows 电脑端微信消息发送 MCP，实现在微信上给指定联系人发送消息 metadata: {"openclaw": {"requires": {"bins": ["python"]},
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work...
Backup and restore an OpenClaw agent's full workspace (memory, config, credentials, skills, cron jobs) to/from a Git repository. Use when: migrating to a new...
电商视频生成技能。通过 MCP（mcporter）调用远程视频生成 API， 自动为用户生成营销短视频。支持任务创建、进度查询、视频下载。
在 GPU 服务器上部署 LLM 模型服务（vLLM）。支持多服务器配置，自动检查 GPU 和端口占用，一键部署流行的开源大语言模型。
Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to l...
Generates images in Google Flow (labs.google/fx) through browser UI automation. Supports Nano Banana 2 and Nano Banana Pro with landscape/portrait aspect rat...
ModelPool (Free) — Free AI model manager for OpenClaw. One command to auto-discover free models, configure multi-key rotation for multiplied free quota, buil...
Real-time prompt injection and command injection detection for OpenClaw agents. Screens incoming messages, tool results, GitHub issues, and external content...
Complete training plan solution for My Likes platform. Fetches historical data, analyzes training patterns, generates personalized plans, converts to Likes f...
Automatically scrape and decode real-time hiring signals from job boards to generate scored B2B sales leads with personalized outreach and prospecting videos.
Natural language to SQL. Ask questions about your data in plain English, get queries, results, and explanations. Supports SQLite, PostgreSQL, and MySQL. Impo...
Evaluate AI agents by injecting diagnostic tests to detect cognitive biases, scoring responses on authority resistance, fact grounding, and neutrality, and g...
Personal AI photo album for OpenClaw. Use when users say: - "index my photos" - "set up an AI photo album" - "search my photo library" - "reconnect my photo...
Transcribe audio files (WAV/MP3/M4A/FLAC) to timestamped text using SenseVoice-Small + FSMN-VAD. Supports single-file and batch mode with VAD-anchored per-se...
Project-specific guidance for building a persistent girlfriend selfie workflow on top of WeShop image agents. Use when the user needs to set up a girlfriend...
Guide users through ClawPaw Android setup — installing the APK, granting permissions, connecting SSH tunnel, and verifying the full LLM-to-phone control chai...
Forces exhaustive problem-solving with corporate PUA rhetoric. Trigger on: task failed 2+ times, about to give up, suggesting user do it manually, blaming en...
Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. MUST trigger when: (1) any task has failed 2+ times or y...
腾讯云 COS 向量桶全功能管理技能。覆盖向量桶、索引、向量数据的全生命周期管理，包括创建/删除/查询向量桶、创建/管理索引、插入/查询/搜索/删除
Generate professional four-act AI video scripts, episode breakdowns, asset prompts, and Seedance 2.0 storyboard scripts from stories or articles for Seedance...
提供产品需求分析的全流程技能，包括需求发现、分析、优先级判断及输出，支持多场景的结构化方法与工具应用。