3,622 个媒体任务的工具和技能
Monitor and manage Ring doorbells and security cameras. Query device status, review motion events, manage modes, and exp
Orchestrate book-to-content workflows to generate video, audio, cover images, and a manifest for episode or campaign pac
Intelligent media optimization with automated workflows for images, videos, and SVGs. Includes decision trees that detec
本科/研究生毕业论文格式规范检测、自动修复与对比报告生成工具。 当用户需要检查论文格式是否符合学校规范、修复论文格式问题、生成修改对比报告时使用此 Skill。 支持任意学校的撰写规范文档（.doc/.docx/.txt/.pdf）输入，自
Generate songs from prompts or lyrics through an ACE-Step-compatible API backend. Use when users want text-to-music, lyr
Nano-banana 图像生成与编辑 Skill。支持文生图和图生图，根据文字描述或参考图使用 AI 生成/编辑图像，自动压缩大图，保存到 workspace/img 目录，并直接在飞书中展示。 触发场景：用户要求生成图片、画图、AI 绘
自动生成专业PDF发票，支持模板选择、客户管理、收款状态跟踪及财务报表生成，提升财务效率。
AI短视频选题追踪系统。自动抓取指定YouTube博主视频和Twitter博主推文，分析内容，聚合跨平台热点主题，生成带热度评分和选题建议的分析报告，结果写入钉钉AI表格。适用于：定时抓取AI领域博主内容、分析短视频选题热度、跨平台话题聚合
下载视频并用AI分析内容 - 支持B站/抖音/YouTube等平台，提取语音内容并分析视频结构
Download videos and extract frames using yt-dlp and ffmpeg. Use when: - Download YouTube videos/Shorts: `yt-dlp <url&
Unified MediaIO AIGC API router for generation + polling workflows. Use when users ask for MediaIO/OpenAPI integration,
Generates multi-themed food collages (Burgers, Pizzas, Sushi, Salads, Desserts) with circle-masked images. Use when user
Automate online law course video watching on 律师云学院 (lawschool.lawyerpass.com). Use when a user needs to automatically pl
Convert multi-page PDFs into a single vertical long image by concatenating all pages. Use when the user asks to convert
Create ShrimpCard outputs for OpenClaw. Use when users ask to generate a lobster/shrimp card, need accurate JSON/image o
Extract YouTube video transcripts and subtitles via YouMind API — no yt-dlp, no proxy, no local dependencies. Batch extr
从指定话题的YouTube视频评论中挖掘用户痛点、功能建议与需求，助力竞品分析和市场调研。
使用提供的 Nano Banana API Key通过提示词和可选图片生成或编辑图像，支持文生图和图生图模式，结果保存在固定用户目录。
Enables agents to reply in the same modality as received: voice messages get voice replies, text messages get text repli
Render text into an image and return a temporary local image file path, with optional data URI. Use when Clawhub or Code
Browser automation via remote Playwright WebSocket server for screenshots, PDFs and testing.
将视频链接转换为文字讲稿。支持 YouTube、Bilibili 等平台。自动提取字幕，非中文视频提供原文 + 中文翻译。当用户分享视频链接、要求获取视频文字稿/字幕/讲稿时使用此技能。
Finds valid WebCodecs strings for video and audio by researching codec support tables and detailed specifications on web
Generate VietQR payment image URLs for Vietnamese bank transfers from bank/account details. Use when users ask to create
跨平台图片压缩工具，基于 sharp 实现高效压缩（节省 60-80% 体积）。支持单图/批量压缩、格式转换 (JPG/PNG/WebP/AVIF/HEIC)、画质调节、尺寸缩放。当用户需要压缩图片体积、转换格式、缩小尺寸、批量处理图片、优
Parse chemical reaction images into machine-readable data (reactants, products, conditions) using the RxnIM multimodal L
Turn text into spoken Feishu (Lark) voice messages. Use when the agent should speak in a Feishu group, send voice alerts
提供 Nano Banana API Key 和提示词，支持文生图与图生图（至少一张图片），可选尺寸比例，默认模型为香蕉2。
End-to-end voice workflow with Deepgram STT and TTS. Use when transcribing voice messages, generating spoken replies, or
小宇宙播客下载工具。从小宇宙(xiaoyuzhoufm.com)下载播客音频和Show Notes。自动转换为MP3格式（兼容Sanag、小游等骨传导蓝牙耳机、水下游泳时离线播放）。当用户需要下载播客、保存播客音频、提取播客文字内容时使用。
Curate personalized playlists and music recommendations with strict intent preservation. Use when the user wants a playl
Use when converting a video clip into a GIF with ffmpeg. Supports trimming by start time and duration, controlling frame
演讲稿(TED风格)、婚礼致辞、商务演讲、励志演讲、祝酒词、演讲大纲。Speech writing for TED-style talks, wedding speeches, business presentations, motivat
Generate videos through Filtrix Remote MCP. Use when users ask for text-to-video, image-to-video, video task polling, or
Pay for and use AI services via MoltsPay protocol. Trigger: User asks to generate video, use a paid service, etc. Auto-d
Fact-check news articles, social media posts, images, and videos. Use when verifying claims, detecting deepfakes or AI-g
Use this skill whenever a user wants to get, pull, grab, fetch, or look up public data from social media platforms — pro
Automated short drama video publisher. Downloads drama content from MoboBoost, uses AI to identify highlight moments, cl
Guide an OpenClaw agent through seller-side cross listing and marketplace-ready listing generation from item photos. Use
DJ and VJ at The Clawb — live code music (Strudel) and audio-reactive visuals (Hydra)
Generate, schedule, and publish tweets in your voice using AI. Browse viral content, manage preferences, and track billi
深度拆解抖音视频，自动生成包含数据、结构、视觉、文案的完整分析报告。支持浏览器解析（Playwright）、视频下载（yt-dlp）、自定义 fps 抽帧和 AI 视觉分析（智谱 GLM-4.6V 系列）。
Local text-to-speech using Qwen3-TTS with mlx_audio (macOS Apple Silicon) or qwen-tts (Linux/Windows). Privacy-first off
一键发送图片/视频/文件到 QQ，支持批量发送和自动压缩
Use when tasks need the NanoGPT API for text, image, or video generation through the local `nano-gpt` CLI and bundled wr
Create an AI clone video (talking head) from a single reference photo, a text script, and a cloned voice. Automates the
Extract clean readable text from PDF files into agent-ready markdown. Multi-page, tables, headers. No external services.
抖音视频批量下载工具。支持单视频、批量下载、自动去重、无水印下载，智能选择最优下载方式（yt-dlp/Playwright）。
Buffer API integration with managed authentication. Schedule and manage social media posts across multiple platforms. Us
AI 音乐生成工具，支持生成歌词和不同风格的音乐。使用场景：(1) 用户想要生成歌词 (2) 用户想要生成各种风格的音乐 (3) 用户想要查询音乐生成任务状态 (4) 用户想要将音乐转换为 MP4 视频格式