Skill rating

Send images/files to WhatsApp. Use when user wants to send an image, photo, screenshot, video, audio or document via WhatsApp. Workflow: (1) Download to /tmp, (2) Copy to ~/.openclaw/workspace/, (3) S

Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing.

Moderate text, images, and video using Vettly's content moderation API via MCP server.

Swap faces between images using EachLabs AI. Use when the user wants to replace or swap faces in photos.

字幕格式转换工具，支持 VTT、SRT、ASS、LRC 四种格式互转，以及时间轴偏移和双语字幕合并。当用户需要转换字幕格式（如 VTT 转 SRT 用于剪映）、调整字幕时间、合并双语字幕、或批量处理字幕文件时使用此技能。触发词：字幕转换、vtt转srt、srt转vtt、剪映字幕、字幕格式、时间轴偏移、双语字幕、字幕合并。

Podcast discovery for Wherever.Audio -- find shows and episodes, generate wherever.audio links.

WhatsApp skill with a 3-rule security gate. Your agent speaks only when spoken to — in the right chat, by the right person.

Downloads YouTube videos to ~/Downloads. Use when user wants to download a YouTube video to their machine.

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing,

Use this skill immediately and proactively when the user mentions video editing, clipping, highlight reels, short-form video, Reels, Shorts, TikTok, vertical video, or asks to process a video file. Do

Download YouTube videos and upload them to Pocket Casts Files for offline viewing. For personal use with content you own or have rights to.

Seedance Video Creative Studio. Autonomously analyzes images, expands copy, matches camera work, validates quality, and generates via API when user provides images/text. Triggers on: Seedance, video g

High-performance containerized web scraper (Docker + Crawlee + Playwright). Use when user mentions any of these: 爬虫, 爬取, 抓取, 采集, 数据采集, 爬数据, 抓数据, 获取数据, scrape, crawl, extract, fetch data, pull data, 亚马

Automatically track creator channels and transcribe new videos (YouTube, Bilibili, TikTok) with zero token cost during the pipeline. Use memory-based updates to skip already processed items and avoid

Create professional cinematic scripts for AI video generation with character consistency and cinematography knowledge. Use when the user wants to write a cinematic script, create story contexts with c

Transcribe audio to text with Whisper models via inference.sh CLI. Models: Fast Whisper Large V3, Whisper V3 Large. Capabilities: transcription, translation, multi-language, timestamps. Use for: meeti

Generate professional captions and subtitles with multi-engine transcription, word-level timing, styling presets, and burn-in.

AI video, image & music generation. 60+ models — Sora, Veo 3, Kling, Seedance, GPT Image, Suno v5, Hailuo, WAN. Text-to-video, image-to-video, text-to-image, AI music. One API key.

Use when performing video/audio processing tasks including transcoding, filtering, streaming, metadata manipulation, or complex filtergraph operations with FFmpeg.

Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rath

Generate images and videos via renderful.ai API (FLUX, Kling, Sora, WAN, etc.) with crypto payments. Use when the user wants to create AI images, videos, or needs a crypto-friendly generation service.

Intelligent multi-model router — automatically selects the best AI model based on task type (vision, image generation, video generation, audio, reasoning, code, general chat) via any OpenAI-compatible

Full content pipeline: YouTube URL → transcript → blog post → Substack draft → X/Twitter thread → vertical video clips via HeyGen AI avatar. One URL in, entire content suite out. Use when asked to: "t

Mux Video infrastructure skill for designing, ingesting, transcoding/packaging, playback ID policy, live streaming, clipping, and observability with Mux Data. Use when architecting or operating Mux-ba

Uses dupe.com APIs in order to find similar products for the product found in the input URL given by the user.

Extract and summarize YouTube video transcripts quickly and efficiently.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, tes

生成火山引擎豆包语音播客（PodcastTTS）。输入主题文本，自动生成双人对话式播客音频。

智能总结工具 - 自动检测内容类型、智能选择长度、缓存、关键点提取。支持网页、PDF、图片、音频、YouTube。

AI 智能视频剪辑助手。支持 ASR 语音转文字、词级时间戳剪切、LLM 驱动剪辑决策（EDL）、视频渲染、自检循环、多平台导出。当用户需要：自动剪辑视频、AI 理解视频内容并剪切、生成字幕并烧录、提取高光片段、导出短视频、多平台视频格式适配时使用此技能。

Generate voiceovers, narration, and spoken audio for videos, explainers, ads, and social content.

从图片或文字描述自动生成完整视频故事。支持灵活输入（1-N张图片/纯文字/混合），可选时长和风格。关键词：故事视频、视频生成、图片转视频、文字转视频、story video、video generation

烯旺集团医疗科研成果智能检索与视频口播文案生成技能。自动检索「烯旺医疗科研成果」文件夹内全部66个文档（含学术论文、公众号推文、热敏灸专著、企业资料等），支持按关键词、主题分类（肿瘤/骨科/五官科/妇科/皮肤/睡眠/心血管/中医/基础理论/企业/产品共11类）、疾病名称检索科研成果，并根据检索结果自动生成高质量的视频口播文案。适用于需要查找烯旺集团石墨烯医疗科研数据、撰写医疗健康科普视频脚本、制作

Video Generation and Editing with Wan 2.7 series models. Supports text2video, image2video (first-frame, first+last-frame, video-continuation), reference2video, and video-editing capabilities.

Pull Weibo user profiles and posts, post comments/likes/reposts, keyword search across posts, videos, users, topics and images, the hot-search board and ranking boards, and channel feeds. 31 endpoints

全平台视频发布汇总。对比四大国内视频平台（小红书、抖音、B站、视频号）的发布规则和步骤，提供最佳发布策略。自动选择最适合的平台组合。

搜索和分析TikTok视频数据，按区域、达人、商品、类目、播放量、时长、发布时间、是否带货/投流/AI视频等条件筛选视频，返回播放量、点赞、评论、分享、收藏、视频销量与GMV等指标，覆盖16个TikTok Shop站点。当用户提到TikTok视频搜索、TikTok视频列表、TikTok带货视频、TikTok视频数据、TikTok视频播放量、TikTok视频销量、TikTok视频分析、EchoTik

Eversince is a creative agent that plans and executes across image, video, and audio. It orchestrates the latest AI models and operates in a purpose-built environment with tools, skills, and memory. W

专业 AI 视频创作技能，帮助用户使用 Seedance 2.0 模型创作高质量视频内容。当用户需要生成 AI 视频、编写视频提示词、使用即梦平台、进行多模态视频创作、制作分镜、设计视觉风格、优化提示词时调用。支持图像、视频、音频、文本四种模态输入的提示词优化和创作方案设计，整合专业电影制作知识体系。

Extract plain-text transcripts from YouTube videos using a local Python script. Use when the user wants to fetch, extract, or get a transcript from a YouTube video URL, analyze YouTube video content a

短视频脚本生成、分镜设计、口播稿撰写、爆款公式套用。适合短视频创作者、MCN、品牌方。

Pull Douyin videos, user profiles and feeds, comments, hashtags, music, live rooms, the hot-search board, and keyword search across videos, users, music, live and hashtags. 27 endpoints, structured JS

AI视频与图片一键生成，支持Seedance 2.0/2.0Fast/1.5 Pro文生视频、图生视频，多模型文生图，积分查询与作品管理。当用户提到生成视频、制作视频、AI视频、文生视频、图生视频、生成图片、AI绘图、文生图、查积分、查余额、查看作品、Seedance视频、seedance等需求时使用此技能。

X(Twitter) Video Downloader — paste an X(Twitter) video link and get a watermark-free video download URL instantly. Use when you need to download X(Twitter) videos, save Twitter videos, or get X video

Resolve a brand or domain to a Google advertiser id, then pull every ad it runs across Search, YouTube, Shopping, Maps and Play, and open one creative with its full region and impression history. 3 en

The audio & video layer for agents. 22 local MCP tools. No cloud, no API keys.

Read Kuaishou (China) profiles, posts, live status, videos, comment threads, hashtag feeds, leaderboards and four kinds of search as structured JSON. 14 endpoints priced per endpoint at 1, 2, 10 or 40

Search ads running across LinkedIn by keyword and/or advertiser company id, returning each ad's advertiser, ad copy, format, promoted label, thumbnail and a detail link, then open one ad in full with

Instagram Video Downloader — paste an Instagram video link and get a watermark-free video download URL instantly. Use when you need to download Instagram videos, save IG videos, or get Instagram video

找客户 / Find Customers / 销售线索 / 评论区获客 Skill。用于找客户、获客、销售线索、潜在客户、客户名单、AI获客、社媒获客、评论分析、评论获客、评论区获客、小红书获客、抖音获客、快手获客，从抖音、小红书、快手公开评论中识别购买意向、AI sales leads、高意向客户和可跟进客户名单。适用于「找客户」「帮我找客户」「获客」「销售线索」「潜在客户」「客户名单」「评论分