Skill rating

Local video, image and audio processing expert for Windows, powered by VN Video Editor. Use this skill whenever the user wants to process video or audio on their Windows PC — including: auto-generatin

Use when YouTube data is needed through MyBrandMetrics: search YouTube videos, get video metadata, inspect channel info, browse playlists, list comments, check live broadcasts, query YouTube Analytics

Seedance 2.0 Pro on RunComfy. Seedance 2.0 Pro (ByteDance Seedance v2) is a multi-modal cinematic short-form video model with native lip-sync audio. This skill calls Seedance 2.0 Pro through the RunCo

Control YouTube Music with natural language. Play, pause, skip, search, manage playlists, and queue tracks. Full playback control via browser automation.

Takes one long-form piece of content and repurposes it into Twitter threads, LinkedIn posts, newsletter editions, and short video scripts.

Seedance2 Video Generation Prompt Engineering — multimodal reference system, cinematic camera language, audio-video sync, and scene-by-scene prompt patterns for ByteDance's Seedance2 model.

Film and video storyboarding with shot vocabulary, continuity rules, and panel layout. Covers shot types, camera angles, movement, 180-degree rule, and annotation format. Use for: video planning, film

Generate images, videos, and process media using the GenVR API. Standalone Node.js CLI.

Using a baby monitor (smart camera) fixed above the crib, the system analyzes infant sleep video in real time to detect sleep posture (supine, side, prone) and whether the mouth/nose area is occluded

视频平台公域流量精准获客工具。基于评论区数据挖掘，支持竞品截流、意向客户筛选、舆情转化及私域引流，适用于短视频营销、销售线索挖掘、精准获客与流量变现，助力企业低成本获取高意向客户。

Use local visual memory tools to index and search photos and videos from creator media libraries.

Kling 3.0 video generation on RunComfy. Kling 3.0 (also called Kling V3.0) is Kuaishou Technology's third-generation multi-shot video model with native synchronized audio and consistent character iden

Can search and get YouTuber information

Using fixed cameras in the living room, child's room, kitchen, or other home zones, AI object detection and pose estimation analyze the video in real time to recognize a child's hand actions and the o

Through a fixed camera in a reptile enclosure, the system continuously captures 24-hour video and uses motion-detection techniques to count hourly activity volume (pixel-change area or motion-pixel ra

内容归档工具免费版，将外部内容捕获为本地快照。Use when 需要视频处理、音频编辑、媒体转换、配音生成时使用。不适用于版权受保护的媒体内容处理。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。提供结构化输出和错误处理机制。支持多场景应用和灵活配置。 支持文章、视频、推文的基本内容提取与标签管理. 提供基于关键词的搜索能力.

Generic Xeon-CPU video upscaler. Plans lanczos pre-scale + N Real-ESRGAN general-x4v3 x4 passes to reach any target resolution, with super-resolution always the last step and a 270-line pre-scale floo

Self-hosted video REST + MCP API. POST JSON, get a video back. Lipsync (LatentSync 1.5 + Wav2Lip/Wav2Lip-GAN) at /v1/video/lipsync, GFPGAN face restore at /v1/video/restore, pure-ffmpeg ops (trim, con

HappyHorse 1.0 — text-to-video generation on RunComfy. HappyHorse 1.0 is currently #1 on Artificial Analysis Video Arena and produces native 1080p video with in-pass synchronized audio (dialogue, ambi

End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg

发送任意本地文件到飞书，自动处理大文件。视频/音频按 20MB 分段（不重新编码），其他文件压缩为 ZIP。支持大文件自动处理。

Design, optimize, and batch-produce video covers/thumbnails for Bilibili, YouTube, Xiaohongshu, Douyin, and more. Title strategy, reference analysis, portrait consistency, AI prompt generation, layout

Self-hosted OpenAI-compatible speech service. /v1/audio/transcriptions fronts 14 open ASR models (Whisper, Parakeet, Nemotron-3.5-ASR, Canary, Sherpa-ONNX, Vosk, plus wav2vec2 and ZIPA phoneme recogni

音乐库整理工作流：扫描→规划→主人确认→软删除→验证→清理。强调安全流程。Safe-by-default music library organizer with soft-delete + mandatory owner confirmation.

Through a fixed camera in the reptile enclosure, the system captures a high-definition image (or a static video frame) once excrement is found, and uses AI visual analysis to identify urate (white/mil

Omnicall — every AI tool your agent needs in one keyless endpoint: 248 LLMs (GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen, Mistral) plus image/video/voice/music generation and live crypto/DEX/DeFi

Save web content to Obsidian vault. Supports Twitter/X, WeChat MP, Xiaohongshu, YouTube, Bilibili, and any web page. Automatically routes to the best fetch method per platform.

Call GET /api/douyin/get-video-sub-comment/v1 for Douyin (TikTok China) Comment Replies through JustOneAPI with commentId.

Lip-sync a face to a specific audio track on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar from a portrait + audio), Sync Labs sync v2 / Pro (state-

🦞 色😍龙虾 - 根据主人审美偏好，在多个平台（小红书、抖音、YouTube、B站）搜索并推荐颜值博主/视频。 自动获取用户cookies，学习主人喜好，推送个性化内容。 使用场景： - 主人说"找美女/小姐姐/颜值博主" - 主人提到特定平台（小红书/抖音/YouTube/B站） - 主人给出审美偏好（如"喜欢 habin/leeesovely 这种类型"） - 主人要求"推荐类似 XXX

25 AI-powered tools for video generation, talking avatars, image editing, voice cloning, and more — powered by DreamAPI. Describe what you want and the agent handles the rest.

杰峰设备视频遮挡技能（开发版）。支持一键遮蔽功能，开启后摄像头转至遮蔽位置并关闭视频预览和录像，保护隐私。

RunComfy CLI on RunComfy. The `runcomfy` CLI is one binary, one auth, hundreds of RunComfy model endpoints — image generation on RunComfy, image edit on RunComfy, video generation on RunComfy, image-t

Render comparison tables a human reads at a glance instead of parsing — colour and bar length carry the comparison, text only confirms it. Use whenever you are about to present several options with se

AI视频脚本生成器。输入主题和平台（抖音/小红书/B站），自动生成完整视频脚本，包括开场钩子、分镜设计、台词文案、BGM建议、封面文案。支持多种风格（干货/故事/测评/教程），记忆用户写作偏好并持续优化。当用户说"生成脚本"、"写视频文案"、"脚本模板"、"视频脚本"时触发此技能。

多平台视频图文发布助手 — 支持抖音、快手、B站、小红书、微信视频号五大平台同步发布图文和视频内容。 触发场景："一键发布到小红书、抖音、快手、B站、视频号"、"帮我同步发多个平台"、"多平台发布视频"、"发布视频到抖音"等。 ⚠️ 本 skill 需要用户协助操作浏览器登录，所有发布操作均在用户本地浏览器中完成，不会自动登录或存储任何账户凭证。

Call GET /api/douyin/get-user-video-list/v3 for Douyin (TikTok China) User Published Videos through JustOneAPI with secUid.

AI漫剧/短剧视频智能帧分析工具。自动提取关键帧 → 多模态逐帧解读 → 输出完整分析报告（剧情大纲、镜头语言、角色设定、台词整理、商业改编建议）。适用于抖音/视频号短剧拆解、竞品分析、改编策划。

中文短视频脚本写作助手。针对抖音、小红书、B站、快手等平台，生成高完播率的短视频脚本。 **当以下情况时使用此 Skill**: (1) 需要写短视频脚本/文案 (2) 用户提到"脚本"、"短视频文案"、"抖音文案"、"小红书文案" (3) 需要视频选题建议或热点选题 (4) 需要优化视频开头/钩子（hook） (5) 需要把长内容裁剪成短视频脚本 (6) 用户提到"完播率"、"开头3秒"、"视

Call GET /api/douyin-xingtu/get-kol-rec-videos/v1 for Douyin Creator Marketplace (Xingtu) Recommended Videos through JustOneAPI with kolId.

End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Powered by SkillBoss API Hub with FFmpeg editing.

当需要搜索或推荐 TikTok、YouTube、Instagram 红人时使用，通过 Finder 获取候选红人。

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。

Video Repurpose is an AI repurposing assistant for turning one long or finished video into multiple short-form assets with new hooks and formats. It helps teams remix scenes, rewrite captions, resize

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。

视频动作分析助手：从教学视频中提取关键帧、分析动作姿态、生成火柴人动作示意图。适用于运动教学视频的逐帧拆解、姿态分析和改进建议。触发关键词：视频分析、动作分析、运动私教、火柴人、姿态分析、截帧

Convierte un contenido en un paquete completo multiplataforma — hilo de X/Twitter, post de LinkedIn, sección de newsletter, carrusel de Instagram y script de video corto — cada uno reescrito nativamen

Food for your model — extract transcripts, key frames, OCR, slides, and LLM summaries from YouTube videos into structured AI-ready knowledge.

MDClaw OpenClaw API 技能，支持文字转语音(TTS)、文生图(Text to Image)、文生视频(Text to Video)、图生视频(Image to Video)等多模态 AI 能力。通过网关服务统一调用，支持账号注册、图片上传、任务轮询等完整功能。

Moonshot AI thinking model with text, image, and video understanding. Suited to complex analysis, coding, and writing that needs long reasoning chains.