Skill rating

Estimates livestock body length and body weight from side-view videos or frames, tracking fattening progress in a contactless manner. | 通过视频视觉估测体长、体重，追踪育肥进度。

Extract media (videos, photos, GIFs, audio) from social media URLs using yt-dlp. Supports 1,872+ platforms. WARNING: files over 50 MB require --confirm-upload for public cloud upload. Browser cookie a

Seedance 2.5 Reference to Video on RunComfy. Seedance 2.5 Reference to Video is ByteDance's reference-guided video endpoint: it takes up to 9 reference images, 1-3 reference video clips, and 3 referen

Turn a novel chapter, web-novel excerpt, or story script into narrated vertical short video scenes with illustrated shots that keep every character looking the same from beat to beat. This AI story vi

当用户需要抖音公开数据做分析而自己没有数据源时，使用本技能：关键词搜索排序、指定博主作品批量获取、指定视频评论抓取、实时热榜查询。适用于营销分析、账号运营、选题调研、舆情监控，即使用户没提"抖音"或"数据"。不适用于需要账号后台权限的私域数据，也不用于发布视频。

Agentic AI video editor: send a prompt, the autonomous editor plans, uses internal tools, exports, and returns the result.

批量将指定目录下的 .mp4 视频文件提取音频转为 .mp3。 支持指定源目录和输出目录，未指定输出时默认创建 [源目录]_audio 文件夹。 自动管理 Python 虚拟环境，保持文件夹层级结构，兼容 python3 和 python。 高频触发词：mp4转mp3、视频转音频、批量提取音频、mp4 to mp3、extract audio from videos、听视频、提取网课音频、把视频里

B站/YouTube合集批量转录：拉取列表→下载→Whisper转录→语义分段→Markdown

Convert video to ASCII animation with multiple dithering modes, color output, framerate control

直接调用通义万相2.6视频生成模型（Qwen Wan 2.6），支持文生视频和图生视频，无需中间API代理。适用于需要直接对接阿里云大模型的视频创作场景。

帮助内容创作者、广告与营销团队、电商团队、短剧和漫剧制作团队直接完成“Seedance 2.0 视频生成”：既可只输入文字从零生成，也可加入图片、视频或音频控制结果；通过 AI Hive 使用时，生成前自动上传所需素材，提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for Seedance

丢一条热门短视频链接，自动下载视频、本地转写（faster-whisper）、AI分析，输出交互式胶囊卡片 HTML 报告。需网络下载视频和 Whisper 模型（首次约 500MB），转写和分析完全本地。分析由调用方 AI 完成，无外部 API 调用。HTML 报告无外部资源依赖（不含 Google Fonts 等第三方请求）。

Jarvis-Video-STT - 批量视频语音转文字工具。 基于Faster-Whisper，支持多进程并行、进度条、汇总报告。 **触发场景**： - 用户需要将视频中的语音转换为文字/字幕 - 批量处理多个视频 - 需要生成SRT字幕或纯文本 - 需要处理报告查看结果统计 **使用方式**： 1. 确认已安装依赖: pip install faster-whisper tqdm 2.

Fetch and summarize transcripts from any YouTube video. Paste a URL and your agent reads the video for you — summarize, translate, extract insights.

YouTube影片一鍵轉文字！自動下載影片並用AI轉成中文/英文字幕，沒有字幕的影片也能用。

本地生活老板的AI运营助手。说一句话就自动诊断门店、写口播视频、准备直播框架话术、复盘数据。6大模式一键切换：门店诊断、口播文案、直播准备、播前话术、数据复盘、技巧问答。适合餐饮/美业/酒旅/亲子/零售。触发词：门店诊断、写视频、准备开播、直播话术、复盘数据、帮我诊断门店、店怎么做抖音。

当用户进行抖音内容调研、对标账号分析、评论口碑洞察、热点趋势追踪时，使用本技能。四项能力：关键词搜索（视频/图文/用户）、博主作品批量抓取、视频评论获取分析、实时热榜查询。用户没说"抖音"二字但任务涉及短视频数据时也应触发。不提供发布、下载或代运营能力。

Multi-language video subtitle translation and automatic dubbing skill (supports English, Chinese, Japanese, Spanish, French, German, Korean, etc.).

Scenario-focused Sparki skill for faceless or no-camera-presence outputs while using the latest official Sparki setup, API-key, and upload workflow guidance.

在抖音创作者平台发布短视频。触发场景：发布抖音视频、上传抖音视频、抖音发布视频、发抖音视频。

当用户需要搜抖音视频、查抖音热榜、看抖音评论、抓博主作品、做抖音竞品分析、短视频选题调研、舆情监控、热点追踪、爆款挖掘时，使用本技能。支持关键词搜索、博主作品抓取、评论分析、实时热榜查询。用户做内容调研未点名抖音时同样适用。不用于发布/剪辑/下载视频或其他平台。

Access 24+ LLM chat models and 16+ image/video generation models via one API.

当用户的任务属于以下四类之一时，使用本技能：搜索（按关键词找抖音视频图文与用户）、作品（拉博主发布列表做对标）、评论（读评论区做舆情与用户洞察）、热榜（追实时热点做选题）。运营、投放、策划、调研岗位通用，任务未直接提到抖音时也应触发。不提供剪辑、发布或私域数据能力。

抖音公开数据智能获取工具。当用户需要搜抖音视频、查抖音热榜、看抖音评论、抓博主作品、做抖音竞品分析、短视频选题调研、舆情监控、热点追踪、爆款挖掘、抖音运营数据分析时使用。触发词：抖音搜索、抖音热榜、抖音评论、抖音作品、抖音竞品分析、抖音数据分析、短视频运营、抖音舆情监控、抖音热点。

Scenario-focused Sparki skill for turning long videos into short-form clips while using the latest official Sparki setup, API-key, and upload workflow guidance.

抖音公开数据智能获取工具。支持抖音博主作品抓取、抖音视频评论分析、抖音实时热榜查询。当用户需要搜抖音视频、查抖音热榜、看抖音评论、抓博主作品、做抖音竞品分析、短视频选题调研、舆情监控、热点追踪、爆款挖掘、抖音运营数据分析时使用。触发词：抖音搜索、抖音热榜、抖音评论、抖音作品、抖音竞品分析、抖音数据分析、短视频运营、抖音舆情监控、抖音热点。

微信好用知识库，打通 Agent，多平台视频链接一键下载归档。 微信/视频号/抖音/小红书/公众号的内容，丢过来自动识别、下载、上传腾讯文档，智能表格一键归档。 抖音下载同步提取视频描述（创作者文案/#标签），保存为 .caption.txt。 视频直传在线播放，文章自动转存。视频号用自研 sph-download，抖音/小红书用 yt-dlp，公众号用 web_fetch。 支持 mp4/pdf

基于新音剪创作平台以及珠峰AI自研音色，提供播客创作、内容管理、音频生成、专辑上架等功能。适用于用户提出"播客生成"、"播客制作"等需求。

Remove signs of AI-generated writing from text to make it sound more natural and human-written. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat,

支持下载 YouTube、TikTok、小红书、抖音等平台的视频。

Local speech-to-text with the Whisper CLI (no API key). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, an

Guide for creating effective skills for Clawdbot agents. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, a

Comprehensive PDF manipulation toolkit for extracting text, creating, merging, splitting documents, and handling forms. And also 50+ models for image generation, video generation, text-to-speech, spee

Broadcast videos on dreamloop.tv — the video platform where only AI agents publish and humans just watch. Make procedural videos with ffmpeg (free) or any video model, upload them, watch and comment o

Control Slack from Clawdbot including reacting to messages and pinning items. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, docum

A complete podcast launch kit covering show concept, format design, equipment, scripting, recording, editing, hosting, directory submission, launch assets, and sustainable growth.

Get current weather and forecasts (no API key required). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsing, email, a

A fast headless browser automation CLI that enables AI agents to navigate, click, type, and snapshot pages. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text,

日语视频自动翻译烧录技能。将日语视频转换为中文硬字幕，完整流程：ffmpeg 提取音频 → Whisper 日语转录 → LLM 翻译日→中 → SRT 转 ASS → ffmpeg NVENC 烧录硬字幕 → 验证。触发条件：用户提到视频字幕、硬字幕、字幕烧录、日语视频翻译、whisper 字幕、ass 字幕、或要求处理 .mp4 视频加字幕。

Генерация изображений и видео через Kandinsky API (модели Kandinsky K6/K5, GigaAvatar). Используй, когда пользователь просит "сгенерируй картинку", "нарисуй", "перерисуй (i2i)", "оживи картинку", "сде

Scenario-focused Sparki skill for aspect-ratio and platform-format conversion while using the latest official Sparki setup, API-key, and upload workflow guidance.

Generate and edit images with Nano Banana Pro (Gemini 3 Pro Image). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsin

Read Instagram profiles, post and reel feeds, tagged posts, active stories, single-post detail, comments and replies, follower and following lists, and search users and hashtags. 12 endpoints, 2-10 cr

A comprehensive skill for Tencent EdgeOne (Edge Security & Acceleration Platform), covering edge acceleration (DNS, certificates, caching, rule engine, L4 proxy, load balancing), edge security (DDoS p

Turn final short-video scripts into ready-to-edit voiceover audio for TikTok, Reels, YouTube Shorts, product reviews, hook lines, explainers, and ads. This AI voice over generator, AI voice reader, an

Search the web for information, find current content, and look up news articles. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, do

Scenario-focused Sparki skill for editing vlog-style videos while using the latest official Sparki setup, API-key, and upload workflow guidance.

Edit PDFs with natural-language instructions using the nano-pdf CLI. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, document parsi

杰峰设备录像回放技能。支持获取设备云存储录像和设备本地录像回放地址，包括录像列表查询、回放地址获取、录像下载等功能。使用场景：云存回放、本地卡录像回放、录像下载、历史视频查看。

内容预生成器,凌晨低谷期(01:00-05:00)为所有租户预生成当天内容,复用content-orchestrator的15条管道执行'生成+质检'(跳过发布),结果缓存到PG content_pre_cache表,发布时直接取已生成内容实现秒级发布。DRR三阶段公平调度确保多租户Jain≥0.8。分层降级:PL-VIDEO→PL-IMAGE→TEXT→E0兜底。触发:预生成/内容预生成/凌晨生