Media AI Skills

Create a dramatic "Giant Product" visual where a regular item is showcased as a massive, building-sized object next to a person, then optionally animate the scene.

YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

Two stages: first a single-page sheet of numbered panels from an image model, then that sheet fed to Seedance as the reference. The sheet owns order, framing and timing, and the video prompt only has…

Add motion graphics at the right moments without blocking the story. Use when the user wants to enhance talking-head, lecture, tutorial, interview, podcast, or creator videos with motion graphics.

Edit video and audio with local FFmpeg from natural-language requests: cut, trim, join, resize/reframe (9:16, 1:1), speed change, captions and subtitles (SRT/ASS, animated, karaoke), logos and text…

HyperFrames HTML 到 MP4 渲染基础设施导航：composition、可 seek 的 GSAP 时间线、素材/字幕/声音、CLI 检查与确定性本地/云端渲染。用于选择视频渲染底座、批量变量视频、Studio 编辑或接入 HyperFrames。

Patterns, gotchas, and conventions for threading changes through LemonadeClient, its callers, and the GAIA test suite. Apply when modifying lemonade_client.py, its providers, VLMClient, UI routers, or…

视频配音与配乐。三件事——(1) 配音：把口播稿用 TTS 生成旁白音频；(2) 配乐：根据视频内容/节奏匹配合适的 BGM，从免版权曲库找到并下载；(3) 混音：把 BGM + 旁白 + 视频用 ffmpeg 合成，自动压音(BGM 在人声下自动变小)、响度归一、淡入淡出、对齐视频长度。当用户说「配音」「配乐」「加 BGM」「背景音乐」「找音乐」「给视频配旁白」「TTS…

Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a composed…

知乎视频 → 下载 → 转录 → 存为 Markdown。 支持知乎视频链接，无需登录。

Download videos and audio from 1500+ websites including YouTube, Bilibili, TikTok, Twitter/X, Instagram, Vimeo, and more using yt-dlp. Use when the user wants to download videos, save media from…

Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with channel="bluebubbles".

Expert prompt engineering for Google Veo 3.2 (Artemis engine). Use when the user wants to generate a video with Veo 3.2, needs help crafting cinematic prompts, or mentions Veo, Google video…

Identify content gaps between your site and competitors. Use when the user says "content gaps", "what am I missing", "competitor content", "content opportunities", "topics I should cover", "content…

Plan, draft, audit, and publish content for Instagram. Use when the user wants to write a caption with a first-125-char hook, plan a slide-by-slide carousel, reverse-engineer the hook from a viral…

When the user wants to write a multi-part thread or content series for Twitter/X, LinkedIn, Threads, Instagram (Reel/carousel/Story series), TikTok (multi-part videos), YouTube (video series,…

当用户要求“理解视频内容”“完整学习视频”“解读视频”“视频学习总结网页”“图文并茂学习网页”“用 Qwen 多模态分析视频”“用 qwen3.7-plus 看视频”“关键知识点匹配画面”“把视频做成学习网页”时必须使用。本 skill 会把本地 MP4 或已下载视频拆成音频转录、时间轴帧图、Qwen 多模态逐段分析，并用既有学习总结网页模板生成图文并茂…

Places album art files in the correct audio and content directory locations. Use when the user has generated or downloaded album artwork that needs to be saved.

Use Doubao Text-to-Speech (Volcengine TTS) to convert text into audio files. When a user mentions "Doubao TTS," "Doubao Text-to-Speech," "doubao tts," "Volcengine TTS," "volcengine tts," "speech…

The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. Use this to record the…

Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to…

Use when routing Alibaba Cloud Model Studio requests to the right local skill (Qwen text, coder, deep research, image, video, audio, search and multimodal skills). Use when the user asks for Model…

This skill should be used when the user asks to "extract audio", "get the mp3", "strip audio from video", "rip audio", "save audio from video", "convert to audio", "get the soundtrack", "pull the…

Generates a UGC video — a creator or customer, on camera as themselves, sharing their own authentic take on a product. Use when the user wants a UGC video, creator video, influencer ad or endorsement,…

Choose default fal.ai endpoint IDs for genmedia production skills. Use this with commercial, marketing, ugc, character-design, cinematography, storytelling, and workflow when the user has not named a…

【Ark Agent Plan 专用版本】基于 Remotion 的英文词汇视频自动化生成流水线。输入一个英文单词，自动完成：诊断、火山引擎 TTS 音频（与 Seedream/Seedance 共享认证）、节奏分割、视频渲染、飞书上传和成本汇报。

Cinematic slow push-in zoom toward a hero detail on the product. Creates a reveal effect.

The CapCut craft skill — edit short-form social video (TikTok, Reels, Shorts) fast and safely: retention-paced cuts, auto-captions, beat-synced sound, exports. Use when someone wants to edit in…

Create, implement, or review beautiful article work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on beautiful article.

Master Ira Glass's narrative storytelling methodology from This American Life to create podcasts that captivate listeners through the power of story. Use when: Creating a branded podcast or audio…

Use when 王建硕 gives a list of movies and wants them turned into Relisten-ready files — find a LEGAL source for each (public-domain / openly licensed copies on Internet Archive, or a copy he already…

Generate a YouTube description with a brief intro, relevant links, and clickable timestamps for each question.

Long-form and episodic video production pipeline (1-10 min, YouTube/web). Use when user requests 'long-form video', 'YouTube video', 'episodic video', or 'video series'.

Export a finished layered edit (footage + graphic cards + alpha fx overlay + captions + SFX/music/VO) into a CapCut desktop draft where EVERY element stays editable — footage segments split at zoom…

Use the workspace as the content system of a website: read published articles and pages, add drafts, upload pictures and videos, and write the text. Use when the user builds or edits a website whose…

Create podcasts from topics, URLs, or text. Triggers on: "做播客", "podcast", "播客", "录一期节目", "chat about", "discuss", "debate", "dialogue", "make a podcast about".

Organische Social-Media-Inhalte für Deutschland und den DACH-Raum planen, verfassen, wiederverwenden, prüfen und messen. Nutze diesen Skill, wenn Posts, Redaktionspläne, Content-Serien oder…

Soul Forge — Distill memories, chat logs, voice, and photos into a 4-dimensional digital soul / persona. Trigger on /relic-forge, or when user wants to distill, awaken, or build a Relic ("distill a…

Start of the UGC pipeline for persona research, creator profiles, format selection, and scriptwriting. Use when the user is clearly asking for messaging work rather than broad full-pipeline…

Active direct sourcing. Registers and creates standout profiles on the 40 target companies' career sites, then applies to matching positions.

Full-featured Telegram bot skill with inline queries and media support. Communicates with users through the Telegram Bot API, handles media, manages group interactions, and supports inline queries.…

OpenClaw agent skill for converting documents to Markdown. Documentation and utilities for Microsoft's MarkItDown library. Supports PDF, Word, PowerPoint, Excel, images (OCR), audio (transcription),…

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character…

One-shot autopilot orchestrator — runs the full spark-video pipeline (screenwriter ↔ director per-scene parallel → render chain-DAG parallel + per-clip review → stitch). User confirms at 4 gates (+ 1…

Import and edit Pocket, phone, action-camera, or similar footage into a concise Remotion vlog with selective cuts, researched location context, titles, maps, transition captions, optional…

Verify whether an image or video is authentic, original and correctly captioned — provenance checks, error level analysis, noise and JPEG compression analysis, clone and copy-move detection, lighting…

Use when building a reusable thumbnail template and design guideline for a video channel (YouTube and other 16:9 video platforms) — from a channel link whose latest thumbnails set the style, from one…

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character…

Expert guide for prompting ByteDance's Seedance 2.0 AI video model (text-to-video, image-to-video, first/last-frame, multi-reference, and multi-shot generation with native synchronized audio). Use…

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use…