Media AI Skills

Use when implementing audio — audio buses, AudioStreamPlayer, spatial audio, music management, SFX pooling, and dynamic mixing

Create native TikTok video ads with Pexo — vertical 9:16, sound-on, hook-first. Give it your product and Pexo writes the script in TikTok's voice, sequences fast-paced shots, picks the models, and…

Build or transform lightweight realtime voice-chat apps with a talking character avatar from either a user-supplied photograph or a text description. Use when Codex is asked to create a talking…

Record the Game View or any Editor window (Scene, Inspector, ...) to an .mp4 or .webm video. Use when a screenshot is not enough: motion, animation, physics, or a gameplay sequence.

当用户给出视频链接、链接清单或 z-web-pack 的 04-media-inventory.md，并要求"下载视频""视频下载""帮我把这个视频下下来""下载 YouTube 视频""下载 B站/哔哩哔哩视频""下载 m3u8/mp4 直链""把视频保存到本地""批量下载这些视频""下载字幕""下载视频号""视频号下载"时必须使用。本 skill 支持单个、多个、文本清单和媒体清单输入，覆盖…

The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is…

Automated daily tech briefing — multi-source collection → knowledge-base deduplication → AI summarization → TTS speech synthesis, generating MP3 audio briefings

Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech,…

Use when running a minimal test matrix for the Model Studio skills that exist in this repo, including image/video/audio, realtime speech, omni, visual reasoning, embedding, rerank, and edit variants.…

This skill should be used when the user asks to "convert this video", "change format to mp4", "trim from X to Y", "cut the first X seconds", "speed up this video", "slow motion", "timelapse", "resize…

Generates the storyboard sheets for a video — one image per clip, panels in a row, each panel one action. Divides each clip into panels itself, then builds the sheets one at a time, each taking the…

Fetch YouTube video subtitles/captions using Felo YouTube Subtitling API. Use when users ask to get YouTube subtitles, extract captions from a video, fetch transcript by video ID or URL, or when…

统一入口的 Remotion skill：用于 React/TS 视频制作、关键帧验图、中文旁白、字幕、渲染与交付。遇到 Remotion 视频需求时优先加载它。

Import a 3D model (GLB/GLTF) into Blender and apply a sleek, glossy product-shot finish with studio lighting. Trigger when asked to polish a 3D model, make a Meshy AI model look shiny, apply product…

Port an existing Remotion composition to HyperFrames HTML while preserving visible behavior. Use only when the user requests a Remotion migration.

Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples.

Optimize paid advertising campaigns across Google Ads, Meta, TikTok, LinkedIn, and other platforms. Use when tasks involve bid optimization, audience targeting, creative testing, ROAS improvement,…

The orchestration layer for AI-native creative production. This skill coordinates multiple AI tools—video, image, audio, digital humans, effects—into cohesive campaigns, productions, and creative…

When the user's Google Business Profile has been suspended, disabled, or is under review. Also use when the user mentions "suspended," "GBP suspension," "listing disabled," "profile removed,"…

Turn a user-provided voiceover audio file + SRT subtitle into a finished, narration-synced MP4 using HyperFrames (HTML-to-video). The audio + SRT are the source of truth — scenes are timed to the SRT…

Generate or edit images with Codex's built-in image generation from any agent, through an MCP tool or a plain CLI. For every image request it first proposes at least four divergent style directions…

视频脚本助手 - 专业的视频内容策划与脚本创作专家。适用场景： (1) 短视频脚本创作（抖音/快手/视频号） (2) 中长视频脚本（B站/YouTube） (3) 分镜头脚本设计 (4) 口播文案撰写 (5) 视频大纲与结构设计 (6) 视频标题与封面文案 (7) 视频SEO优化（标题/描述/标签）…

数字人提示词生成。根据一张或多张人物演唱图和一段歌曲音频，使用带时间码的真实歌词，生成可直接粘贴到 11 号 MiniMax H3 数字人工作流的六段式提示词。支持单人和男女对唱；使用 wav2vec2 男女声分类模型结合音色聚类识别声部，音高算法仅作兜底。对唱使用交替单人镜头，每个歌词段画面中只有对应歌手，另一人完全在画外。

Video repurposing pipeline for multi-platform clip extraction. Use when the user requests to 'extract clips', 'repurpose video', 'create clips from video', or 'clip video for social'.

Use when the user knows what they want to do but not how to be known for it, such as finding a niche, positioning, thought leadership, rebranding, or making bios consistent across channels. Uses the…

Writes an image or video generation brief: a shot list, per-scene prompts for AI image and video tools, aspect ratios, and a style guide. Use whenever someone wants a visual or creative brief, a…

Capture website B-roll and screenshots for a video edit: full-page screenshots of real pages (for shot-cards and "proof" beats), smooth scripted-scroll screen recordings, and high-fidelity Screen…

爆款拆解复刻：把抖音/TikTok 爆款带货视频（链接、转写或口述结构）拆成 8 维结构与 5-beat 节拍，再映射到你的商品，输出拆解表 + 3 个复刻角度 + 可渲染 storyboard.json。Use when the user says 爆款, 拆解, 复刻, 对标, 仿拍, viral remake, breakdown, swipe file, copy structure,…

Extract visual, video, and audio features from media. Use for pixel features (Pillow), video frames (FFmpeg+Pillow), speech/audio features (openSMILE), music features (librosa), and visual semantic…

Generate an MP3 pronunciation of a glossary term using ElevenLabs TTS API and insert a "Pronounce" button into the term's entry in a markdown file. Trigger when the user says "Create a pronounce…

Collect a product's official brand and promotional material and put it on its prototype canvas as image rows, one row per surface. Covers the company's own brand kit, the App Store, Google Play and…

Zoom Meeting SDK for React Native. Use when embedding Zoom meetings in React Native iOS/Android apps with @zoom/meetingsdk-react-native, JWT auth, join/start flows, platform setup, and native bridge…

Split AI content into two layers — AI generates raw material (backgrounds, characters, clips), code assembles the deliverable (text, layout, render). Use when AI-generated carousels/cards come out…

Developing for multicore systems in Zephyr RTOS. Covers Symmetric Multiprocessing (SMP), Asymmetric Multiprocessing (AMP) with OpenAMP/RPMsg, inter-processor communication (IPC) patterns, and Linkable…

Soul Engine — Bring an awakened Relic alive for conversation. Trigger on /relic-talk, or when user wants to talk to, chat with, or invoke a Relic ("talk to grandma", "chat with Mimi", "跟XX聊天", "召唤XX",…

lyt 系列电商产品短视频拍摄脚本 skill。用于用户已经有具体产品、产品图片、商品链接、产品资料、已确认卖点或现有产品文案，希望生成可直接拍摄的 TikTok Shop 或跨境电商短视频脚本、分镜表、UGC 脚本、演示/对比/测评/场景脚本、广告素材脚本或达人寄样脚本；也可把已有产品文案整理成可拍分镜，或生成目标市场语言与中文回译。不用于从 0…

Generate the canonical first frame with Nano Banana 2. Composition, character, environment, and color — all locked before animation. The visual design gate.

视频拆解与逐镜复刻 —— 宣传片线方向之一：拆解用户提供的视频或关键帧，提取镜头顺序、运镜、光影与节奏证据，编译为逐镜复刻提示词。

将小说/故事改编为互动小说网页游戏（React SPA），含 AI 生成素材（视频/图片可选）、 可选 TTS 旁白、程序化音频、分支剧情引擎、存档系统。 使用 `bl` CLI 完成素材生成（`bl video generate` / `bl image generate` / `bl speech synthesize`）。 当用户提到互动小说、文字冒险游戏、小说改编游戏、H5…

Edit narration-led Remotion video essays using talking-head footage, overlays, selective B-roll, comic callouts, and still-frame visual QA. Use for personal reflective essays; not for a generic slide…

Transform one piece of content into multiple formats - blog to social, video to text, podcast to threads.

Use when resizing or reformatting a CoDesign / CE.SDK design to a new size or aspect ratio (ig-post ↔ ig-square ↔ ig-story ↔ widescreen, or a custom W×H); when building the size/format editions of a…

Image and media aspect ratio standards, responsive aspect ratios, and consistent media sizing.

Create, inspect, edit and render visual media with the SlopCamera CLI and SDK. Use for diagrams, raster-to-SVG conversion, existing screen or camera recordings, video editing and captions, social…

Build a HyperFrames slideshow to present live - slides, fragment reveals, branching hotspots and presenter mode with speaker notes, served by `hyperframes present` - or turn an existing page into one.…

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Posts content to Weibo (微博). Supports regular posts with text, images, and videos, and headline articles (头条文章) with Markdown input via Chrome CDP. Use when user asks to "post to Weibo", "发微博",…

使用 social-auto-upload 的 `sau weibo` 登录微博并发布视频，可指定封面。Use when 用户要向微博发布视频或检查微博账号状态。

Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax…

Use this skill when the user asks MoviePilot to identify and organize a local or downloaded video/music file, season folder, recording, album directory, or mixed folder that automatic transfer did not…

Open the independent Data Annotation Training Cloud workbench and read saved project status when explicitly requested.