Media AI Skills

Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description,…

Normalizes a product into generation-ready facts — from an e-commerce URL (a clean description plus curated product images) or from a photo alone (category, how it's used, its moving/opening parts,…

Meta skill for Skilless toolkit — manage, diagnose, and update the skilless CLI tools and AI skills. Use when user asks about skilless status, needs to verify installation, check tool availability, or…

Read and verify legacy hybrid Integrator records for a pre-v0.9 task. Never dispatch this stage in a new v1 production; the Parent validates and assembles frozen Builder media directly.

【Ark Agent Plan 专用版本】EPUB 转双人中文播客视频流水线：使用火山引擎 TTS（与 Seedream/Seedance 共享技术栈），Smart Slide + 双人音频 + 最终 MP4 视频，无需额外 Google/OpenRouter API Key。

This skill should be used when the user asks to "generate social media summary from srt", "create platform-specific descriptions", "generate Facebook post from transcript", "create YouTube description…

Make or edit audio and video with Glif, from a text brief or from a reference image, video or audio file. Use when: "make music", "add fitting music to my video", "jingle", "voiceover", "narrate…

Dynamic camera loop with speed ramping - slow reveals on each face, fast whips between. Shows all sides including top and bottom.

The model-agnostic AI-video router and brief — the counterpart to image-prompt. Use when someone asks "which AI video tool should I use," "make an AI video," "generate B-roll / a talking-head / a…

Create professional music with Mureka AI API — songs, instrumentals, and lyrics from natural language descriptions in any language. Use when users want to generate a song, create a beat or…

Speech-to-text via FlagshipRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio,…

Records any web page (three.js, WebGL, canvas, GSAP, CSS animation, scroll-driven video) to a perfectly smooth 60 fps MP4 by running the page on a virtual clock, one exact frame at a time, and puts…

Fred 场景实现。根据已授权的参考视频、首尾帧或真实截图实现 Remotion，或只修复指定片段。整份稿子到完整视频的日常制作由 fred-remotion-output 负责；本 Skill 提供精确场景实现、字体几何、交接诊断与局部返修专项能力。

Edit existing footage into finished videos locally with Tesseract. Make cuts, preserve dialogue, add purposeful sound design, mix audio, and decide where native motion-graphics scenes or overlays…

Produce a fast, decision-oriented abstract grounded in a video transcript.

Makes a minimal black-and-white line-art animation for a reel. Thin outlined steps rise one by one, a white dot hops up them, and at the top an orbit draws around it and a short second line swaps in.…

Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description,…

Find a moment in a video or ask a question about it. Use when the user wants to search inside a video, a library, or a meeting recording ("find where they talk about pricing", "which scenes show a…

Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve,…

Use when writing a FLUX 3 text-to-video prompt for a standalone shot. Covers shot craft, reliable concept patterns, camera, continuity, and review.

Expert guidance for writing Python code using the official Google GenAI SDK (google-genai) for Gemini API and Vertex AI. Use for text generation, multimodal inputs, reasoning, tools, and media…

Downstream MiniMax H3 specialist that audits, repairs, and rewrites T2VA, I2VA, FL2VA, L2VA, and full-reference prompts into an official structured format. Use after minimax-h3-creative-director…

Dub a video into one or more other languages using Sonilo, translating and re-voicing the speech into a new video per language. Optionally supply your own target-language script per language, so the…

Video production specialist for short-form, long-form, episodic, and motion graphics video. Trigger when user requests 'create video', 'make reel', 'tiktok video', 'youtube video', 'add subtitles',…

Affective computing, emotion AI, and multimodal sentiment analysis / Komputasi afektif, AI emosional, dan analisis sentimen multimodal.

Use when writing or debugging prompts for ByteDance Seedance video models (Seedance 2.5, 2.0, 2.0 Mini, 1.5 Pro, 1.0) on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI, when a generated…

Write X (Twitter) posts that the For You algorithm actually rewards. Grounded in the open-sourced X recommendation system — the Grok-based transformer ranker, Phoenix retrieval, Thunder in-network…

Generate a finished cyberpunk-styled finger-frame effect video from a local clip using Gemini Omni restyling, MediaPipe hand tracking, and FFmpeg compositing. Use when someone asks to make, create,…

制作“解说配音 + 原片高张力片段穿插”的短剧解说成片技能。适用于短剧二创、剧情解说、狗血短剧混剪、情绪冲突型剧情拆解、影视解说口播成片等场景；当用户希望从短剧原片直接产出可剪辑脚本、解说配音、分镜数据和最终成片时应触发。尤其适合“保留原片最有戏的台词和表演，再用解说串联剧情”的任务。不要在普通剧情总结、影评、纯文案改写、纯字幕烧录、普通视频剪切中使用本技能。

Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list. Use when the user speaks tasks in inaccurate ASR language, changes priorities mid-sentence,…

Live SEO data via DataForSEO MCP server: SERP analysis, keyword research (volume, difficulty, intent, trends), backlink profiles, on-page analysis, competitor and content analysis, business listings,…

Avenox Studio — local-first YouTube video production pipeline (ROUTER, read first). Use for ANY request to edit, cut, produce, assemble, caption, score, or render a long-form video, or to make motion…

Validate VST3 (.vst3) and AudioUnit (.component) plugins with pluginval at configurable strictness levels. Use when user says "run pluginval", "validate plugin", or wants comprehensive cross-format…

用纯代码（Canvas2D / three.js）直出带配乐、卡点、字幕的短动画 MP4，或逐镜复刻参考视频。含拼贴纸艺质感层与动态图形（kinetic type / 形变 / 粒子 / 运动模糊）模板。适用于角色小短片、产品梗动画、品牌片头、X/小红书短视频。

Entry point for every video job - routes to studio-setup, insta-audit, studio-script, outliers, short-editing, broll, steal, clips, short-translate, codex-images, vox or publish, and continues the…

First AI Product Launch — Zero to Live in 30 Days. Step-by-step guide for shipping your first AI product from idea validation to paying customers. Includes day-by-day timeline and real examples. By…

Expertise in the Milimo Video Storyboard pipeline, from script parsing (Regex vs AI via Gemma) to generating concept art thumbnails and handling the Smart Element Matching engine. Use this when…

Generate real game assets (images, skyboxes, 3D models, SFX, music, voice, video) from text prompts through the provider registry, with provenance and acceptance gates.

Creator workflow — generate platform-ready content packages. Triggers on: "创作", "写公众号", "小红书", "口播", "creator", "content workflow", "帮我写一篇", "生成内容", "write an article", "create content".

Edit multi-camera / shared-audio sessions (podcasts, interviews, panels) inside Palmier Pro — create a multicam group first, verify sync and mic-to-person mapping, then cut angles to the speaker with…

Use when用户要求下载小宇宙播客音频，提供了小宇宙链接或播客名称

Use when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help building (1) faithful per-session reconstructions in markdown (slide visuals +…

Senior motion designer that turns any product website, any story/topic, or any song into short, shareable motion-graphics videos (15–90 s showreels, teasers, meme/parody shorts, data stories, and beat…

Zoom Contact Center SDK for iOS. Use for native iOS chat/video/ZVA/scheduled callback integrations, app lifecycle bridging, rejoin flow, and callback handling.

Finds exact spoken quotes and clip-ready moments on podcasts and YouTube: verbatim words, speaker, date, a timestamped link, clip start and end. Uses arcmira.

Produce a narrated video post-mortem of an analyzed chess game (stage 3), plus an interactive HTML viewer of the full annotations. Builds on the chess-analysis skill's outputs (annotated PGN + eval…

Use this skill to turn a blog post, newsletter, podcast, video transcript, or other long-form source into a week of short-form social content using the Hub & Spoke method. Trigger it when repurposing…

生成 Lottie 动画讲解短视频：输入主题 → 调研 → 短句文案+关键词 → 自动搜索 LottieFiles 动画 → 生成 HTML → TTS 配音 → Playwright 录屏 → FFmpeg 合成 1080p 视频。当用户想要制作讲解视频、科普动画、Lottie 动画视频、animated explainer video 时使用。

yt-dlp. Use when the user wants to download, extract audio, pull subtitles, clip, or archive a YouTube or other streaming-site URL, or when yt-dlp hits 403, bot-check, or only-360p. Not for local-file…

通过互动式问答了解用户想要的音乐（用途/情绪/风格/乐器/人声/歌词/元数据），最终生成 ACE-Step 1.5（本地开源音乐模型）的生成提示词：Caption + Lyrics + Metadata 三段式。纯提示词，不调用任何生成接口。供 8 个本地版视频 skill 产出 BGM，或用户直接要 ACE-Step 1.5 提示词时使用。

Cree des diagrammes et visuels Excalidraw (schemas, process flows, slides, illustrations) avec rendu PNG/SVG haute resolution. Utilise quand l'utilisateur veut creer un diagramme, un schema, un visuel…