CMS, document processing, and media generation.
Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".
Best practices for Remotion - Video creation in React
Generates and displays OVN-Kubernetes network topology diagrams showing logical switches, routers, ports with IP/MAC addresses in Mermaid format
Comprehensive technical diagramming toolkit for solutions architects, presales, and developers. Creates Azure architecture diagrams (700+ official Microsoft icons), business process flows (swimlanes, workflows), ERD diagrams (database schemas), project timelines, UI wireframes, and network topology diagrams. Perfect for proposals, documentation, and architecture reviews. Also generates diagrams from Bicep, Terraform, and ARM templates.
Extract frames or short clips from videos using ffmpeg.
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
Design intuitive user experiences following Jobs-era Apple principles. Use this skill when designing onboarding flows, empty states, dashboards, user journeys, CTAs, forms, or any UI that needs to anticipate user needs and reduce friction. Applies progressive disclosure, anticipatory design, and conversion optimization principles.
Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, etc.) using yt-dlp. Use this skill when users provide video URLs and want to download videos, extract audio, or need help with video download issues.
GIF动图切分工具，将超过指定帧数的GIF文件自动拆分成多个小文件。适用于微信公众号等平台上传GIF时遇到"帧数超限"的问题。
MiniMax-native multimodal workflow for image, video, voice, music, and media-processing tasks. Use when the user asks to generate image/video/audio assets, wants MiniMax-specific media APIs, needs TTS or voice workflows, wants reproducible local media outputs, or needs FFmpeg-style processing around generated media.
Draft and refine prompts for video generation models (text-to-video and image-to-video), and create character-sheet prompts for image models when the goal is character consistency before image-to-video. Use when a user asks for a "video prompt", a model-specific prompt such as Seedance 2.0, Ovi, Sora, Veo 3, Wan 2.2, LTX-2, or LTX-2.3, or a consistent-character prompt such as "character sheet prompt", "character turnaround", "character reference sheet", or "photographic identity sheet".
Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz with reference numbering
Generate images using Google's Gemini Nano Banana API. Supports standard (flash) and pro models. Use --pro flag for higher quality output with gemini-3-pro-image-preview.
Generate or edit images with Google Gemini. Alternative to DALL-E for image generation. Requires GEMINI_API_KEY.
Extract frames, thumbnails, or clips from video files using ffmpeg. Use when analyzing video content or creating previews.
