video▌

Generate videos with 40+ AI models including Veo, Seedance, Wan, and Grok via inference.sh CLI. \n \n Supports text-to-video, image-to-video, avatar animation, lipsync, video upscaling, and foley sound generation across multiple model families \n Access to Google Veo (3.1, 3, 2), ByteDance Seedance, Falai Wan, xAI Grok, and economical alternatives like P-Video and WAN models \n Includes utility tools for video upscaling, sound effect generation, and multi-clip merging with transitions \n Require

Write React components, get real MP4 videos. This skill teaches your AI agent how to build with Remotion — from a first animation to a production rendering pipeline.

Generate high-quality videos from structured prompts with optional reference image guidance. \n \n Creates JSON-formatted prompts specifying subject, style, camera work, dialogue, and audio elements \n Supports reference images to guide or anchor the first/last frame of generated videos \n Executes generation via Python script with configurable aspect ratio (default 16:9) \n Integrates with image-generation skill to create reference frames when needed \n

Help YouTubers/UP主 prepare video content: write structured scripts (口播稿), blog posts, and platform-specific publishing materials.

Structured prompting techniques for generating high-quality videos across multiple AI platforms. \n \n Covers eight video generation models (Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora) with model-specific optimization tips \n Provides a reusable prompt formula combining shot type, subject, action, setting, lighting, style, and technical parameters \n Includes reference tables for shot types, camera movements, lighting keywords, and visual aesthetics with practical examples \n Demonstrat

Programmable video production with Remotion, scene planning, asset orchestration, and validation gates for brand-consistent automated content. \n \n Generates videos from text instructions through a structured five-step workflow: spec definition, scene outlining, asset preparation, Remotion composition implementation, and QA rendering \n Supports multiple aspect ratios (16:9, 1:1, 9:16) and video lengths (30s–90s) with configurable tone, narration style, and language \n Includes scene templates,

Short video production is the art and science of creating engaging 15-60 second vertical videos optimized specifically for Xiaohongshu's mobile-first, algorithm-driven platform. This skill encompasses the complete workflow from concept through filming, editing, and optimization—combining compelling storytelling, visual appeal, rapid pacing, and concise delivery to capture viewer attention within milliseconds and retain it through completion. The core principle: on mobile platforms with endless c

Translate natural language video editing requests into ready-to-run FFmpeg commands. \n \n Supports 15+ operations: cut/trim, format conversion, aspect ratio changes, resolution scaling, compression, audio extraction, speed adjustment, GIF creation, rotation, watermarking, subtitle burning, and video merging \n Handles common aspect ratios (16:9, 4:3, 1:1, 9:16, 21:9) with automatic letterboxing and standard resolutions (4K, 1080p, 720p, 480p, 360p) \n Includes time format flexibility (HH:MM:SS,

$23

Convert still images to animated videos with model selection, motion prompting, and camera control. \n \n Six models available (Wan 2.5 i2v, Seedance, Fabric, Grok) with guidance on when to use each based on content type and motion style \n Motion prompting framework covering camera movement (pan, dolly, orbit, crane), subject motion (natural elements, character, liquid), and atmospheric effects \n Best practices emphasizing subtle motion over dramatic action, with structured prompt templates an