Loading...
Loading...
Found 115 Skills
Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progress tracking, and local file saving. Use for generating videos from text descriptions, animating static images, creating cinematic content, and various aspect ratios. Requires TENSORSLAB_API_KEY environment variable. Video generation takes several minutes.
Professional AI Video Storyboard Designer. This skill must be used when users want to create videos, make storyboard scripts, generate AI video prompts, or plan video content structures. It covers all video types: short videos, commercials, educational content, brand videos, vlogs, micro-films, etc. Even if users only say "Help me make a video" or "I want to create content on the theme of XX", this skill should be triggered. It outputs professional storyboard designs + prompts that can be directly used in mainstream AI video tools like Seedance 2.0 (Jimeng), Sora, Kling, Runway, Veo, etc. Among them, Seedance 2.0 supports specialized output with multimodal @ reference syntax.
Animate a single image into a video using fal.ai Veo 3.1. Use when the user wants to create a video from a still image, animate a photo, or bring an image to life. Supports up to 8 seconds of video with optional audio.
UGC lifestyle b-roll video templates for brands. Contains 20 TikTok-native, lofi b-roll formats with shot-by-shot structure and AI video generation prompts. Use when the user wants to create lifestyle b-roll content — aesthetic scene-setting, product-in-context shots, mood pieces, or ambient footage for ads and social.
Use when generating dance or motion-transfer videos with Alibaba Cloud Model Studio AnimateAnyone (`animate-anyone-gen2`) using a detected character image and an action template. Use when cloning motion from a dance/action video into a target character image.
Craft professional video prompts for Google Veo 3.1 using cinematic techniques, audio direction, and timestamp choreography. Use when generating AI videos, creating video prompts, or working with Veo 3.
Enhance text storyboards into Seedance 2.0 video prompts one by one. Call this when the text storyboard is completed and needs to be converted into executable video prompts.
[QianWen] Generate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE). TRIGGER when: user wants to create, generate, or edit video content, mentions video generation/animation/video clips/Wan models, or explicitly invokes this skill by name (e.g. use qianwen-video-generation). DO NOT TRIGGER when: user wants to generate images (use qianwen-image-generation), understand/analyze existing videos (use qianwen-vision), text-only tasks.
Control video generation requests before execution. Use this when the user asks for a simple clip, storyboard video, UGC video, podcast clip, reference video, talking-head, image-to-video, text-to-video, or research-handoff video and the skill must classify the request before handing it to video-request-architect and a runner such as seedance-submitter or video-batch-runner.
Quick start guide for Tavus Conversational Video Interface (CVI). Use when starting a real-time video conversation, creating your first persona, or testing the CVI API. Covers the minimal setup to get a conversation running.
higgsfield ai image/video generation using pw protocol wrappers. trigger when user wants to generate images or videos.
UGC video format templates for mobile app brands. Contains 15 TikTok-native, lofi video formats with shot-by-shot structure and AI video generation prompts. Focuses on the person and their physical relationship with their phone — reactions, rituals, and real moments — never screen content or app UI. Use when the user wants to create mobile app UGC content.