Results for “video-creation”

Draft a scene-by-scene video script with timing, visual direction, narration, and source attribution from upstream creator-media artifacts

Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

Generate formatted video scripts from transcripts, outlines, or topics with visual and audio columns

Ingest, index, search, edit, and generate video and audio content from files, URLs, live streams, or desktop capture.

When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Runway,' 'Kling,' 'Pika,' 'video generation,' 'AI avatar,'...

Generate video clips with Google Veo (Veo 3.1 / Veo 3.0) via a command-line script, with options for duration, aspect ratio, and model selection.

Generate videos or music as asynchronous media artifacts. Use this skill when the user asks for text-to-video, image-to-video, first-and-last-frame video, multi-reference-image video, music, a song, a soundtrack, or background music. This skill creates video/music files; it is not for text-to-speech.

Generates video production plans including shot lists, scripts, B-roll suggestions, music mood, thumbnail concepts, and platform-specific specs for reels, YouTube, and video ads.

AI辅助的视频编辑工作流程，用于剪辑、构建和增强实拍素材。涵盖从原始拍摄到FFmpeg、Remotion、ElevenLabs、fal.ai，再到Descript或CapCut最终润色的完整流程。适用于用户想要编辑视频、剪辑素材、制作vlog或构建视频内容的情况。

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

Generates a multi-part animated story video by establishing a consistent character, creating sequential scenes, and animating them using image generation and image-to-video models.

Writes engaging video scripts with hooks, transitions, B-roll suggestions, and call-to-action placement

AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.

Transform an approved video script into a Remotion build specification with scaffolded project directory, compositions, scene components, and render config

Create talking head videos with AI avatars, lipsync, and voiceover using the inference.sh CLI.

Generate video clips with Google Veo (Veo 3.1 / 3.0) via a Python script, supporting duration, aspect ratio, and model selection.

Generates a sequence of fullscreen video frames with cinematic visuals, auto-play, and metadata for Remotion/Hyperframes rendering.

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

Expert YouTube scriptwriting skill for creators who want to write videos that hold attention, deliver value, and grow a channel. Use this skill whenever the user wants to write or improve a YouTube video script, craft a stronger hook or intro, structure a video idea, write a YouTube title or description, or plan a video outline. Triggers: "write a YouTube script", "help me script my video", "I'm making a video about", "write an intro for my video", "help me with my hook", "write a YouTube description", "how should I structure this video", "make my script more engaging", or any request related to YouTube video content. Do NOT limit to obvious script requests — if the user has a topic or idea and mentions YouTube, use this skill.

Generate visual storyboards with AI image generation, covering shot types, camera angles, movement, continuity rules, and panel layout for video planning and pre-production.

Execute Python code in a safe sandboxed environment with 100+ pre-installed libraries for data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, and automation.

Generates high-fidelity UI screens, multi-page websites, DESIGN.md documentation, and React components from natural-language prompts using the Stitch MCP server, with support for prompt refinement and walkthrough video creation via Remotion.