video-generator
Video Generator lets you create polished short-form videos by writing text prompts, choosing between Google VEO 3.1 for synchronized audio or OpenAI Sora for visual quality and longer clips up to 12 seconds. The skill includes storyboarding guidance, prompt structuring rules, and cost estimates to help you iterate efficiently.
Video Generator creates professional short-form videos from text prompts using Google VEO 3.1 or OpenAI Sora.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-08
Video Generator creates professional short-form videos from text prompts using Google VEO 3.1 or OpenAI Sora. Video Generator lets you create polished short-form videos by writing text prompts, choosing between Google VEO 3.1 for synchronized audio or OpenAI Sora for visual quality and longer clips up to 12 seconds. The skill includes storyboarding guidance, prompt structuring rules, and cost estimates to help you iterate efficiently.
Use it when
- Video Generator helps you choose between VEO 3.1 and Sora based on your priorities.
- Yes.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Install
cdeistopened/skill-stack/video-generator · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I generate AI videos with Google VEO or OpenAI Sora?
Video Generator lets you create short-form videos by writing text prompts and selecting your preferred engine. Google VEO 3.1 excels at synchronized audio and dialogue, while OpenAI Sora prioritizes visual quality and supports clips up to 12 seconds. The skill guides you through prompt structuring, storyboarding, and choosing the right tool for your needs.
What's the difference between VEO and Sora in Video Generator?
Video Generator helps you choose between VEO 3.1 and Sora based on your priorities. VEO 3.1 is optimized for native audio and synchronized dialogue, making it ideal for videos with sound effects or voiceovers. Sora delivers superior visual quality and longer durations up to 12 seconds, better for cinematic or complex scenes.
Can Video Generator create vertical videos for social media?
Yes. Video Generator supports vertical 9:16 format optimization for Reels, TikTok, and other social platforms. The skill includes guidance on framing prompts for vertical layouts and helps you iterate quickly with fast drafts before final renders to maximize engagement on mobile-first channels.
Does Video Generator support video generation with native audio?
Video Generator prioritizes audio support through Google VEO 3.1, which creates videos with synchronized audio and dialogue. The skill provides prompt structuring rules to ensure your audio requirements are clearly communicated, and includes cost estimates to help you plan multi-iteration workflows efficiently.
How does Video Generator help me iterate on video concepts?
Video Generator enables rapid iteration by helping you structure prompts effectively, storyboard scenes before generation, and estimate costs upfront. You can create fast drafts to test concepts, then refine based on results before committing to final renders, reducing wasted generation credits.
What guidance does Video Generator provide for prompt writing?
Video Generator includes comprehensive prompt structuring rules, storyboarding guidance, and best practices for both VEO and Sora. The skill helps you craft clear, detailed text prompts that maximize generation quality, whether you're making product demos, podcast headers, or professional social content.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Video Generator
Generate professional short-form videos using Google VEO 3.1 (with native audio) or OpenAI Sora (high visual quality, up to 12s).
Prerequisites & Setup
API Keys
You need at least one. Both gives you maximum flexibility.
VEO (Google): 1. Go to Google AI Studio 2. Sign in with your Google account 3. Click "Create API Key" 4. Copy the generated key
export GEMINI_API_KEY=your_gemini_key_here
Sora (OpenAI): 1. Go to OpenAI Platform 2. Create a new API key 3. Copy the generated key
export OPENAI_API_KEY=your_openai_key_here
Install Dependencies
pip install google-genai requests
Available Models
| Provider | Model | CLI --model |
Best For |
|---|---|---|---|
| VEO | Veo 3.1 Standard | standard |
(truncated - see the full file via the links below)
File tree — 2 files
.claude/skills/video-generator/SKILL.md
.claude/skills/video-generator/scripts/generate_video.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate professional short-form videos using AI with text prompts”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Higgsfield Operator teaches you to generate cinematic AI videos using Higgsfield's unified platform, which combines Sora 2, Veo 3.1, WAN 2.5, Kling 2.6, and other models with professional controls like camera simulation and character consistency. Learn image-to-video workflows, VFX application, talking-head creation, and Python SDK automation across 70+ camera presets and 23+ effects.
Prompt Translator converts video prompts across models by matching your input to one of 10 reference scenarios, then applying the target model's format rules from a lookup table of 110 cross-model examples. It preserves all semantic content while restructuring labels and phrasing to fit each model's official formula.
Access fal.ai's complete text-to-video generation system with support for multiple models including Kling 2.6 Pro, Sora 2, LTX-2 Pro, Runway Gen-3 Turbo, and Luma Dream Machine. Configure video duration, aspect ratio, and motion prompts to generate cinematic content with optional native audio. Use quality-focused models for final output or fast-iteration options for previews.
Video Gen automates video creation by converting text descriptions into finished video files through Veo and Sora AI models. Choose your preferred model, specify video length and aspect ratio, and optionally provide a reference image for Sora-powered generations. The skill handles the full workflow from prompt collection through status polling to final delivery.
Learn structured approaches to writing prompts that generate high-quality videos across leading AI models. This guide covers shot composition, camera techniques, lighting vocabulary, and style keywords, plus model-specific tips and real-world examples for product demos, documentaries, and more.
Seedance 2.0 is ByteDance's unified video-and-audio model, available as OpenMontage's premium default for trailers, teasers, and motion-heavy work. It handles single-pass synchronized audio, multiple shots in one generation, director-level camera language, lip-sync from dialogue, and character identity consistency across cuts. Access it via fal.ai, Replicate, Runway, Higgsfield, or other aggregators by routing through `video_selector` with `preferred_provider="seedance"`.
More skills Sora Video (NOASSERTION) · doubao-tts (MIT)