ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

sora

Generate videos from text prompts or reference images using OpenAI Sora. ✅ USE WHEN: - Need AI-generated video from text description - Want image-to-video (animate a still image) - Creating cinematic/artistic video content - Need motion/animation without lip-sync ❌ DON'T USE WHEN: - Need lip-sync (person speaking) → use veed-ugc or ugc-manual - Just need image generation → use nano-banana-pro or morpheus - Editing existing videos → use Remotion - Need UGC-style talking head → use veed-ugc INPUT: Text prompt + optional reference image OUTPUT: MP4 video (various resolutions/durations)

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/pauldelavallaz/sora
Or

Sora Video Generation

Generate videos using OpenAI's Sora API.

API Reference

Endpoint: POST https://api.openai.com/v1/videos

Parameters

ParameterValuesDescription
promptstringText description of the video (required)
input_referencefileOptional image that guides generation
modelsora-2, sora-2-proModel to use (default: sora-2)
seconds4, 8, 12Video duration (default: 4)
size720x1280, 1280x720, 1024x1792, 1792x1024Output resolution

Important Notes

  • Image dimensions must match video size exactly - the script auto-resizes
  • Video generation takes 1-3 minutes typically
  • Videos expire after ~1 hour - download immediately

Usage

# Basic text-to-video
uv run ~/.clawdbot/skills/sora/scripts/generate_video.py \
  --prompt "A cat playing piano" \
  --filename "output.mp4"

# Image-to-video (auto-resizes image)
uv run ~/.clawdbot/skills/sora/scripts/generate_video.py \
  --prompt "Slow dolly shot, steam rising, warm lighting" \
  --filename "output.mp4" \
  --input-image "reference.png" \
  --seconds 8 \
  --size 720x1280

# With specific model
uv run ~/.clawdbot/skills/sora/scripts/generate_video.py \
  --prompt "Cinematic scene" \
  --filename "output.mp4" \
  --model sora-2-pro \
  --seconds 12

Script Parameters

FlagDescriptionDefault
--prompt, -pVideo description (required)-
--filename, -fOutput file path (required)-
--input-image, -iReference image pathNone
--seconds, -sDuration: 4, 8, or 128
--size, -szResolution720x1280
--model, -msora-2 or sora-2-prosora-2
--api-key, -kOpenAI API keyenv var
--poll-intervalCheck status every N seconds10

API Key

Set OPENAI_API_KEY environment variable or pass --api-key.

Prompt Engineering for Video

Good prompts include:

  1. Camera movement: dolly, pan, zoom, tracking shot
  2. Motion description: swirling, rising, falling, shifting
  3. Lighting: golden hour, candlelight, dramatic rim lighting
  4. Atmosphere: steam, particles, bokeh, haze
  5. Mood/style: cinematic, commercial, lifestyle, editorial

Example prompts:

Food commercial:

Slow dolly shot of gourmet dish, soft morning sunlight streaming through window, 
subtle steam rising, warm cozy atmosphere, premium food commercial aesthetic

Lifestyle:

Golden hour light slowly shifting across mountains, gentle breeze rustling leaves, 
serene morning atmosphere, premium lifestyle commercial

Product shot:

Cinematic close-up, dramatic lighting with warm highlights, 
slow reveal, luxury commercial style

Workflow: Image → Video

Metadata

Stars1217
Views2
Updated2026-02-20
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-pauldelavallaz-sora": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

brand-analyzer

Analyze brands to generate comprehensive brand identity profiles (JSON). Use when the user wants to analyze a brand, create a brand profile, or needs brand data for ad generation. Stores profiles for reuse across Ad-Ready, Morpheus, and other creative workflows. Can list existing profiles and update them.

pauldelavallaz 1217

ugc-campaign-pipeline

Complete UGC video campaign pipeline: product → hero image → variations → videos → edited final. ✅ USE WHEN: - User says "crear campaña UGC" or "pipeline completo" - Need end-to-end UGC video production - Starting from product image/URL → final edited video - Want the full Doritos-style workflow ❌ DON'T USE WHEN: - Just need one step (use individual skills) - Already have final videos, just editing → use Remotion - Only need images, no video → use Morpheus only OUTPUT: Edited MP4 video with multiple scenes + subtitles + logo

pauldelavallaz 1217

nano-banana-pro

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

pauldelavallaz 1217

multishot-ugc

Generate 10 perspective/angle variations from a single image for multi-shot UGC videos. ✅ USE WHEN: - Have a hero image and need camera angle variations - Creating multi-scene UGC videos (need different shots) - Want close-ups, wide shots, side angles from one source - Building a video with scene changes ❌ DON'T USE WHEN: - Don't have a hero image yet → use morpheus-fashion-design first - Need completely different scenes/locations → use Morpheus multiple times - Just need one image → skip this step - Want to edit images manually → use nano-banana-pro INPUT: Single image (person with product) OUTPUT: 10 PNG variations with different perspectives TYPICAL PIPELINE: Morpheus → multishot-ugc → select best 4 → veed-ugc each → Remotion edit

pauldelavallaz 1217

morpheus-fashion-design

Generate professional advertising images with AI models holding/wearing products. ✅ USE WHEN: - Need a person/model in the image WITH a product - Creating fashion ads, product campaigns, commercial photography - Want consistent model face across multiple shots - Need professional lighting/camera simulation - Input: product image + model reference (or catalog) ❌ DON'T USE WHEN: - Just editing/modifying an existing image → use nano-banana-pro - Product-only shot without a person → use nano-banana-pro - Already have the hero image, need variations → use multishot-ugc - Need video, not image → use veed-ugc after generating image - URL-based product fetch with brand profile → use ad-ready instead OUTPUT: Single high-quality PNG image (2K-4K resolution)

pauldelavallaz 1217