Text-to-video and image-to-video generation.
The Video superskill lets your AI agent generate videos from text prompts or reference images using Veo 3.1, Kling V3 Pro, or Seedance 2.0 in resolutions up to 4K. Your agent can choose duration, aspect ratio, resolution, and audio settings, then track generation status and save finished videos as reusable assets.
Capabilities available out of the box.
Platforms and services your agent connects to.
CLI commands available with this superskill.
Generate a video from a text prompt or reference image using AI.
clawpow videos generateGet details and status of a video generation.
clawpow videos generation <generationId>List all video generations.
clawpow videos generations# Video
Generate AI videos from text prompts or image references, then review and download the finished results.
## When to Use
- User wants to generate a video from a text prompt
- User wants to turn a reference image into a video
- User needs a product demo, short ad, launch video, or social video
- User wants to compare generated video outputs across supported models
## How It Connects
- **Images** -> Use generated images as reference images for image-to-video prompts.
- **Social Media** -> Attach generated videos to posts using `--media` with the asset ID.
- **Documents** -> Save prompt notes, campaign briefs, or generation results in documents.
## Quick Start
Generate a video:
```bash
clawpow videos generate --prompt "A drone shot over mountains at sunset" --json
```
List generated videos:
```bash
clawpow videos generations --json
```
## Commands
### Generate Video
```bash
clawpow videos generate --prompt "A drone shot over mountains at sunset" --json
clawpow videos generate --prompt "Product reveal" --image ./product.png --model kling-v3-pro --json
clawpow videos generate --prompt "City timelapse" --model seedance-2.0 --duration 15 --json
clawpow videos generate --prompt "Abstract art" --model veo-3.1 --resolution 4k --no-audio --json
```
Generate a video from a text prompt, or from a text prompt plus a reference image.
**Options:**
- `--prompt <text>` (required) -- Text prompt describing the video
- `--model <name>` -- Model: veo-3.1, kling-v3-pro, seedance-2.0 (default: veo-3.1)
- `--image <path>` -- Reference image for image-to-video mode
- `--resolution <res>` -- 720p, 1080p, or 4k (default: 1080p)
- `--duration <seconds>` -- Duration in seconds (model-specific allowed values)
- `--aspect-ratio <ratio>` -- 16:9 or 9:16 (default: 16:9)
- `--no-audio` -- Disable audio generation
- `--json` -- Output as JSON
**Returns:** `{"generationId": "...", "status": "queued", "studioUrl": "...", "nextCommand": "clawpow videos generation <generationId>"}`
### Get Generation
```bash
clawpow videos generation <generationId> --json
```
Get details and status for a video generation.
**Options:**
- `<generationId>` (required) -- Video generation ID
**Returns:** Full generation object including prompt, model, status, asset ID, URL, and Studio URL.
### List Generations
```bash
clawpow videos generations --json
clawpow videos generations --status ready --json
```
List generated videos with optional status filter.
**Options:**
- `--status <status>` -- Filter by status: pending, processing, uploading, ready, failed
**Returns:** Array of video generation objects.
### Delete Generation
```bash
clawpow videos generate-delete <generationId> --json
clawpow videos generate-delete <generationId> --yes
```
Delete a generated video record.
**Options:**
- `<generationId>` (required) -- Video generation ID
- `--yes` -- Skip confirmation prompt
- `--json` -- Output as JSON
**Returns:** `{"deleted": true, "generationId": "..."}`
## Output Format
All commands support `--json` for structured output. Without `--json`, output is human-readable.
## Important Notes
- Always use `--json` for machine-parseable output
- Video generation is a paid operation (consumes credits based on model, resolution, duration, and audio)
- Generation listing, detail lookup, and deletion are free operations
- Generated videos are stored as assets and can be used in social posts
- Available models: veo-3.1 (best quality, supports 4K), kling-v3-pro (cinematic/dialogue), seedance-2.0 (native audio, multi-shot cuts)
Works great together with these.