VM0Agent Skills
OpenAI
Use OpenAI models for text, image, and audio generation
OpenAI provides AI models for text generation, image creation, and more. This skill enables your agent to use GPT, DALL-E, Whisper, and other OpenAI APIs.
Required Environment
| Name | Type | Description |
|---|---|---|
OPENAI_API_KEY | secret | API key from OpenAI Platform |
Configuration
version: "1.0"
agents:
my-agent:
framework: claude-code
skills:
- https://github.com/vm0-ai/vm0-skills/tree/main/openaiRun
Store your secret on the platform (recommended, one-time setup):
vm0 secret set OPENAI_API_KEY your-openai-api-keyThen run your agent - secret is automatically loaded:
vm0 run my-agent "generate an image"For CI/CD or temporary overrides, pass secrets at runtime: --secrets OPENAI_API_KEY=value. See Environment Variables for details.
Example Instructions
# Image Generation Agent
You use OpenAI DALL-E to create images based on descriptions.
## Workflow
1. Receive image description from user
2. Generate image using DALL-E
3. Save image to artifacts
4. Provide the image URL
## Guidelines
- Create detailed prompts for better results
- Specify style, mood, and composition
- Generate multiple variations when needed# Audio Transcription Agent
You use OpenAI Whisper to transcribe audio files to text.
## Workflow
1. Receive audio file path
2. Transcribe using Whisper API
3. Format the transcript with timestamps
4. Save as markdown file
## Supported Formats
- MP3, MP4, WAV, M4A
- Max file size: 25MB