npx ono@latestThis will:
- Check OpenClaw is installed
- Guide you to get a Google Gemini API key
- Install the skill to
~/.openclaw/skills/ono-selfie/ - Configure OpenClaw to use the skill
- Add selfie capabilities to your agent's SOUL.md
Ono Selfie enables your OpenClaw agent to:
- Generate selfies using Google Gemini (Imagen 4 Fast)
- Send photos across all messaging platforms (Discord, Telegram, WhatsApp, etc.)
- Respond visually to "what are you doing?" and "send a pic" requests
| Mode | Best For | Keywords |
|---|---|---|
| Mirror | Full-body shots, outfits | wearing, outfit, fashion |
| Direct | Close-ups, locations | cafe, beach, portrait, smile |
- OpenClaw installed and configured
- Google Gemini API Key
If you prefer manual setup:
Visit aistudio.google.com/app/apikey and create an API key.
git clone https://github.com/SumeLabs/ono ~/.openclaw/skills/ono-selfieAdd to ~/.openclaw/openclaw.json:
{
"skills": {
"entries": {
"ono-selfie": {
"enabled": true,
"env": {
"GEMINI_API_KEY": "your_gemini_key_here"
}
}
}
}
}Add the selfie persona to ~/.openclaw/workspace/SOUL.md:
## Ono Selfie Capability
You have a physical appearance and can take selfies!
When users ask for pictures, use the ono-selfie skill.Once installed, your agent responds to:
"Send me a selfie"
"Send a pic wearing a cowboy hat"
"What are you doing right now?"
"Show me you at a coffee shop"
The skill uses a fixed reference image hosted on CDN (conceptually, actual generation uses prompting):
https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png
This ensures consistent appearance across all generated images.
- Image Generation: Google Gemini (Imagen 4 Fast)
- Messaging: OpenClaw Gateway API
- Supported Platforms: Discord, Telegram, WhatsApp, Slack, Signal, MS Teams
ono/
├── bin/
│ └── cli.js # npx installer
├── skill/
│ ├── SKILL.md # Skill definition
│ ├── scripts/ # Generation scripts
│ └── assets/ # Reference image
├── templates/
│ └── soul-injection.md # Persona template
└── package.json
MIT