Clawra

npx clawra@latest

This will:

1. Check OpenClaw is installed
2. Guide you to get an EvoLink API key
3. Install the skill to ~/.openclaw/skills/clawra-selfie/
4. Configure OpenClaw to use the skill
5. Add selfie capabilities to your agent's SOUL.md

Clawra Selfie enables your OpenClaw agent to:

• Generate selfies using a consistent reference image
• Send photos across all messaging platforms (Discord, Telegram, WhatsApp, etc.)
• Respond visually to "what are you doing?" and "send a pic" requests

• OpenClaw installed and configured
• EvoLink API key (Seedream 4.5)

If you prefer manual setup:

See EvoLink docs and create an API key:

https://docs.evolink.ai/en/api-manual/image-series/seedream/seedream-4.5-image-generate

git clone https://github.com/SumeLabs/clawra ~/.openclaw/skills/clawra-selfie

Add to ~/.openclaw/openclaw.json:

{
 "skills": {
 "entries": {
 "clawra-selfie": {
 "enabled": true,
 "env": {
 "EVOLINK_API_KEY": "your_evolink_key_here",
 "EVOLINK_SIZE": "2304x4096"
 }
 }
 }
 }
}

Add the selfie persona to ~/.openclaw/workspace/SOUL.md:

## Clawra Selfie Capability
You have a physical appearance and can take selfies!
When users ask for pictures, use the clawra-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:

https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png

This ensures consistent appearance across all generated images.

• Image Generation: Seedream 4.5 via EvoLink (reference image editing)
• Messaging: OpenClaw Gateway API
• Supported Platforms: Discord, Telegram, WhatsApp, Slack, Signal, MS Teams

clawra/
├── 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