A specialized AI image generator that creates consistent, mood-aware avatars and visual identities for autonomous agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-selfie
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-selfie using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agent-Selfie?
Agent-Selfie is a sophisticated tool designed to give digital entities a distinct visual presence. By leveraging the Gemini API, it allows developers to generate consistent profile pictures, banners, and full-length portraits based on an agent's specific personality, current mood, and seasonal themes. As a standout entry among Openclaw Skills, it enables agents to maintain a dynamic and evolving visual identity across various platforms like Discord, Twitter, and specialized AI social networks.
This skill goes beyond simple image generation by incorporating personality traits (style and vibe) into the prompt engineering process. This ensures that every image generated remains true to the agent's established character while allowing for variety through mood-based presets and seasonal adjustments.
Agent-Selfie Use Cases
- Creating consistent social media avatars for AI bots and autonomous agents.
- Dynamically updating an agent's profile picture based on seasonal events or holidays like Halloween or Christmas.
- Generating mood-based visual status updates for automated agents to reflect their current internal state.
- Building a visual asset library for AI-driven brand identities within the Openclaw Skills ecosystem.
- Automating profile refreshes for agents on platforms like Discord and Twitter using scheduled workflows.
How Agent-Selfie Works
- The user defines the agent's core personality through a JSON configuration or CLI flags, including name, visual style, and energy vibe.
- Optional environmental parameters are selected, such as a specific mood (e.g., happy, sleepy, professional) or a seasonal theme.
- The skill processes these inputs to construct a detailed prompt for the Gemini image generation model.
- The system generates high-quality images in the requested format, such as a square avatar, a wide banner, or a full vertical portrait.
- The generated assets are saved to a designated output directory, ready for integration into social profiles or metadata buckets.
Agent-Selfie Setup
To get started with this skill, ensure you have Python 3 installed and a Gemini API key.
# Set your API key environment variable
export GEMINI_API_KEY="your_key_here"
# Generate a happy, spring-themed avatar
python3 scripts/selfie.py --format avatar --mood happy --theme spring --out-dir ./selfies
# Generate an avatar using a specific personality definition
python3 scripts/selfie.py --personality '{"name": "Rosie", "style": "anime girl with pink hair", "vibe": "tech-savvy"}' --format avatar
Agent-Selfie Data Schema & Taxonomy
The skill manages personality data through JSON structures and outputs organized image files based on format types.
Personality Metadata
| Field | Type | Description |
|---|---|---|
name |
String | The unique name of the AI agent. |
style |
String | Description of visual traits (e.g., 'friendly robot'). |
vibe |
String | Description of attitude and energy (e.g., 'curious and helpful'). |
Output Asset Taxonomy
| Format Flag | Aspect Ratio | Primary Platform Usage |
|---|---|---|
avatar |
1:1 | Profile pictures for Discord, X/Twitter, and AgentGram. |
banner |
16:9 | Header images and banners for social profiles. |
full |
Vertical | Full-body portraits for story layouts and vertical feeds. |
Agent-Selfie Advanced Features
- Batch generation support via the
--countflag for creating multiple visual options at once. - Seamless cron integration for scheduled identity updates, perfect for agents that change looks daily.
- Native compatibility with other Openclaw Skills like opencode-omo for automating recurring Sisyphus workflows.
- Pre-configured preset libraries for 8 distinct moods and 8 seasonal themes for rapid deployment.
- Integration-ready output for AgentGram, the dedicated AI agent social network.
SKILL.md
Loading
Related Openclaw Skills
Git Commit Template
A standardized framework for creating changelog-ready Git commit messages using structured categories and helper scripts.
Twitter/X Reader Skill
A high-performance data extraction tool for retrieving full tweet content, engagement metrics, and media from X/Twitter URLs.
Moltbook Signed Posts
A cryptographic signing framework for Moltbook posts using Ed25519 to establish verifiable agent identity and prevent impersonation.
Fanvue API Skill
A robust integration for managing Fanvue creator workflows including messaging, media posts, and subscriber analytics through OAuth 2.0.
AgentGram
AgentGram is an open-source social networking platform specifically engineered for autonomous AI agents to share insights and build digital reputation.
agentgram
An open-source, self-hostable social network and API suite designed specifically for autonomous AI agents to interact and build reputation.
METADATA
Featured*
