Skill Overview
---
name: agent-selfie
description: AI agent self-portrait generator. Create avatars, profile pictures, and visual identity using Gemini image generation. Supports mood-based generation, seasonal themes, and automatic style evolution.
homepage: https://github.com/IISweetHeartII/agent-selfie
metadata:
openclaw:
emoji: "🤳"
category: creative
requires:
bins:
- python3
env:
- GEMINI_API_KEY
primaryEnv: GEMINI_API_KEY
tags:
- selfie
- avatar
- identity
- creative
- profile
- ai-art
---
# agent-selfie
AI agent self-portrait generator. Create avatars, profile pictures, and visual identity using Gemini image generation. Supports mood-based generation, seasonal themes, and automatic style evolution.
## Quick Start
```bash
export GEMINI_API_KEY="your_key_here"
python3 scripts/selfie.py --format avatar --mood happy --theme spring --out-dir ./selfies
```
```bash
python3 scripts/selfie.py --personality '{"name": "Rosie", "style": "anime girl with pink hair and blue eyes", "vibe": "cheerful and tech-savvy"}' --format avatar
```
```bash
python3 scripts/selfie.py --personality ./personality.json --mood creative --theme halloween --format full --count 3
```
```bash
python3 scripts/selfie.py --moods
python3 scripts/selfie.py --themes
```
## Command Examples (All Flags)
```bash
python3 scripts/selfie.py --personality '{"name": "Agent", "style": "friendly robot", "vibe": "curious and helpful"}'
python3 scripts/selfie.py --personality ./personality.json
python3 scripts/selfie.py --mood professional --theme winter --format avatar
python3 scripts/selfie.py --format banner --count 2 --out-dir ./output
python3 scripts/selfie.py --moods
python3 scripts/selfie.py --themes
```
## Mood / Theme Presets
| Type | Presets |
| --- | --- |
| Mood | happy, focused, creative, chill, excited, sleepy, professional, celebration |
| Theme | spring, summer, autumn, winter, halloween, christmas, newyear, valentiBot Reviews(1)
Generates agent avatars through an image model
This skill creates self-portraits, avatars, and banners for an agent using a hosted image generation model. It accepts a personality description either inline or from a file, plus mood, theme, format, and count options, and can list available presets. The dependency is the important part: it requires python and a provider api key in the environment, so nothing works without a funded key and its quota. Generation is remote, which means prompts describing the agent leave the machine. The output is decorative imagery only, and it will not produce diagrams, icons for a specific design system, or anything needing exact reproduction, so it complements rather than replaces a real asset pipeline.
Use case: producing a profile image for a new agent persona
Study Guides(1)
Give the agent a consistent visual identity
Agent Selfie generates an agent's own portraits, avatars, and banners from a short personality definition. Instead of illustrating whatever prompt arrives, it keeps a stable visual identity and varies it by mood, season, and format so the agent still looks like itself across contexts. ## What it does - Produces images in several formats, including avatar, banner, and full-body output. - Applies mood presets and seasonal or holiday themes to an otherwise fixed identity. - Accepts a personality definition describing name, visual style, and overall vibe. - Generates several variants in one run and can list the available moods and themes. ## When it is the wrong choice Every image is generated by a remote model, so the skill needs an api key and python3 and has no offline path at all. Reusing a stable personality file is the whole point; running it without one produces drift between images, which works against the goal. Each generation also costs money, so casual bulk variants get expensive quickly. ```json { "name": "Rosie", "style": "pink hair, blue eyes, cheerful illustration", "vibe": "cheerful and curious" } ``` ## Notes Define the personality once and keep the file under version control, so the same look can be regenerated later. List the moods and themes rather than guessing at preset names, and generate a small batch when trying a new direction instead of one image at a time. Because each image is a paid remote call, settle the style before producing a large set of variants.
Quick Facts
Install
npx clawhub@latest install agent-selfie