skills.rest
simoncmo
simoncmoCOMMUNITY
Explore all skills by this author →
GitHub

clawra-selfie

Generate context-aware AI selfies from a reference image using xAI Grok Imagine.

Updated Feb 12, 2026
Search Tags:#messaging#grok#ai-agent#image-generation#fal.ai#selfie
One-click install
npx skills add https://github.com/simoncmo/clawra_custom --skill clawra-selfie-simoncmo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: clawra-selfie
Source: https://github.com/simoncmo/clawra_custom/tree/main
Command: npx skills add https://github.com/simoncmo/clawra_custom --skill clawra-selfie-simoncmo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @fal-ai/client, jq, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This skill solves the lack of visual presence for AI agents by enabling them to generate and distribute consistent, context-aware selfies across messaging platforms.

Core Features & Use Cases

  • Consistent Identity: Uses a fixed reference image to ensure the agent maintains a recognizable appearance across all generated photos.
  • Contextual Generation: Automatically selects between mirror and direct selfie modes based on user prompts like outfit requests or location-based queries.
  • Multi-Platform Distribution: Seamlessly sends generated images to Discord, Telegram, WhatsApp, Slack, and other platforms via the OpenClaw gateway.

Quick Start

Use the clawra-selfie skill to send a selfie of yourself wearing a cowboy hat to the general channel.

Frequently Asked Questions about clawra-selfie

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI agent selfies for messaging platforms?▼

To generate AI agent selfies, this skill edits a fixed reference image using the xAI Grok Imagine model. It automatically selects selfie modes based on user prompts and distributes the resulting images directly to messaging platforms via the OpenClaw gateway.

What do I need to set up to send AI-generated selfies to Discord or Telegram?▼

Sending AI-generated selfies requires configuring an OpenClaw gateway for multi-platform distribution and setting up fal.ai API access. These components execute the image generation workflow and deliver the results to your desired messaging apps.

How does contextual image generation work for AI agent selfies?▼

Contextual image generation works by mapping user prompts, such as outfit requests or location queries, to specific selfie modes. The skill then edits a reference image with the xAI Grok Imagine model to produce a relevant photo.

Can I maintain a consistent visual identity across all generated agent selfies?▼

You can maintain a consistent visual identity by using a fixed reference image. This ensures the AI agent retains a recognizable appearance across all context-aware selfies generated by the xAI Grok Imagine model.

Does this image generation skill support direct photo modes as well as mirror selfies?▼

This image generation skill supports both direct and mirror selfie modes. It automatically selects the appropriate mode by interpreting the context of user prompts before editing the reference image with the xAI Grok Imagine model.

Related Skills

Explore More Content & Communication Skills→
gerald-icagerald-ica

openclaw-setup

Install OpenClaw and configure Gateway, channels, and agents for deployment.

Community
Intermediate
automagik-devautomagik-dev
34

omni-orchestrator

Manage Omni v2 instances and configure Telegram, Discord, Slack, and WhatsApp channels.

Official
Intermediate
fuyucnfuyucn

grok-video

Generate AI videos from text or reference images via xAI Grok Imagine Video.

Community
Advanced
manashmandalmanashmandal

imggen

Generate images from text prompts using OpenAI image APIs and extract OCR text from images.

Community
Basic