sticker-analyzer
Analyze images in media/stickers using Vision API to identify and filter meme/sticker content vs screenshots or documents.
Why use this skill?
Efficiently organize your sticker library with the OpenClaw Sticker Analyzer. Automatically identify and remove unwanted screenshots and documents using AI vision.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/autogame-17/sticker-analyzerWhat This Skill Does
The Sticker Analyzer skill is a specialized utility designed to bring order to your digital image library by distinguishing genuine stickers and memes from unintentional screenshots, documents, or personal photos. By leveraging the advanced vision capabilities of the Google Gemini 2.5 Flash model, this agent autonomously scans the ~/.openclaw/media/stickers directory. It evaluates each file's visual content, classifying them to ensure your media collection remains curated and focused on expressive communication assets rather than clutter. This skill is essential for users who frequently download chat media and want to maintain a clean workspace for their AI agents.
Installation
To install this skill, use the ClawKit CLI by running: clawhub install openclaw/skills/skills/autogame-17/sticker-analyzer. Once installed, ensure you have the Google AI SDK installed in your environment via npm install @google/generative-ai. You must then provide a valid API key from Google AI Studio. Add GEMINI_API_KEY=your_key_here to your .env file to authorize the agent to perform vision analysis.
Use Cases
This skill is perfect for automated library management. It is primarily used by power users who wish to purge "dead" images from their sticker folders. It can also be integrated into broader automated workflows where an agent needs to categorize incoming media files based on their utility (e.g., separating meme content for replies versus administrative screenshots for archival).
Example Prompts
- "OpenClaw, scan my sticker folder and delete all images that aren't memes or stickers."
- "Please analyze my media library and report how many screenshots I accidentally saved in the sticker folder."
- "Clean up my sticker collection by filtering out any document captures found in
~/.openclaw/media/stickers."
Tips & Limitations
While the skill is highly accurate, it is best utilized periodically. Since it uses Gemini 2.5 Flash, it is optimized for high-speed performance, but please note that large batches of images may consume your API quota. Ensure your file permissions allow the agent to read from and write to the target directory. If the model is uncertain about an image, it is programmed to lean toward caution to prevent the accidental deletion of important files.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-autogame-17-sticker-analyzer": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-read, file-write, external-api
Related Skills
AB-Agents-Vision-MiniMax
👁️ Image analysis via MiniMax VL API. Describe images, extract text from screenshots, analyze photos. Requires MiniMax Token Plan API key (free tier available).
AB-Agents-Vision
👁️ Image analysis using MiniMax VL API. Describe images, extract text from screenshots, analyze photos. Works with local files and URLs. Simple shell wrapper.
ekyc-suite
KYC and eKYC identity verification suite for AI agents — 8 financial-grade biometric and document verification capabilities in one skill. Face comparison and face matching (similarity score 0-100), face liveness detection for selfie verification (anti-deepfake, anti-fraud screening), video liveness detection (deepfake detection with auto-retry), document OCR for ID card, bank card, driver license, and vehicle license, plus media labeling with 15+ image analysis attributes for fraud prevention and compliance. Use for: know-your-customer (KYC) onboarding, identity verification, face recognition and face verification, AML compliance checks, fintech customer onboarding, biometric selfie verification, document verification, deepfake and AI-generated content detection, anti-fraud risk screening, and AI security audits. Trigger when user says "compare two faces", "is this photo AI-generated", "is this video real", "read ID card", "read bank card number", "read driver's license", "read vehicle license", "check for mask", "detect coercion", "check if in car", "do KYC", "ekyc", "verify identity". Do NOT use for: conceptual KYC questions (no actual image processing), requests to transmit names/ID numbers as text.