A comprehensive utility for searching, managing, and sending sticker and emoji images across various chat platforms.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install emo-img
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 emo-img 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 emo-img?
emo-img is a specialized tool designed to bring visual expression to AI-driven conversations. It allows agents to handle sticker images and 表情包 through a hybrid search system that queries local collections before searching the Tenor online database. By leveraging Openclaw Skills, this tool enables seamless media sharing across popular communication channels like WhatsApp, Discord, iMessage, and Telegram.
The skill provides a robust management layer for local media libraries, allowing for efficient tagging and retrieval. It effectively bridges the gap between text-based AI interactions and the rich, visual nature of modern chat, ensuring that agents can participate in digital culture using the same media formats as human users.
emo-img Use Cases
- Sending relevant reaction stickers or memes during active chat sessions.
- Managing a local library of frequently used emoji images for low-latency retrieval.
- Automating the search and download of trending content from Tenor based on user intent.
- Organizing a collection of 表情包 with multilingual tags for better cross-cultural communication.
How emo-img Works
- The agent identifies a user's intent to send a sticker or visual reaction within the conversation.
- The search command is triggered to look for matches in the local
~/.openclaw/stickers/directory. - If no local matches are found, the skill queries the Tenor API for online results.
- Selected online images are downloaded locally to ensure compatibility with the channel's media requirements.
- The file path is passed to the message tool's media field to deliver the image to the target chat channel.
- The local index is updated if new stickers are added or downloaded for future use.
emo-img Setup
To get started with this skill in the context of Openclaw Skills, ensure you have Python 3 installed and configured.
# The skill defaults to storing data in your home directory
# You can override the storage path if needed
export STICKER_DIR="/custom/path/to/stickers"
# Optional: Set a Tenor API key for unrestricted online searches
export TENOR_API_KEY="your_tenor_api_key"
# Add your first local sticker to the collection
python3 scripts/sticker.py add /path/to/image.gif --name "happy-cat" --tags "happy,cat,开心"
emo-img Data Schema & Taxonomy
The emo-img skill organizes its assets and metadata within a dedicated directory structure to ensure high performance within Openclaw Skills.
| File/Folder | Purpose |
|---|---|
~/.openclaw/stickers/ |
The root directory where all GIF and image files are stored. |
index.json |
The central registry containing sticker names, file paths, and metadata tags. |
scripts/sticker.py |
The core execution logic for searching, adding, and removing assets. |
Each entry in the index includes a unique name and a list of comma-separated tags, supporting both English and Chinese for broader search coverage.
emo-img Advanced Features
- Hybrid search logic that prioritizes local storage to save bandwidth and reduce latency.
- Cross-platform media support, enabling a single sticker file to be sent across different protocols.
- Automated metadata management through CLI commands for adding, tagging, and removing stickers.
- Direct integration with the Tenor API for real-time discovery of new and trending content.
- Flexible environment variable configuration for custom storage locations within the Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
Sequential Read
An AI-powered reading assistant that processes long-form text sequentially to simulate evolving human perspective and deep thematic synthesis.
Wiki.js CLI Skill
A comprehensive command-line interface for managing Wiki.js instances through the GraphQL API.
TTS WhatsApp Voice Messaging
An AI-powered skill to automate high-quality text-to-speech voice message delivery on WhatsApp in over 40 languages.
Self-Reflection
Enable continuous self-improvement for AI agents through structured reflection, mistake tracking, and memory management.
Multimodal Memory
A persistent visual memory system for AI agents to store, analyze, and recall images, charts, and website screenshots.
Quant Trader Daily
A professional workflow and task management system for quantitative and stock traders to automate reporting and risk monitoring.
Featured*
