A cross-platform GIF reaction skill that enables AI agents to search and send optimized animated GIFs on Telegram, WhatsApp, Discord, Signal, and other messaging channels.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gif-multi
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 gif-multi 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 GIF Multi?
The GIF Multi skill is a highly versatile tool designed for AI assistants to express dynamic reactions natively across various messaging platforms such as Telegram, WhatsApp, Discord, and Signal. Powered by the Giphy API, it allows AI agents using Openclaw Skills to search, optimize, and automatically deliver relevant animated media directly within conversations. By detecting active communication channels, this skill ensures that media delivery fits perfectly within the host application's specifications.
With multi-channel auto-discovery and intelligent caching, GIF Multi serves as an essential feature for making conversations with AI agents more lifelike, contextual, and engaging. Its flexible operating modes enable spontaneous, human-like reaction patterns or strictly requested interactions, providing developers with granular control over AI conversational behavior.
GIF Multi Use Cases
- Contextual AI Reactions: Allow your AI agent to spontaneously drop animated reactions in active chat rooms like Discord or Telegram to mimic human conversations.
- On-Demand Media Search: Let users query GIFs natively within the chat stream by asking the agent to "find a funny reaction gif".
- Cross-Platform Automated Messaging: Dynamically resolve and format media for WhatsApp, Signal, and other integrated platforms based on the current user channel.
- Dynamic Conversation Pacing: Inject visual humor and brand personality into customer support and community management channels utilizing high-quality assets sourced directly via Giphy.
How GIF Multi Works
- Channel Detection: The skill scans inbound metadata to identify the active messaging channel (e.g., Telegram, WhatsApp, Discord) from the host's session context.
- Configuration Validation & Auto-Discovery: It runs a quick check to ensure Giphy configuration exists. If a new, unconfigured channel is detected, it runs the auto-discovery sequence to register the channel silently.
- Query & Giphy API Resolution: On trigger, the script queries Giphy using the configured API key, downloading and optimizing the matched animated GIF.
- Media Optimization and Cache Management: The downloaded file is stored securely in a local cache directory with a unique timestamp to prevent race conditions during concurrent requests.
- Secure Dispatch: The optimized media payload path is returned to the runner to send via the designated message action handler.
- Post-Execution Cleanup: Once successfully transmitted, the media file is removed, and orphan files older than 10 minutes are automatically deleted to maintain a zero-bloat footprint.
GIF Multi Setup
Prerequisites
Make sure your environment has the following system packages installed:
- Python 3
- ffmpeg
- curl
1. Obtain Giphy API Key
Register for a developer account at Giphy Developers, click "Create an App", and select the API option (free tier provides up to 1,000 requests/day).
2. Configure Environment
Save your Giphy API key securely using one of the following methods:
Option A: Through openclaw.json (Recommended)
{
"skills": {
"entries": {
"gif-multi": {
"env": {
"GIPHY_API_KEY": "your_giphy_api_key_here"
}
}
}
}
}
Option B: Through ~/.openclaw/.env
echo 'GIPHY_API_KEY=your_giphy_api_key_here' >> ~/.openclaw/.env
3. Verify Installation
Verify the integration works properly and check for missing system dependencies:
python3 {baseDir}/scripts/gif_multi.py --check
GIF Multi Data Schema & Taxonomy
File and Config Management
This skill maintains a local configuration and directory structure for caching images to ensure high performance with Openclaw Skills:
| Item | Description | Location / Value |
|---|---|---|
| Local Config | Stores current platform registrations, operational modes, and settings | {baseDir}/config.json |
| GIF Cache Directory | Temporary storage folder for active GIF processes | {baseDir}/.gif_cache/ |
| Rating Options | Configurable content filter level to prevent inappropriate material | g (default), pg, pg-13, r |
| Auto-clean Timer | Clears orphaned assets to maintain disk health | Files older than 10 minutes |
Output Format
When a search query is executed, the tool returns a JSON object containing the absolute system path to the cached media file:
{
"path": "/path/to/project/.gif_cache/gif_1700000000.gif"
}
GIF Multi Advanced Features
- Interactive Conversational Mode-Switching: Users can alter the behavior of the agent in real time. Simply saying "stop sending GIFs without asking" switches the running mode to
on_request, while telling the agent "feel free to send GIFs naturally" restores it tonaturalmode. - Auto-Discovery Workflow: The skill automatically registers newly configured messaging platforms silently during runtime without needing developer intervention.
- Concurrent Task Isolation: Every query receives a unique cryptographic/timestamp-based filename, allowing multi-user, multi-group, or parallel-channel chats to proceed simultaneously without cache conflicts.
- Safe Search Filter Customization: Developers can explicitly control content ratings using the
--ratingparameter (options includeg,pg,pg-13, orr) directly from the CLI tool or configuration file. - Self-Healing Storage Pipeline: Automatic cleanup rules discard downloaded assets that exceed a 10-minute lifespan, preventing resource leaks on self-hosted servers running Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Text to SQL
An AI-powered skill that bridges the gap between natural language and structured database queries by translating plain English into precise, schema-validated SQL.
AI Image To Code
Converts user interface screenshots into accurate, functional HTML/CSS or React and Tailwind CSS components using advanced vision models.
Quick Note
A lightweight, local-first note-taking tool that instantly captures ideas, to-dos, and reading lists with automatic categorization and zero external dependencies.
Python Flow Engine
A zero-dependency Python library for constructing data pipelines with serial, parallel, and conditional execution paths.
Web to Markdown
A highly structured URL extraction skill converting web pages into clean markdown through a deterministic fallback pipeline of markdown.new and Jina Reader.
Text to SQL
A developer-focused agent skill that converts natural language requests into schema-accurate, dialect-specific SQL queries.
Featured*
