← Back to Skills Marketplace
openclaw-whatsapp-gif
by
witty-quotes25
· GitHub ↗
· v1.0.1
595
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install openclaw-whatsapp-gif
Description
Source and send relevant reaction GIFs in WhatsApp chats using safe filters and deterministic ranking. Use when the user asks for a GIF/meme/reaction, or whe...
Usage Guidance
This skill appears to do what it says: look up safe GIFs and prepare/send a WhatsApp payload. Before installing, consider: 1) Provide TENOR_API_KEY/GIPHY_API_KEY only if you want provider results; otherwise it will use the built-in safe catalog. 2) It downloads media to the OS temp directory (cache and optional telemetry log). If you have storage or privacy concerns, inspect/override references/policy.json (allowedMediaHosts, allowRemoteUrlFallback, enableTelemetryLog, cacheDir, logFile). 3) Web-scrape fallback and remote-URL fallback are disabled by default; enable them only if you trust those behaviors. 4) The skill hands off a payload to your platform's message tool — verify that tool enforces delivery policies and handles local file attachments safely. 5) Avoid running the integration_test with real phone numbers. Overall the skill is internally consistent and proportional to its purpose.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-whatsapp-gif
Version: 1.0.1
The OpenClaw WhatsApp GIF skill is classified as benign. It demonstrates robust security practices, including strict host whitelisting for all network requests and media downloads (enforced by `is_allowed_host` and `allowedMediaHosts` in `policy.json`), content filtering for search results, and validation of downloaded media size and type. Risky features like web scraping (`search_tenor_web` in `scripts/find_gif.py`) and remote URL fallback are disabled by default in `references/policy.json`. There is no evidence of intentional data exfiltration, persistence mechanisms, or prompt injection attempts in `SKILL.md`.
Capability Assessment
Purpose & Capability
Name/description match what the code and SKILL.md implement: searching Tenor/Giphy (via optional TENOR_API_KEY/GIPHY_API_KEY), applying blocklists/safe filters, ranking candidates, and producing a WhatsApp message payload or local file. No unrelated credentials or binaries are requested.
Instruction Scope
Instructions are specific about running the included scripts and using the message tool. The skill downloads remote media, writes temp cache files, reads optional API keys and a local references/policy.json, and (if enabled by policy) may web-scrape Tenor. These behaviors are documented in SKILL.md and limited to media fetching and local logging; they are within expected scope but worth reviewing if you need stricter host/policy constraints.
Install Mechanism
No install spec is present (instruction-only with included scripts). No packages or remote install URLs are fetched by an installer. Runtime network I/O is limited to provider APIs and optional web-scrape.
Credentials
No required env vars; TENOR_API_KEY and GIPHY_API_KEY are optional and appropriate for provider access. The skill does not ask for unrelated secrets or system credentials.
Persistence & Privilege
always:false and no system-wide config changes. The skill writes temporary cache and an optional telemetry log under the OS temp directory and uses a local references/policy.json for runtime policy. openai.yaml sets allow_implicit_invocation:true (implicit/automatic invocation), which is reasonable for a messaging helper but worth awareness.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-whatsapp-gif - After installation, invoke the skill by name or use
/openclaw-whatsapp-gif - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
openclaw-whatsapp-gif v1.0.1
- Added agents/openai.yaml configuration file.
- Updated SKILL.md to include operational metadata: optional API keys, temp cache behavior, and policy controls for web scraping, remote URL fallback, and telemetry logging.
- Clarified that web scraping and remote URL fallback are disabled by default and require explicit policy enabling.
- Updated script usage notes for temp cache use and default telemetry/logging behavior.
v1.0.0
- Initial release of openclaw-whatsapp-gif skill.
- Sources and sends safe, high-quality reaction GIFs to WhatsApp chats based on user intent.
- Uses deterministic filters, keyword ranking, and retries if GIF delivery fails.
- Adheres to decision rules for when visual reactions are appropriate.
- Provides fallback to concise text if no GIF can be sent.
- Supports both API-driven and fallback (web scraping or built-in catalog) approaches for GIF sourcing.
Metadata
Frequently Asked Questions
What is openclaw-whatsapp-gif?
Source and send relevant reaction GIFs in WhatsApp chats using safe filters and deterministic ranking. Use when the user asks for a GIF/meme/reaction, or whe... It is an AI Agent Skill for Claude Code / OpenClaw, with 595 downloads so far.
How do I install openclaw-whatsapp-gif?
Run "/install openclaw-whatsapp-gif" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is openclaw-whatsapp-gif free?
Yes, openclaw-whatsapp-gif is completely free (open-source). You can download, install and use it at no cost.
Which platforms does openclaw-whatsapp-gif support?
openclaw-whatsapp-gif is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created openclaw-whatsapp-gif?
It is built and maintained by witty-quotes25 (@witty-quotes25); the current version is v1.0.1.
More Skills