A professional-grade moderation tool that leverages AI to automatically filter and audit text, image, and video content via the Vettly API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install content-moderation
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 content-moderation 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 Content Moderation (Vettly API)?
The content-moderation skill is a powerful integration designed to bridge AI agents with Vettly's sophisticated moderation engine. By utilizing Openclaw Skills, developers can implement automated safety checks that analyze user-generated content for toxicity, spam, and other restricted categories. This skill is essential for maintaining community standards and ensuring that all interactions within an application remain safe and compliant.
Built on top of the Model Context Protocol (MCP), this tool allows for seamless communication between your agent and the Vettly service. Whether you are managing a social platform, a forum, or a media sharing site, incorporating Openclaw Skills into your workflow provides a scalable way to handle moderation without manual oversight. The skill supports multiple media formats and provides auditable decisions to ensure transparency in your moderation process.
Content Moderation (Vettly API) Use Cases
- Automatically moderate user-generated comments and posts to maintain community health using Openclaw Skills.
- Scan uploaded images and videos for policy violations before they are visible to other users.
- Validate and test complex moderation policy YAML configurations in a sandbox environment.
- Review and audit recent moderation decisions to fine-tune safety thresholds and accuracy.
- Monitor platform-wide moderation costs and usage statistics to optimize resource allocation.
How Content Moderation (Vettly API) Works
- The agent receives content, such as a text string or a media URL, that requires safety verification.
- Through the Openclaw Skills interface, the content is sent to the Vettly MCP server along with a specific policy identifier.
- Vettly's AI engine evaluates the content against defined categories like toxicity, hate speech, or adult content.
- The skill returns a structured assessment including safety scores, the final action taken (flag, block, or allow), and metadata like latency and cost.
- Developers can use additional tools within the skill to list available policies or validate new YAML rules before they go live.
Content Moderation (Vettly API) Setup
To get started with this component of Openclaw Skills, you must first obtain an API key from Vettly. Once you have your key, configure the MCP server in your environment.
# Set your Vettly API key in your environment variables
export VETTLY_API_KEY="your-vettly-api-key"
Add the following configuration to your MCP settings:
{
"mcpServers": {
"vettly": {
"command": "npx",
"args": ["-y", "@vettly/mcp"],
"env": {
"VETTLY_API_KEY": "your-api-key"
}
}
}
}
Content Moderation (Vettly API) Data Schema & Taxonomy
The content-moderation skill organizes data through several key structures to ensure clarity and auditability within Openclaw Skills:
| Object | Description |
|---|---|
| Content Request | Includes content (text or URL), policyId, and contentType (text, image, video). |
| Safety Assessment | Returns category scores, decision outcome, provider data, and cost metrics. |
| Policy Configuration | YAML-based definitions of thresholds and actions for various content categories. |
| Usage Stats | Aggregated data on request volume and expenditures over a defined timeframe (1-365 days). |
| Decision Logs | A history of recent moderation events with filters for flagged or safe status. |
Content Moderation (Vettly API) Advanced Features
- Multi-modal support allowing for the moderation of text, images, and video through a unified API.
- Real-time policy validation to catch syntax errors in YAML configurations before deployment.
- Comprehensive decision auditing that tracks the provider, latency, and specific category scores for every request.
- Usage analytics integration to monitor high-level trends and spikes in moderation activity.
- Flexible filtering for decision history by policy ID or content type to streamline manual reviews.
SKILL.md
Loading
Related Openclaw Skills
OpenHarmony React Native Performance Optimizer
A specialized set of static analysis rules and optimization guidelines designed specifically for React Native applications running on the OpenHarmony platform.
BatchJob Async Job Skill
A comprehensive tool for managing the end-to-end lifecycle of asynchronous batch jobs via HTTP APIs.
Marketing Calendar Generator
An AI-driven marketing strategist that automates the Hua Yu Hua methodology to generate high-scoring, culturally relevant campaign calendars.
Brand Proverb Generator (Hua Yu Hua Method)
An AI-driven copywriting engine that applies the professional Hua Yu Hua methodology to generate rhyming, colloquial brand proverbs and ranked slogans.
Shelter
Shelter is a read-only financial intelligence skill that enables AI agents to analyze bank data, calculate safe-to-spend limits, and provide personalized coaching.
Spotify Playlist Builder
An AI-driven automation tool for building, managing, and personalizing Spotify playlists via natural language requests.
Featured*
