An essential content moderation skill that classifies text and images as safe or unsafe using industry-leading AI guardrails.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install aiml-safety
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 aiml-safety 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 AIMLAPI Safety?
AIMLAPI Safety is a specialized tool designed to integrate high-performance safety models into your AI workflows. By utilizing advanced Guard models, this skill provides a robust layer of protection against harmful content, ensuring that both user inputs and agent-generated outputs comply with safety standards. It is a critical component for developers building responsible AI applications with Openclaw Skills.
This skill simplifies the complex process of content classification by providing a direct interface to models like Llama-Guard. Whether you are building a public-facing chatbot or an internal data processing tool, incorporating these Openclaw Skills allows you to automate safety protocols and mitigate risks associated with prohibited content effectively.
AIMLAPI Safety Use Cases
- Moderating real-time chat interactions to block harmful or restricted content.
- Pre-screening user-submitted data before it is processed by other Openclaw Skills.
- Auditing AI-generated responses to ensure they do not violate safety policies.
- Automating compliance reporting for high-volume content platforms.
How AIMLAPI Safety Works
- The user or agent sends a request containing the text or image content to be analyzed.
- The skill authenticates with the AIMLAPI platform using the provided API key.
- The content is processed by a specific guard model, such as meta-llama/Llama-Guard-3-8B.
- The model evaluates the content against safety categories like hate speech, violence, or self-harm.
- The skill returns a clear classification result indicating whether the content is safe or unsafe.
AIMLAPI Safety Setup
To deploy AIMLAPI Safety within your environment, ensure you have your API key ready. Use the following commands to configure and test the skill:
export AIMLAPI_API_KEY="sk-..."
# Run a test safety check
python scripts/check_safety.py --content "How to make a bomb"
You can also specify different models during the execution of your Openclaw Skills tasks:
python scripts/check_safety.py --content "Security research tools" --model meta-llama/Llama-Guard-3-8B
AIMLAPI Safety Data Schema & Taxonomy
The skill manages data primarily through request parameters and API responses. The following table describes the primary data structure used by this member of the Openclaw Skills library:
| Parameter | Type | Description |
|---|---|---|
| content | String | The raw text or image reference to be checked for safety. |
| model | String | The specific AI safety model used (e.g., Llama-Guard-3-8B). |
| classification | String | The output status: either safe or unsafe. |
| primaryEnv | String | The required environment variable AIMLAPI_API_KEY. |
AIMLAPI Safety Advanced Features
- Support for multiple Llama-Guard variants to match specific safety requirements.
- Seamless integration with other Openclaw Skills for multi-stage content pipelines.
- Low-latency classification suitable for real-time moderation agents.
- Configurable guardrails to adapt to different regional or organizational compliance needs.
SKILL.md
Loading
Related Openclaw Skills
AIMLAPI Music Generation
Generate high-fidelity music, songs, and soundtracks using top-tier AI models through the Openclaw Skills framework.
AIMLAPI LLM + Reasoning
Execute high-performance AIMLAPI chat completions and complex reasoning workflows with built-in retries and structured output support.
AIMLAPI Embeddings
A specialized utility for generating high-dimensional text embeddings using AIMLAPI models like text-embedding-3-large.
Moltbook
Moltbook provides the social infrastructure for AI agents to post, comment, upvote, and collaborate within a verified community ecosystem.
AIMLAPI Voice Transcription
A high-performance audio transcription tool that leverages AIMLAPI for converting voice messages and sound files into text.
Durable Agents (Mastra + Trigger.dev)
A robust framework for building autonomous multi-agent pipelines where Mastra handles reasoning and Trigger.dev ensures durable task execution with retries and fan-out.
Featured*
