A portable identity system for creating, validating, and publishing standardized JSON identity cards for AI agents.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-identity-kit
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-identity-kit using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Agent Identity Kit is a specialized tool designed to bring structure and interoperability to the AI agent landscape. It provides a standardized framework for creating agent.json identity cards, allowing developers to define clear handles, descriptions, and ownership for their autonomous entities. As a core component of the Openclaw Skills library, this kit ensures that agents can be easily identified, verified, and integrated into broader ecosystems.
By leveraging the Agent Card v1 schema, this skill allows for the creation of portable identity files that can be hosted on well-known endpoints or registered in global directories. This promotes a more transparent and discoverable environment for AI agents, facilitating trust and seamless communication between different agentic systems within the Openclaw Skills framework.
To begin using the Agent Identity Kit, navigate to the skill directory and use the provided bash scripts for configuration:
# Initialize a new agent identity card
./scripts/init.sh
# Validate an existing identity card against the schema
./scripts/validate.sh path/to/agent.json
Ensure that you have execution permissions for the script files and that your environment supports standard JSON validation tools.
The skill organizes its data based on the Agent Card v1 specification. The following table highlights the primary fields used in the identity system:
| Field | Required | Description |
|---|---|---|
version |
Yes | The specification version (e.g., "1.0"). |
agent.handle |
Yes | A Fediverse-style unique identifier (@name@domain). |
owner.name |
Yes | The entity or individual accountable for the agent. |
capabilities |
No | A list of tags defining what the agent can do. |
protocols |
No | Supported communication protocols like MCP or HTTP. |
trust.level |
No | Verification status such as active or verified. |
Loading
A cross-platform bridge for AI agents to interact with social networks, news feeds, and skill directories through a single configuration.

A strategic framework designed to transform AI agents from reactive responders into proactive task-executors that operate independently.

A Model Context Protocol (MCP) tool providing AI-grounded location data, real-time weather, and travel routes via Google Maps.

A social media ecosystem specifically designed for AI agents to publish, discover, and engage with AI-generated visual art.

A modular framework that prevents AI context loss by organizing memory into episodic, semantic, and procedural layers.

A comprehensive process framework for building and managing self-sustaining AI agent teams with automated work loops.








































