A meta-skill designed to teach developers and agents how to create, structure, and publish their own custom agentic capabilities.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install how-to-skill
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 how-to-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The How To Skill serves as a recursive educational framework within the ecosystem of Openclaw Skills. It provides a blueprint for developers to transition from users to creators by explaining the fundamental mechanics of skill architecture. The primary purpose is to simplify the process of defining agent behaviors through structured Markdown documentation, ensuring that new skills are both discoverable and functional.
By following this guide, creators learn the art of balancing simplicity and utility. It emphasizes the importance of clear documentation and precise trigger phrases, which are essential for any successful entry in the Openclaw Skills marketplace. Whether you are wrapping an existing API or building a complex multi-step workflow, this skill provides the necessary technical foundation.
To begin creating your own Openclaw Skills, ensure you have the developer environment ready and follow these CLI steps:
clawhub publish your-skill-name
The skill utilizes a structured Markdown taxonomy to ensure that agents can parse and execute commands effectively. The following table outlines the expected metadata for Openclaw Skills:
| Component | Purpose | Requirement |
|---|---|---|
| Skill Name | Display name and primary identifier | Mandatory |
| What Is | Conceptual summary for agent context | Mandatory |
| Commands | Trigger phrases and execution logic | Mandatory |
| Links | External documentation and source code | Optional |
| Trigger Phrases | Natural language patterns for activation | Mandatory |
Loading
Exoskeletons provide AI agents with a persistent onchain identity, reputation system, and secure marketplace built on the Base network.

A high-performance CLI skill for the Exponential productivity platform, enabling seamless task creation, project tracking, and workspace management.

A specialized skill for interacting with Frigate NVR servers to manage cameras, snapshots, and motion events through session-based authentication.

A secure CLI tool for managing multiple calendar and email accounts with AI-optimized JSON output.

An AI agent skill designed to execute multi-step tasks autonomously while adhering to strict safety guardrails and confirmation protocols.

A runtime safety control plane that enforces deterministic security policies on shell commands, network requests, and file operations.








































