A command-line engine designed to search, install, and orchestrate multi-step automations by chaining various Openclaw Skills together.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawflows
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 clawflows using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
ClawFlows acts as the orchestration layer for your agentic environment, allowing you to combine individual Openclaw Skills into powerful, logic-driven workflows. By shifting the focus from specific skill implementations to abstract capabilities, it ensures that your automations are portable and flexible across different setups. Whether you are building a daily news aggregator or a complex market monitoring system, ClawFlows provides the framework to manage data flow and execution between multiple agents.
This tool centralizes the discovery and management of automated tasks through a dedicated registry. It allows developers to define steps, capture outputs, and pass variables between different Openclaw Skills without hardcoding specific tool dependencies. This abstraction layer is what makes it a vital component for anyone looking to scale their automation capabilities.
To begin orchestrating your Openclaw Skills, install the ClawFlows CLI globally via npm:
npm i -g clawflows
Once installed, you can browse available automations by running:
clawflows search --capability database
ClawFlows utilizes YAML files to define the lifecycle of an automation. These files map abstract requirements to the specific Openclaw Skills available on your system.
| Component | Description |
|---|---|
steps |
The sequence of operations to be performed. |
capability |
The generic requirement (e.g., social-search) fulfilled by compatible Openclaw Skills. |
method |
The specific function to call within the skill (e.g., getRecentVideos). |
args |
Input parameters, supporting variable interpolation from previous steps. |
capture |
A variable name used to store the output for subsequent steps. |
Loading
LiquidSkills provides a specialized knowledge layer for AI agents to bridge the gap between stale training data and production Hyperliquid infrastructure.

A privacy-focused metasearch skill that aggregates results from over 70 engines using a self-hosted SearXNG instance.

A self-hosted, privacy-respecting metasearch skill that aggregates results from over 70 sources into a structured JSON API.

A privacy-respecting metasearch skill that aggregates results from over 70 engines into a single, self-hosted API for secure web research.

A zero-dependency Python tool for generating and editing high-quality images using the Gemini API and Nano Banana Pro model.

An intelligent automation skill for completing US nonimmigrant visa DS-160 forms using structured CSV data and AI-assisted captcha solving.








































