AO Op for Openclaw

An OpenClaw skill that provides a reliable wrapper to operate a local installation of Agent Orchestrator (AO) directly through execution commands.

chaoyang78
v1.0.0
May 21, 2026
0
690
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install ao-op

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install ao-op 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 AO Op?

The AO Op skill acts as a robust execution bridge between your AI agent environment and a locally cloned instance of Agent Orchestrator (AO). By wrapping the native Node.js-based entrypoint of your source checkout, it bypasses launcher-entrypoint warning issues typically flagged by doctor utilities. This makes it an essential utility among Openclaw Skills for developers looking to manage complex orchestrator workflows directly from their coding workspace.

With this skill, you can bypass typing verbose workspace paths and instead trigger orchestrator commands seamlessly. It is designed to work reliably from any directory, providing a direct pipeline to the stable node packages within your development repository.

AO Op Use Cases

  • Orchestrating and managing multiple coding-agent sessions concurrently.
  • Running status checks, initiating, or stopping orchestrator dashboard services without manual navigation.
  • Checking health diagnostics via doctor commands when global CLI binaries throw launcher errors.
  • Dispatching messages directly to active development sessions or checking code review feedback.
  • Pulling down and rebuilding the latest Agent Orchestrator repository source straight from your workspace CLI.

How AO Op Works

  1. Command Execution: The agent triggers the skill using the wrapper script ao.sh located in the skill directory.
  2. Directory Switching: The script navigates to the pre-configured local repository path at /Users/ShiXin/Documents/Workspace/github-project/agent-orchestrator.
  3. Source Execution: It invokes the local node package entrypoint (node packages/ao/bin/ao.js) passing all provided CLI arguments.
  4. Output Capture: System diagnostics, session metrics, or action results are returned back directly to the OpenClaw execution environment.

AO Op Setup

To set up the AO Op skill within your workspace, ensure your local Agent Orchestrator repository is cloned and that the wrapper script is executable.

# Verify the local repository path exists
ls /Users/ShiXin/Documents/Workspace/github-project/agent-orchestrator

# Make the execution wrapper script executable
chmod +x /Users/ShiXin/.openclaw/skills/ao-op/scripts/ao.sh

# Test the integration health status
/Users/ShiXin/.openclaw/skills/ao-op/scripts/ao.sh doctor

AO Op Data Schema & Taxonomy

This skill operates over a highly organized local workspace. Below is the mapping of critical directories, scripts, and logs utilized by the integration:

Path Description
/Users/ShiXin/.openclaw/skills/ao-op/scripts/ao.sh Main CLI executable wrapper running node from source.
/Users/ShiXin/Documents/Workspace/github-project/agent-orchestrator Source root directory containing the agent orchestration packages.
packages/ao/bin/ao.js Direct entrypoint script executed by Node.js.
references/commands.md Cookbooks, common CLI arguments, and routing logs.

AO Op Advanced Features

  • Automatic Source Diagnostics Bypass: Prioritizes running local Node scripts over globally installed executable wrappers to avoid environment issues.
  • Source Compilation Integrations: Ability to pull, resolve dependencies via pnpm, and rebuild workspace sub-packages recursively with simple directives.
  • Contextual Session Handlers: Ability to route session checks (ao status) and retrieve status or dashboard outputs through clean command abstraction.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*