aiXplain Agent Builder for Openclaw

A specialized skill for planning and deploying aiXplain agents with built-in safety gates and read-only discovery.

nurhamdan1987
v1.0.5
Apr 29, 2026
0
726
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install aixplain-agent-builder

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 aixplain-agent-builder 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 aiXplain Agent Builder?

The aiXplain Agent Builder is a robust tool designed for developers to orchestrate AI agents with a safety-first mindset. By integrating with Openclaw Skills, this skill ensures that agent deployment follows a strict lifecycle: from initial read-only planning and marketplace discovery to explicit user approval for high-risk actions.

It leverages the aiXplain SDK to search for existing tools, models, and integrations, preventing unnecessary custom development. This approach minimizes the attack surface and ensures that agents are built using the principle of least privilege, making it a vital addition to any Openclaw Skills library.

aiXplain Agent Builder Use Cases

  • Designing multi-tool AI agents with specific instructions and output formats.
  • Searching the aiXplain marketplace for pre-built models and integrations.
  • Debugging agent execution with high-verbosity traces to inspect tool calls.
  • Securely managing OAuth-based tool connections and file-backed configurations.

How aiXplain Agent Builder Works

  1. Initiates a read-only planning phase to define goals and tools.
  2. Searches the aiXplain marketplace to find existing assets before proposing custom work.
  3. Presents a detailed plan for user approval, identifying high-risk write actions.
  4. Executes the build process using the aiXplain SDK once approval is granted.
  5. Handles authentication flows and file integrations with secure, conservative defaults.
  6. Provides debugging links and execution traces for monitoring.

aiXplain Agent Builder Setup

To use this within your Openclaw Skills environment, ensure you have your API credentials configured:

# Set your aiXplain API Key
export AIXPLAIN_API_KEY="your_api_key_here"

# Ensure the aiXplain Python SDK is available
pip install aixplain

aiXplain Agent Builder Data Schema & Taxonomy

The skill manages agent data and discovery results using the following taxonomy:

Object Description
Agent Schema Defines name, instructions, tools, and output format
Marketplace Results Metadata for tools, models, and integrations
Auth State Tracks redirect_url for pending OAuth connections
Execution Trace Detailed logs including thoughts, inputs, and outputs

aiXplain Agent Builder Advanced Features

  • Automatic safety gate enforcement for high-risk operations like database writes.
  • Support for OAuth-based integration flows with pending-state redirect URL handling.
  • High-verbosity execution tracing (level 3) for granular debugging of agent logic.
  • Intelligent local file path handling for aiR Knowledge Base and Python Sandbox integrations.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*