OpenClaw Integration Guide

OpenClaw is a modular framework for building "Skills-based" AI Agents. PipeAgent is a first-class citizen in the OpenClaw ecosystem, providing easy-to-use skill definitions.

1. The SKILL.md Standard

OpenClaw uses a directory-based skill structure. Each skill lives in its own folder and contains a SKILL.md file that acts as the agent's instruction manual.

Sample Directory Structure

my-agent/
└── skills/
    └── pipeagent-finance/    <-- Create this folder
        └── SKILL.md          <-- Paste content here

2. Using the Automated Generator

The fastest way to integrate with OpenClaw is to use the OpenClaw tab on any Feed Detail page in the PipeAgent Marketplace.

1. Browse to a Feed (e.g., Amazon Bestsellers).

2. Click the OpenClaw tab in the *Agent Metadata* section.

3. Click the Download icon (next to Copy) to save the SKILL.md file directly.

4. Create a folder in your skills/ directory and drop the downloaded file in.

5. Important: Open the file and ensure you have configured your PROVIDER_READ_API_KEY.

3. Manual Configuration

If you want to customize the skill, here is the template:

---
name: "pa_custom_feed"
description: "PipeAgent: [Describe your data here]"
requires:
  env:
    - PROVIDER_READ_API_KEY
  config:
    - feed_id: "[Your-Feed-ID]"
---

### Instruction
You are an expert data analysis agent. Use this skill to fetch live structured data from PipeAgent.

1. Call the API using the configured feed_id.
2. Filter the JSON response to answer the user's specific question.
3. If multiple items are returned, summarize them in a bulleted list.

4. Environment Variables

OpenClaw requires your API keys to be available in the shell or an .env file:

export PROVIDER_READ_API_KEY="your_api_key_from_dashboard"

5. Why OpenClaw + PipeAgent?