Automate the entire Amazon shopping lifecycle, from reordering essentials to processing returns, using browser-based AI agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install amazon-ordering
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install amazon-ordering 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 Amazon Ordering?
The Amazon Ordering skill leverages browser automation to handle e-commerce tasks directly within a Chrome instance. By integrating with Openclaw Skills, developers can create agents capable of searching order histories, placing new orders, and navigating the complex return flow without manual intervention.
This skill is built to work with the agent-browser CLI, utilizing the Chrome DevTools Protocol (CDP) to interact with the DOM, manage sessions, and handle persistent browser profiles. It streamlines procurement workflows for both individual users and automated procurement systems by providing a programmable interface to the Amazon storefront.
Amazon Ordering Use Cases
- Automated reordering of household or office supplies based on previous order history.
- Streamlining the Amazon return process by automatically selecting reasons and drop-off locations.
- Delegating product research and initial cart staging to an AI agent for final review.
- Managing multiple Amazon orders across headless Linux environments or local macOS setups.
How Amazon Ordering Works
- The agent connects to a running Chrome instance via the remote debugging port (9222) using the agent-browser CLI.
- It identifies whether the request is for a new item or a reorder by searching the user's order history.
- For reorders, the agent proceeds directly to checkout; for new items, it captures a detailed screenshot for user approval before adding to the cart.
- During checkout, it verifies shipping and payment environment variables to ensure accuracy before placing the order.
- For returns, it navigates the multi-step return UI, selecting reasons and drop-off locations based on pre-configured default answers.
- Once the action is complete, it provides a concise summary, including refund amounts or QR code availability for returns.
Amazon Ordering Setup
To get started with this skill in your Openclaw Skills environment, ensure the agent-browser CLI is installed and Chrome is running with the remote debugging port enabled.
# Start Chrome with remote debugging (macOS)
open -na "Google Chrome" --args --remote-debugging-port=9222
# Configure your environment variables
export AMAZON_SHIPPING_ADDRESS="Your shipping address"
export AMAZON_PAYMENT_METHOD="Your preferred card"
export AMAZON_RETURN_DROPOFF="Whole Foods"
Amazon Ordering Data Schema & Taxonomy
The skill utilizes environment variables for configuration and maintains session persistence through a dedicated Chrome profile. Data is organized as follows:
| Attribute | Description |
|---|---|
AMAZON_SHIPPING_ADDRESS |
The default shipping destination used during the checkout verification step. |
AMAZON_PAYMENT_METHOD |
A string identifier for the preferred card or payment method to select in the wallet. |
AMAZON_RETURN_DROPOFF |
The preferred location (e.g., Whole Foods, UPS) for generating return labels and QR codes. |
chrome-agent profile |
Persistent session data stored at $HOME/.config/chrome-agent to keep the user logged in. |
snapshots |
Temporary image files captured during product navigation for user verification. |
Amazon Ordering Advanced Features
- Headless execution support using Xvfb and VNC for server-side or cloud-based automation.
- Intelligent reorder logic that bypasses manual confirmation for recognized items to increase efficiency within Openclaw Skills workflows.
- Automated return handling with silent execution to minimize agent-to-human interruptions.
- Multi-tab management ensuring isolated browser sessions by using the --new-tab command for every operation.
- Custom screenshot engine that automatically scrolls past navigation bars to capture clear product and pricing information.
SKILL.md
Loading
Related Openclaw Skills
Self-Reflection AI Agent Skill
A recursive optimization skill that enables AI agents to analyze their own performance and update their knowledge base automatically.
Clabcraw AI Gaming Agent
An automated gaming skill that allows AI agents to compete in 1v1 high-stakes matches for USDC rewards.
WHOOP Lab
A comprehensive health integration that fetches, interprets, and charts WHOOP biometric data to optimize recovery and track fitness experiments.
SnapTrade Portfolio
A comprehensive tool for connecting brokerage accounts through SnapTrade to monitor balances and execute stock trades automatically.
Amazon Automation
A browser automation skill for purchasing, reordering, and processing returns on Amazon using an AI agent.
Caddy Wildcard Reverse Proxy
A specialized tool for managing Caddy-based reverse proxy routes with wildcard subdomain support and automated HTTPS for local services.
Featured*
