A browser automation skill for purchasing, reordering, and processing returns on Amazon using an AI agent.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install amazon-shopper
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-shopper 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 Automation?
This skill enables an AI agent to interact directly with the Amazon web interface via the Chrome DevTools Protocol. By utilizing Openclaw Skills, developers can automate the entire lifecycle of an Amazon order—from searching and reordering to handling the complexities of the return process. It provides a bridge between high-level agent instructions and low-level browser actions, ensuring that e-commerce tasks are performed efficiently and accurately.
The skill is designed to work with a persistent browser profile, allowing it to maintain login sessions and handle checkout workflows with minimal user friction. Whether you are managing personal supplies or automating procurement for a team, this skill brings sophisticated automation to the world's largest marketplace.
Amazon Automation Use Cases
- Automatically reordering frequently used household or office supplies.
- Processing product returns silently using pre-defined default logic.
- Researching new products and capturing clean screenshots for human approval.
- Checking order history and tracking the status of recent shipments via CLI.
How Amazon Automation Works
- The agent connects to a running Chrome instance via the agent-browser CLI using the Remote Debugging Port (9222).
- It initializes a new browser tab to prevent interference with existing sessions.
- For reorders, it navigates directly to the Order History, identifies the item, and proceeds to checkout using saved preferences.
- For new items, it captures a product screenshot, waits for user confirmation, and then adds the item to the cart.
- For returns, it navigates the return flow, answers condition questions based on default or user-provided parameters, and confirms the drop-off location.
- Upon completion, the agent provides a summary of the action taken, such as refund amounts or order confirmations.
Amazon Automation Setup
To use this skill within the Openclaw Skills ecosystem, configure your environment and start your browser with the debugging port enabled.
# Set your default automation preferences
export AMAZON_SHIPPING_ADDRESS="Your shipping address"
export AMAZON_PAYMENT_METHOD="Your preferred card"
export AMAZON_RETURN_DROPOFF="Whole Foods"
# Start Chrome with remote debugging (macOS example)
open -na "Google Chrome" --args --user-data-dir=$HOME/.config/chrome-agent --no-first-run --remote-debugging-port=9222 https://www.amazon.com
# Connect the agent browser
agent-browser connect 9222
Amazon Automation Data Schema & Taxonomy
The skill manages configuration through environment variables and local filesystem persistence. This ensures that Openclaw Skills can maintain a consistent state across sessions.
| Data Element | Type | Description |
|---|---|---|
| AMAZON_SHIPPING_ADDRESS | Env Var | The primary delivery address used for automated checkouts. |
| AMAZON_PAYMENT_METHOD | Env Var | A text-based identifier for selecting the correct card during payment. |
| AMAZON_RETURN_DROPOFF | Env Var | The preferred physical location for returning items (e.g., Whole Foods). |
| ~/.config/chrome-agent | Directory | A persistent Chrome profile that stores your Amazon login session and cookies. |
Amazon Automation Advanced Features
- Silent Execution: Reorders are processed without requiring visual confirmation once preferences are set.
- Intelligent Screenshotting: Automatically scrolls past navigation bars to capture high-quality product images for review.
- Headless Support: Fully compatible with Linux/VNC setups for server-side execution of Openclaw Skills.
- Automated Return Logic: Handles complex return questionnaires using a standardized set of default answers to minimize user input.
- Security First: Uses a dedicated browser profile to keep automation data separate from your primary browsing data.
SKILL.md
Loading
Related Openclaw Skills
Amazon Ordering
Automate the entire Amazon shopping lifecycle, from reordering essentials to processing returns, using browser-based AI agents.
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.
Caddy Wildcard Reverse Proxy
A specialized tool for managing Caddy-based reverse proxy routes with wildcard subdomain support and automated HTTPS for local services.
Git Commit & Push Automator
Automatically stage changes, generate AI-driven commit messages, and push code to your remote repository in one seamless workflow.
Featured*
