amazon-order-matcher
Scrape Amazon order history and match to Monarch Money transactions for auto-categorization. Uses browser automation to extract order details, then matches by amount and date to categorize uncategorized transactions.
Best use case
amazon-order-matcher is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Scrape Amazon order history and match to Monarch Money transactions for auto-categorization. Uses browser automation to extract order details, then matches by amount and date to categorize uncategorized transactions.
Teams using amazon-order-matcher should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/amazon-order-matcher/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How amazon-order-matcher Compares
| Feature / Agent | amazon-order-matcher | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Scrape Amazon order history and match to Monarch Money transactions for auto-categorization. Uses browser automation to extract order details, then matches by amount and date to categorize uncategorized transactions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Amazon Order Matcher Automatically categorize Amazon purchases in Monarch Money by matching against Amazon order history. ## How It Works 1. **Scrape Amazon Orders**: Browser automation (profile `openclaw`) extracts order history 2. **Match Transactions**: Matches by amount (exact match) with date tolerance (bank posts 1-3 days after order) 3. **Categorize**: Auto-assigns categories based on Amazon product descriptions 4. **Update Monarch**: Batch updates via Monarch CLI ## Quick Start ```bash # Browser must be running with openclaw profile browser action=start profile=openclaw # Navigate to Amazon orders (login persisted in profile) browser action=navigate targetUrl="https://www.amazon.com/your-orders/orders?timeFilter=year-2026" # Extract orders via JavaScript evaluation (see scripts/extract_orders.js) # Match to Monarch transactions (see scripts/match_and_categorize.py) # Batch update (see scripts/batch_update.sh) ``` ## Scripts | Script | Purpose | |--------|---------| | `match_and_categorize.py` | Match Amazon orders to Monarch transactions, suggest categories | | `batch_update.sh` | Apply category updates to Monarch | | `quick_categorize.py` | Amount-based heuristics when order data unavailable | ## Category Mapping | Product Type | Monarch Category | Category ID | |--------------|------------------|-------------| | Baby gates, locks, protectors | Baby formula | 225123032227674020 | | Health supplements | Household | 162959461244237526 | | Home appliances | Household | 162959461244237526 | | Cables, tools, work equipment | Business expense | 178462006985127548 | | Electronics, gadgets | Jeremy Spending Money | 162782301949818821 | | Car accessories | Transportation | 162777981853398770 | | Gifts | Gifts | 162777981853398756 | ## Data Files - `data/amazon_orders_2026.json` - Scraped order data with dates, amounts, products - Order data persists between sessions for re-matching ## Browser Session Amazon login is persisted in the `openclaw` browser profile: - No MFA needed on repeat visits - Session survives browser restarts - Target ID may change between sessions (get fresh via `browser action=tabs`) ## Cron Schedule Weekly reconciliation runs Sunday 8pm ET: - Scrapes new orders from Amazon - Matches to uncategorized Monarch transactions - Applies categories automatically - Reports summary to Telegram ## Limitations - Amount matching only (no order ID correlation with bank data) - Multi-item orders may match incorrectly if total matches another order - Refunds/returns need manual review - Amazon Store Card transactions processed separately ## First-Time Setup 1. Start browser: `browser action=start profile=openclaw` 2. Navigate to Amazon and log in manually 3. Complete MFA verification 4. Login persists for future sessions
Related Skills
amazon-writing
Use when writing narrative memos, 6-pagers, 1-pagers, press releases, or PRFAQs in Amazon style. Applies Amazon's no-PowerPoint writing standards with data over adjectives, active voice, and the "so what" test.
order-analysis
分析产品升级工单,识别共性问题并提出产品改进建议。通过 agent-browser工具 访问工单系统,提取工单数据,进行问题分类、趋势分析和根因定位,输出改进方案。
asciinema-recorder
Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.
amazon-bestseller-launch
Complete Amazon KDP bestseller launch system with proven strategies for achieving
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
mcp-create-declarative-agent
Skill converted from mcp-create-declarative-agent.prompt.md
MCP Architecture Expert
Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, prompts, and security best practices
mathem-shopping
Automatiserar att logga in på Mathem.se, söka och lägga till varor från en lista eller recept, hantera ersättningar enligt policy och reservera leveranstid, men lämnar varukorgen redo för manuell checkout.
math-modeling
本技能应在用户要求"数学建模"、"建模比赛"、"数模论文"、"数学建模竞赛"、"建模分析"、"建模求解"或提及数学建模相关任务时使用。适用于全国大学生数学建模竞赛(CUMCM)、美国大学生数学建模竞赛(MCM/ICM)等各类数学建模比赛。
matchms
Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.
managing-traefik
Manages Traefik reverse proxy for local development. Use when routing domains to local services, configuring CORS, checking service health, or debugging connectivity issues.
managing-skills
Install, find, update, and manage agent skills. Use when the user wants to add a new skill, search for skills that do something, check if skills are up to date, or update existing skills. Triggers on: install skill, add skill, get skill, find skill, search skill, update skill, check skills, list skills.