Query and analyze local Copilot Money transaction and budget data using SQL and shell utilities.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install copilot-money-mac
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install copilot-money-mac using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Copilot Money skill enables deep programmatic access to your personal financial data stored locally on your Mac. Unlike standard exports, this skill leverages Openclaw Skills to interact with the app's internal SQLite database and Firestore LevelDB cache. This allows for real-time analysis of spending, budget tracking, and investment performance directly from the source data used by the Copilot app, ensuring your financial insights are always up to date with your local application state.
Accessing your financial data requires the Copilot Money Mac app to be installed. You can verify the database path and test connectivity using the following command:
sqlite3 -header -column ~/Library/Group\ Containers/group.com.copilot.production/database/CopilotDB.sqlite "SELECT date, name, amount FROM Transactions LIMIT 5;"
Ensure your terminal or AI agent environment has the necessary permissions to read from the Library folders within your macOS user directory to enable Openclaw Skills functionality.
The skill interacts with two primary data structures to provide a complete financial picture:
| Data Source | Description |
|---|---|
Transactions (SQLite) |
Core ledger containing dates, amounts, merchant names, and category references. |
accountDailyBalance (SQLite) |
Historical snapshots of account liquidity and available balances. |
Firestore Collections (LevelDB) |
Metadata for budgets, investments, and recurring transaction definitions. |
Note that transaction amounts are stored as positive values for expenses and negative values for income.
Loading
A lightweight personal CRM and context-retention skill for AI agents to store and recall specific details about individuals.

A high-performance, real-time voice interface for Openclaw agents featuring sub-2 second latency and multi-provider STT/TTS support.

A specialized tool for extracting and summarizing YouTube transcripts to save time on video content consumption.

A powerful automation bridge for Typefully to manage social media drafts and multi-platform scheduling directly via the CLI.

An AI-driven discovery tool that leverages the watcha.cn API to find, evaluate, and recommend AI products based on community sentiment and technical specifications.

A unified CLI and AI-powered icon library providing access to over 19,000 icons with framework-aware generation and tree-shaking.








































