Spreadsheet

What This Skill Does

The Spreadsheet skill enables OpenClaw to interact with complex tabular data, providing a robust interface for reading, writing, and analyzing files across Google Sheets, Excel (.xlsx), and CSV formats. Designed for high-reliability data manipulation, it treats spreadsheets as first-class objects, maintaining schema awareness and format integrity. By utilizing a local directory structure (~/spreadsheet/), the skill caches project-specific schemas, formulas, and user preferences, ensuring that iterative tasks are performed consistently without manual configuration drift.

Installation

To integrate this skill into your environment, run the following command in your terminal: clawhub install openclaw/skills/skills/ivangdavila/spreadsheet Once installed, ensure the directory structure is initialized by triggering a file operation. The system will automatically prepare the necessary folders for memory and exports.

Use Cases

This skill is ideal for tasks requiring structured data management:

• Financial Reporting: Automating the collation of monthly expense reports from Excel and CSV exports.
• Inventory Management: Tracking stock levels where schema preservation is critical to prevent data corruption.
• Google Sheets Integration: Syncing local analytical results directly to cloud-based sheets for team collaboration.
• Data Cleaning: Normalizing column types, date formats, and numerical styles across large, unstructured datasets.

Example Prompts

1. "Open the Q3 sales report in ~/data/sheets/q3_final.xlsx, identify all rows where the region is 'EMEA', and update the status column to 'Reviewed' while keeping all formulas intact."
2. "Load the product inventory CSV and create a schema file in the project folder. Once done, generate a summary report of items with stock counts below 50."
3. "Connect to my Google Sheet ID [SheetID] and append the latest analytical results from my current project, ensuring date formats match the existing ISO standard in column D."

Tips & Limitations

• Large Data: When handling datasets exceeding 10,000 rows, the system will pause to warn you; use targeted queries to improve performance and avoid rate limits.
• Formula Safety: Always prioritize 'data_only=False' operations to prevent accidental overwriting of complex calculations.
• Schema Maintenance: If a spreadsheet's structure has been stagnant for more than 7 days, trigger a schema re-verification to account for silent column shifts.
• Platform Priority: The system automatically optimizes for Google Sheets (via API), then Excel, then CSV. For maximum speed on massive datasets, prefer native Excel formats over CSV imports.