Setup & Installation
openclaw skills install @gitgoodordietrying/csv-pipeline
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install csv-pipeline
What This Skill Does
Process and transform tabular data in CSV, TSV, or JSON formats using Python 3 and standard shell tools. Supports filtering, joining, aggregating, deduplicating, format conversion, and Markdown report generation. No external libraries required.
Covers the full ETL cycle, including streaming large files, without requiring pandas, a database, or any package installs beyond Python 3.
When to use it
- Filtering sales records by amount threshold
- Joining customer and order datasets on a shared ID column
- Converting JSON API exports to CSV for use in spreadsheets
- Deduplicating an email list before a campaign send
- Generating grouped summary reports from transaction logs
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: I have orders.csv and customers.csv, join them on customer_id and summarize revenue by category
AGENT
- 1Read both CSV files into lists of dicts using read_csv()
- 2Left join orders to customers on the customer_id column
- 3Aggregate the joined rows by category, summing the revenue field
- 4Write the aggregated results to summary.csv
- 5Generate a Markdown report table with count, sum, avg, min, and max per category
OUTPUT
summary.csv with per-category revenue totals and report.md with a formatted breakdown table