🔪 CSV Surgeon

🔪 CSV Surgeon

Meet CSV Surgeon — a production-ready AI agent built for business automation and workflow optimization. CSV Surgeon is the AI-powered first-aid kit for data engineers tackling malformed CSVs, inconsistent delimiters like comma vs. semicolon, and encoding mismatches such as UTF-8 to ISO-8859-1, just as required in Amazon and Capital One ETL roles. It automates header normalization, type inference, and column operations akin to Pandas read_csv(engine='python') or OpenRefine clustering, saving hours on messy Excel/Google Sheets exports. Built for high-demand data prep pipelines at tech giants like Google and Snowflake, it delivers production-ready tabular data without the manual drudgery of traditional ETL tools. Deploy instantly on your favorite AI platform and start automating today.

Key Features

• Delimiter detection & fixing, matching Amazon's 'handling malformed CSVs'
• Encoding auto-detection (UTF-8/ANSI/CP1252), as in Capital One 'CSV remediation'
• Header normalization, per Palantir 'fix broken tabular data from exports'
• Type inference & casting, core to Pandas usage in 85% of postings
• Split/merge column operations, like Tableau Prep pivot/unpivot
• Null handling and data validation, inspired by Great Expectations
• Preprocessing for messy spreadsheet exports, as in Google ML Engineer roles
• Scalable for ETL pipelines, compatible with PySpark for large files

What's Included

• SOUL.md — Agent personality, tone, and behavioral guidelines
• AGENTS.md — Workspace rules, memory management, and safety boundaries
• System Prompt — Universal prompt compatible with any LLM
• README — Setup guide with deployment instructions

Compatible With

• OpenClaw (recommended — full agent lifecycle)
• ChatGPT / OpenAI API
• Claude / Anthropic API
• Gemini / Google AI
• Grok / xAI
• Any LLM that accepts system prompts