Thomaszhou22

File To Database Skill — Data skill for Claude Code

Data community

Turn data files (CSV/Excel/JSON/JSONL/TSV) into a validated database, then operate it in natural language — pluggable methodology, quality gates, migration ledger, visual delivery.

How to install File To Database Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Thomaszhou22/file-to-database-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What File To Database Skill does

Turn data files (CSV/Excel/JSON/JSONL/TSV) into a validated database, then operate it in natural language — pluggable methodology, quality gates, migration ledger, visual delivery.

Alternatives in Data

  • Claude Code Usage Monitor — by Maciek-roboblog - A real-time terminal-based tool for monitoring Claude Code token usage 7k ★
  • HTML Video — Programmatic video for coding agents — HTML to video on your laptop 4.5k ★
  • MCP Server Chart — 🤖 A visualization mcp & skills contains 25+ visual charts using @antvis 4k ★

README

🗄️ File to Database

![License](https://img.shields.io/badge/license-MIT-blue) ![Version](https://img.shields.io/badge/version-1.0.0-green) ![Platform](https://img.shields.io/badge/platform-OpenClaw%20%7C%20Claude%20Code%20%7C%20Cursor%20%7C%20Codex%20%7C%20Gemini%20CLI-purple) ![ClawHub](https://img.shields.io/badge/ClawHub-draft-yellow)

**English** | **[中文](README.zh-CN.md)**

Turn raw data files (CSV / Excel / JSON / JSONL / TSV) into a validated database — then keep operating it in natural language: queries, inserts, updates, and deletes with safety gates, audit logs, and a visual delivery package after every change.

**7 reference docs** encode the full engineering loop. **6 file formats** supported. **0 dependencies** (stdlib Python only; openpyxl optional for xlsx).

**The problem:** "Send the files to Cursor and it builds a database" works once, but every new project means re-explaining your design rules, the agent guesses foreign keys and indexes differently each time, and after the DDL you're on your own. File to Database fixes all three: your design methodology lives in `references/methodology.md` (swap it to change the design style), every generated schema follows it verbatim, and the runtime mode keeps the agent as the database's natural-language operator afterwards.

Table of Contents

Click to expand

How It Works

data files ──▶ infer_schema.py ──▶ column profiles
                                        │