Transforms and exports data with DuckDB SQL. It reads CSV, Parquet, JSON, Excel and database files, applies joins, aggregations and pivots, and can write the results to files.
Claude Code
> /plugin marketplace add richard-gyiko/data-wrangler-plugin> /plugin install data-wrangler@data-wrangler-marketplace
Codex
$ npx skills add richard-gyiko/data-wrangler-plugin -a codex
Cursor
$ npx skills add richard-gyiko/data-wrangler-plugin -a cursor
Gemini CLI
$ npx skills add richard-gyiko/data-wrangler-plugin -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add richard-gyiko/data-wrangler-plugin$ copilot plugin install data-wrangler@data-wrangler-marketplace
OpenCode
$ npx skills add richard-gyiko/data-wrangler-plugin -a opencode
Windsurf
$ npx skills add richard-gyiko/data-wrangler-plugin -a windsurf
A Claude Code plugin that enables powerful data transformation and export using DuckDB SQL.
Add the marketplace and install:
/plugin marketplace add richard-gyiko/data-wrangler-plugin
/plugin install data-wrangler@data-wrangler-marketplace
/plugin marketplace add ./path/to/data-wrangler-plugin
/plugin install data-wrangler@data-wrangler-marketplace
Once installed, Claude will automatically use this skill when you ask data transformation questions.
Simple file query:
"What are the top 10 products by revenue in sales.csv?"
Join multiple files:
"Join orders.parquet with customers.csv and show total orders per customer"
Export to Parquet:
"Filter active users from users.csv and save as users_active.parquet"
Create partitioned dataset:
"Convert events.json to Parquet partitioned by year and month"
Store database and cloud credentials securely using a YAML secrets file with environment variable substitution.
Create secrets.yaml:
secrets:
my_postgres:
type: postgres
host: db.example.com
user: analyst
password: "${PGPASSWORD}" # Uses environment variable
database: analytics
Supported secret types:
See SECRETS.md for full configuration options.
The skill uses DuckDB, an embedded analytical database that excels at:
uv package manager (for running the script)Dependencies are automatically installed via the inline script metadata:
duckdb>=1.4.3polars[pyarrow]>=1.36.1data-wrangler-plugin/
├── .claude-plugin/
│ ├── plugin.json # Plugin manifest
│ └── marketplace.json # Marketplace definition
├── skills/
│ └── data-wrangler/
│ ├── SKILL.md # Skill instructions for Claude
│ ├── SECRETS.md # Secrets management docs
│ ├── TRANSFORMS.md # Advanced SQL patterns
│ └── scripts/
│ └── query_duckdb.py # DuckDB query engine
├── tests/ # Test suite
└── README.md
MIT License - see LICENSE file for details.
Contributions welcome! Please open an issue or pull request.
Stars on GitHub
Reads text from scanned pages, photos and PDFs and returns it as structured Markdown or JSON, so you can pull tables, formulas and headers out of a document without retyping them. Covers many languages and works as input for AI tools.
@paddlepaddleGives your AI assistant a memory that persists across sessions, so it remembers your preferences and earlier work in this repository instead of starting fresh. Search, forget, pause and resume memories with simple commands.
@mem0aiGives AI agents a library of ready-made skills for scientific work such as metabolic flux analysis, protein experiment design, time series modeling, and analytical method validation, so research tasks need less hand-built code. It works with any agent that supports the open Agent Skills standard.
@k-dense-aiGives Claude Code skills, agents, and commands for PostHog analytics, session replay, feature flags, error tracking, and LLM observability. Includes MCP server setup and project access checks.
@posthogTransforms and exports data with DuckDB SQL. It reads CSV, Parquet, JSON, Excel and database files, applies joins, aggregations and pivots, and can write the results to files. Install it with the command on its page. It includes data-wrangler. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it