Skip to content

OpenRefine Data Cleaning CLI

Lets an agent clean, transform, and export messy datasets through OpenRefine via a command-line tool.

Stars
58,084
Licence
Apache-2.0
Files
1 file

What it does

Once installed, the agent can drive a local OpenRefine data-cleaning server through a command-line interface. It can import messy CSV files into a project, apply reusable JSON operation histories (such as trimming whitespace or running text transforms), inspect rows, export cleaned CSV or TSV files, and undo or redo steps within a saved session. OpenRefine itself must be running separately on your machine.

Great for

  • Analysts who need repeatable, scripted cleanup of messy CSV or TSV files
  • Developers building automated data pipelines that should use OpenRefine operations
  • Teams who want a saved, replayable record of transformations applied to a dataset

Skip it if

  • Users who do not have OpenRefine installed or cannot run a local server, since the skill depends on it
  • Sensitive datasets sent through a server you do not control, because the tool talks to an OpenRefine server URL that can be set to any address

Try asking

  • “Clean up the messy_customers.csv file by trimming whitespace in the Name column and export the result as CSV”
  • “Apply my saved OpenRefine operation history trim.json to the current project and show me the first 10 rows”
  • “Undo the last cleaning step in my session and export the current state to clean.tsv”
Step-by-step guide: how to use OpenRefine Data Cleaning CLIInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    skills.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip skills.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip skills.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Always add --json and --session so the agent's state stays isolated and results are machine-readable
  • Keep the OpenRefine server bound to 127.0.0.1 unless you intentionally need remote access
  • Save operation histories as JSON files so the same cleaning steps can be replayed on new data

What's inside

  • SKILL.md

Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.