skills.rest
HKUDS
HKUDSOFFICIAL
Explore all skills by this author →
WebsiteGitHub

cli-anything-openrefine

Automate OpenRefine data cleaning, transformation, and export through an agent-native CLI.

48.8k|4.5k|Updated Mar 8, 2026
Search Tags:#CLI#data transformation#etl#data cleaning#Automation#CSV#openrefine
One-click install
npx skills add https://github.com/HKUDS/CLI-Anything --skill cli-anything-openrefine
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cli-anything-openrefine
Source: https://github.com/HKUDS/CLI-Anything/tree/main/openrefine/agent-harness/cli_anything/openrefine/skills
Command: npx skills add https://github.com/HKUDS/CLI-Anything --skill cli-anything-openrefine

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cleaning messy CSV/TSV data with OpenRefine normally requires manual GUI interaction, which blocks automated agent workflows. This Skill exposes OpenRefine as a scriptable CLI so agents can import data, apply reusable JSON operation histories, inspect rows, and export cleaned results without human clicks.

Core Features & Use Cases

  • Project and Data Management: Import messy CSV files into OpenRefine projects, list projects, and inspect rows with JSON output.
  • Reusable Operation Histories: Generate and apply standard OpenRefine operation-history JSON (e.g., text transforms like value.trim()) to any dataset.
  • Session Undo/Redo and Export: Track isolated session state, undo or redo operations, and export cleaned data as CSV or TSV.
  • Use Case: An agent receives a messy customer CSV, imports it into OpenRefine, applies a trim/dedupe operation history, previews the first 10 rows, and exports a clean CSV for downstream loading.

Quick Start

Ask the agent to import your messy CSV into OpenRefine, apply a trim transformation to a chosen column, and export the cleaned result as a CSV file.

Frequently Asked Questions about cli-anything-openrefine

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate OpenRefine data cleaning from the command line?▼

Install the cli-anything-openrefine harness, start OpenRefine on port 3333, then use commands like project import, data apply, and data export with the --json flag. Operation histories are standard OpenRefine JSON files applied directly to projects.

How to apply an OpenRefine operation history JSON to a new dataset?▼

Pass the existing operation-history JSON file to the data apply command with an active session, for example: cli-anything-openrefine --json --session run/session.json data apply run/trim.json. The operations replay on the currently imported project.

Does the OpenRefine CLI require a running OpenRefine server?▼

Yes, OpenRefine must be started before backend commands, typically with openrefine -i 127.0.0.1 -p 3333. You can override the server location with the OPENREFINE_URL environment variable or the --base-url flag.

Can I undo or redo OpenRefine operations from the CLI?▼

Yes, the session undo and session redo commands manage operation history within an isolated session file specified via --session. This lets agents safely experiment with transformations and revert mistakes.

Why does a piped OpenRefine REPL session return a nonzero exit code?▼

Piped REPL workflows return a nonzero exit status at exit or EOF if any command in the stream failed. This behavior lets CI pipelines detect unsuccessful automated user journeys.

Related Skills

Explore More Data & Analytics Skills→
andregusman-raizandregusman-raiz
19

csv-transform

Cleans, validates, and transforms messy CSV/TSV data into structured datasets.

Community
Advanced
novoleinovolei

xlsx

Clean and transform CSV, TSV, and XLSX data into formatted XLSX workbooks.

Community
Intermediate
brainbrewlabsbrainbrewlabs
7

data-cleaning

Profile and clean tabular datasets, then write a cleaned file with a change report.

Official
Intermediate
PedroHBOPedroHBO
1

data-processing

Clean, transform, and analyze datasets with Pandas, Polars, and NumPy.

Community
Advanced