Parallel Data Enrichment

parallel-web/parallel-agent-skillsOfficial

You've got a CSV of 500 companies and need to add CEO names, funding rounds, or employee counts without manually looking each one up. This skill handles that, farming out web research in parallel and merging the results back into structured output. It's built on top of Parallel's CLI and can chain context from previous research tasks, so if you already had Claude dig up a list of startups in a sector, you can enrich that same list without re-explaining what you found. The polling can time out on huge datasets, but it resumes where it left off. Most useful when you need to turn a skeleton dataset into something you can actually filter and sort on real attributes.

skills.sh installs: 13.9K
GitHub stars: 91
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parallel-web/parallel-agent-skills --skill parallel-data-enrichment --agent claude-code

Installs into .claude/skills of the current project.

Files

Data Enrichment

Enrich: $ARGUMENTS

Before starting

Inform the user that enrichment may take several minutes depending on the number of rows and fields requested.

Optional: Suggest output columns

If the user gave a vague intent ("enrich these companies with useful info") and you're not sure what columns to add, ask the API for a suggestion before kicking off the run:

parallel-cli enrich suggest "Find CEO and recent funding info" --json

The response is an envelope: {title, processor, enriched_columns, warnings}. Extract just the enriched_columns array (not the whole envelope) and pass it as the value of --enriched-columns on enrich run, in place of --intent. These flags are alternative ways to specify what to enrich. If suggest returned a processor, pass it explicitly via --processor on the run call. Skip this section if the user already specified the fields they want.