parallel-data-enrichment Skill for Claude: What It Does and How to Install It

Makes Claude add web-sourced fields, like CEO names or funding, to a list of companies, people or products.

Installs: 13.7K; on skills.sh
Stars: 91; on GitHub
Updated: Oct 2026; last repo commit

This is Parallel's own enrichment skill. Claude starts a parallel-cli enrich run for your CSV or inline list, gives you a monitoring link, polls until it finishes, and saves the rows as JSON. It reports how many rows succeeded and how many failed.

It needs parallel-cli installed, signed in and funded, and your rows are sent to Parallel. The folder holds only SKILL.md and bundles no scripts.

Good for

Sales and research teams who need extra columns on a company or contact list
Anyone enriching a CSV with fields found on the web
Analysts who want per-row results saved as JSON or CSV

Install parallel-data-enrichment

Claude Code

Copy this prompt.

Install the parallel-data-enrichment skill in Claude Code. Run this command:

/plugin marketplace add parallel-web/parallel-agent-skills
/plugin install parallel

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin installs all 15 skills (counted from the repo), a hosted Parallel Search MCP server (parallel-search, anonymous) and a Bash-only agent called parallel-subagent. Restart Claude Code after installing it. This skill needs parallel-cli installed, signed in and funded; the second method in each tab lists the install commands from the repo's setup skill, and /parallel:parallel-cli-setup runs them for you. In Codex, use $ instead of / for skill names.

From the project README. Source.

What's in the skill

When it loads

Bulk data enrichment. Adds web-sourced fields (CEO names, funding, contact info) to lists of companies, people, or products. Use for enriching CSV files or inline data. Supports multi-turn: pass --previous-interaction-id from a prior research task to carry context forward.

Sections in SKILL.md

Before starting
Optional: Suggest output columns
Step 1: Start the enrichment
Step 2: Poll for results
If polling times out or is interrupted
If the user requested CSV
Response format
Setup

Key facts

Author: Parallel Web Systems (vendor's own repo)
Repo: parallel-web/parallel-agent-skills
License: MIT (LICENSE file; README and plugin.json agree)
Installs on skills.sh: 13,692 (Nov 2, 2026)
GitHub stars: 91 for the whole repo (Nov 2, 2026)
Last repo commit: Oct 28, 2026
Audits on skills.sh: Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn
What it includes: 1 file: SKILL.md. It bundles no scripts
Part of: Plugin parallel: 15 skills, a hosted MCP server and 1 agent
Needs: parallel-cli, internet access, a funded Parallel account

What it includes

Asks the API which columns to add when your request is vague
Use it only when you did not name the fields. It needs parallel-cli 0.3.0 or newer, and its output feeds --enriched-columns.
Try: “Enrich these companies with useful info”
Runs code · enrich suggest
Starts an enrichment from a JSON list passed with --data
Always uses --no-wait so the command returns at once with a taskgroup_id and a monitoring URL.
Try: “Add CEO name and founding year to Google and Microsoft”
Runs code · enrich run (inline data)
Reads a CSV with --source-type csv and the columns you describe
Your input CSV is left untouched.
Runs code · enrich run (CSV)
Waits in 60-second chunks and saves rows as JSON
The saved file is JSON whatever its extension. Each row has either an output or an error.
Runs code · enrich poll
Checks a group after a timeout instead of recreating it
It shows is_active, status_counts and num_runs.
Runs code · enrich status
Turns the saved JSON into a separate CSV, keeping every input row and an error column
SKILL.md says this is a local conversion, not a CSV produced by polling.
Write · CSV conversion
Passes --previous-interaction-id from an earlier research task
Unavailable on Zero Data Retention accounts.
Runs code · Context chaining
Reports successful, failed and total rows against num_runs
A finished group can still contain failed rows.
Row accounting

From the official docs

Permissions

Medium risk

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Your list is sent to Parallel
Every row you enrich, such as company or person names, goes to Parallel's API, and the README says task inputs are handled under its Customer Terms and Privacy Policy. Do not enrich lists with data you cannot share. github.com
It runs against your funded Parallel account
The README says CLI-backed skills are billed as ordinary API usage on your own Parallel account. Check current pricing on the vendor site before large runs. github.com
Large lists mean many billed runs
SKILL.md says enrichment may take several minutes depending on rows and fields, and the group records a run count (num_runs). Try a few rows first. github.com
The setup path installs and signs in a CLI
The repo's setup skill installs parallel-cli (brew, uv, npm or pipx), starts a device sign-in, and points to `parallel-cli balance add` for top-ups. The search and research skills say never to add funds without explicit confirmation. github.com

Technical details

Turning on read-only	There is no read-only switch. The skill runs parallel-cli commands that call Parallel's API under your account.
Sign-in and keys	parallel-cli signs in with a device OAuth flow you approve in a browser. The README says CLI-backed skills use credentials you already configured.
Scopes	Runs parallel-cli through Bash (allowed-tools: Bash(parallel-cli:*)) Reads your input CSV or inline data Writes enrichment results as JSON, and a separate CSV if you ask, to paths Claude chooses

Questions

What does the parallel-data-enrichment skill do?

It makes Claude add web-sourced fields, such as CEO names, funding or contact details, to a list of companies, people or products. The list can be a CSV file or inline data. Results are saved as JSON, and as a separate CSV if you ask.

How do I install parallel-data-enrichment?

Use the install box above. The plugin installs it with 14 other skills. Then install and sign in to parallel-cli.

Does it change my original CSV?

SKILL.md says to leave the input CSV untouched. Results go to a separate JSON file, and an optional CSV conversion keeps every original column and row, with an error column for failures.

What if I do not know which columns to add?

Claude can run parallel-cli enrich suggest with your intent and use the suggested columns. That needs parallel-cli 0.3.0 or newer. Otherwise you describe the fields yourself.

Can some rows fail?

Yes. SKILL.md says a completed group can include failed rows, so Claude should report successful, failed and total counts against the run count and not claim every row worked.

How much does it cost?

The skill gives no prices. Runs are billed to your own Parallel account as ordinary API usage, per the README. Try a handful of rows first and see the vendor's pricing page.

Is it safe?

It runs parallel-cli in Bash, sends the rows you enrich to Parallel, reads your CSV and writes result files. It spends credits on your account. Our advice: test with a few rows and enrich only data you are allowed to share.

Is it an official Parallel skill?

It is in Parallel Web Systems' own repo, and the repo's marketplace.json describes the plugin as the "Official Parallel Web Systems plugin for Claude Code".

Information

updated Nov 2, 2026

Repository: parallel-web/parallel-agent-skills
Folder: skills/parallel-data-enrichment

parallel-web/parallel-agent-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

parallel-agent-skills README · github.com
parallel-agent-skills marketplace.json · github.com
parallel plugin.json · github.com
parallel-cli-setup SKILL.md · github.com
parallel-data-enrichment SKILL.md · github.com