Skip to content
TrustedSkillsbeta
Back to all skills

Parallel Data Enrichment

Checked
parallel-web·vlatest·ai-ml·MIT

Automatically expands limited training data with synthetic examples generated from web searches, boosting model accuracy.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

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

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

parallel-web

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned parallel-web/parallel-agent-skills at 8fc1fc426e.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
8fc1fc426e
Manifest
skills/parallel-data-enrichment/SKILL.md
Scanned
1 file, 102 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill automatically expands limited training data with synthetic examples generated from web searches. It takes existing data (either inline or from a CSV file) and enriches it based on a specified intent, such as retrieving CEO names and founding years for companies. The process can take several minutes depending on the amount of data requested and allows for context chaining across enrichment tasks to build upon previously discovered entities.

When to use it

  • Expanding small datasets to improve model accuracy.
  • Adding missing information or details to existing records.
  • Generating synthetic training examples based on a specific intent (e.g., finding company founding dates).
  • Building upon previous enrichment tasks by leveraging context chaining.
  • Preparing data for machine learning models where more comprehensive information is needed.

Key capabilities

  • Data Enrichment: Generates additional data points based on user-defined intents.
  • CSV File Support: Accepts CSV files as input and outputs enriched data to a specified file.
  • Inline Data Support: Accepts data directly within the command line.
  • Context Chaining: Allows follow-up enrichment tasks to build upon the context of previous runs using an interaction_id.
  • Asynchronous Processing: Uses --no-wait flag to initiate enrichment and return immediately, allowing for background processing.

Example prompts

  • "Enrich this data with CEO names and founding years: '[{"company": "Google"}, {"company": "Microsoft"}]'"
  • "Can you enrich the 'company' column in 'input.csv' to find the CEO name and founding year?"
  • "Continue enriching the data from the previous task, using interaction ID [previous_interaction_id]."

Tips & gotchas

  • Asynchronous Operation: Always use the --no-wait flag to avoid blocking the agent’s execution. You'll need to poll for results separately.
  • Timeout Limit: The polling process has a timeout of 9 minutes (--timeout 540). If it times out, re-run the parallel-cli enrich poll command to continue waiting.
  • Interaction ID: Remember and reuse the interaction_id for follow-up enrichment tasks to maintain context.