Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Download and parse raw scientific data v1.0.0

Use this resource to download and parse raw or large scientific datasets

New

  • 321 downloads
  • 191 likes
  • 203 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install scientific-data-download-parsing

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent writes the code that queries the source, filters, downloads and parses the files, for cases ToolUniverse tools do not cover. It turns to code over tools as soon as thousands of records are needed. You get usable data along with the script that produces it.

Mostly picked by

Updated November 2, 2026

Card for the “Download and parse raw scientific data” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md : tool-versus-code decision tree and usage rules
  • references/specialized-domains.md : genomic, structural, omics and imaging formats
  • evals/evals.json : evaluation cases for the skill

Good fit for

  • You need to parse a VCF or h5ad file
  • A tool only returns metadata and you need the data itself

Not for

    Tags

    • data
    • download
    • python
    • scientific formats

    About

    You say

    “Download all the files in this series and extract the counts into a table.”

    Card for the “Download and parse raw scientific data” skill

    Skill published by mims-harvard under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to download and parse raw or large scientific datasets
    3. Review and adjust the result

    Content preview

    Files

    • evals/evals.json1.4 KB
    • LICENSE11.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/specialized-domains.md11 KB
    • SKILL.md16.8 KB

    Origin and licence

    Listed unmodified

    Author
    mims-harvard
    Source
    github.com/mims-harvard/tooluniverse/tree/169d065deeb3e289b3ff36d665529a123bdad791/skills/tooluniverse-data-wrangling
    Licence
    Apache-2.0

    Notice

    « tooluniverse-data-wrangling » (mims-harvard, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.