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

PalateKit

Sign in
Menu

Request a resource

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

0 / 280

A page, a video or an image online.

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.

Structured extraction with the unstructured library v1.0.0

Use this resource to extract structured elements from documents in mixed formats

New

  • 578 downloads
  • 227 likes
  • 112 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install unstructured-document-extraction

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 uses the unstructured library to detect each document's type and split it into typed elements (text, table, title) with their metadata. The output has the same structure whatever the input format.

Mostly picked by

Updated November 2, 2026

Card for the “Structured extraction with the unstructured library” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: automatic partitioning and supported formats
  • SKILL.md: element types, access to extracted elements and code examples

Good fit for

  • One pipeline must handle emails, PDFs and web pages with the same code
  • You want to load document chunks into a vector store

Not for

    Tags

    • extraction
    • unstructured
    • documents
    • python

    About

    You say

    “Extract the body and attachments of this email, with the metadata of each element.”

    Card for the “Structured extraction with the unstructured library” skill

    Skill published by claude-office-skills under the MIT 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 extract structured elements from documents in mixed formats
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md14.6 KB

    Origin and licence

    Listed unmodified

    Author
    claude-office-skills
    Source
    github.com/claude-office-skills/skills/tree/9c4c7d5cd2813a8936bf2c9fdb174ea883b85a11/data-extractor
    Licence
    MIT

    Notice

    « data-extractor » (claude-office-skills, MIT) 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.