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 field extraction from documents v1.0.0

Use this resource to extract structured fields from documents without inventing values

New

  • 428 downloads
  • 216 likes
  • 208 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install document-data-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 sends the document to the third-party Stipple service (free anonymous tier), gets the extracted values with their page and confidence, and lists anything not found as missing. You get JSON usable for accounting or a file.

Mostly picked by

Updated November 2, 2026

Card for the “Structured field extraction from documents” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: steps for sending the document and the output format
  • SKILL.md: limits, security rules and notes

Good fit for

  • You need to enter invoices into your accounting software
  • A loan file requires data extracted from bank statements

Not for

    Tags

    • extraction
    • documents
    • json
    • invoices

    About

    You say

    “Extract the amount, date and supplier from this invoice as JSON, with the source page.”

    Card for the “Structured field extraction from documents” skill

    Skill published by Sketchjar 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 extract structured fields from documents without inventing values
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md4.5 KB

    Origin and licence

    Listed unmodified

    Author
    Sketchjar
    Source
    github.com/sickn33/agentic-awesome-skills/tree/e9809578fd426a284af017c5db99f8eb6628e6ca/skills/extract-document-data
    Licence
    Apache-2.0

    Notice

    « extract-document-data » (Sketchjar, 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.