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.

Text recognition (OCR) for scanned documents v1.0.0

Use this resource to extract text from scanned documents or images

New

  • 522 downloads
  • 134 likes
  • 228 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install ocr-document-text-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 compares OCR engines (Tesseract, EasyOCR, PaddleOCR, Textract, Document AI or Claude vision), applies preprocessing (deskew, denoise, binarize) and writes the extraction script. You get the text, with per-word confidence when the engine provides it.

Mostly picked by

Updated November 2, 2026

Card for the “Text recognition (OCR) for scanned documents” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: OCR engine comparison and a Tesseract script with page segmentation modes
  • SKILL.md: image preprocessing, EasyOCR, PaddleOCR and table extraction

Good fit for

  • You have scanned documents to convert to text
  • You need to choose a free or paid OCR engine

Not for

    Tags

    • ocr
    • tesseract
    • document
    • scan

    About

    You say

    “Extract the text from these scanned invoices and keep the column layout.”

    Card for the “Text recognition (OCR) for scanned documents” skill

    Skill published by claude-dev-suite 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 text from scanned documents or images
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.3 KB

    Origin and licence

    Listed unmodified

    Author
    claude-dev-suite
    Source
    github.com/claude-dev-suite/claude-dev-suite/tree/e10ab644ba43abe2abc923399226df4af7337214/skills/document-processing/ocr
    Licence
    MIT

    Notice

    « ocr » (claude-dev-suite, 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.