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.

Data extraction from construction images v1.0.0

Use this resource to extract structured data from site images or drawings

New

  • 422 downloads
  • 103 likes
  • 216 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install image-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 uses computer vision, OCR and AI models to analyse a photo, a drawing or a scanned document. You get structured data, such as the image type, dimensions from a drawing or a safety gap.

Mostly picked by

Updated November 2, 2026

Card for the “Data extraction from construction images” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: image types and quick start
  • SKILL.md: photo analysis, drawing extraction and safety violation detection
  • instructions.md: usage instructions

Good fit for

  • You receive scanned drawings you must re-enter by hand
  • You want to sort site photos automatically

Not for

    Tags

    • OCR
    • vision
    • drawings
    • photos

    About

    You say

    “Extract the dimensions and title block from this scanned drawing.”

    Card for the “Data extraction from construction images” skill

    Skill published by datadrivenconstruction 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 data from site images or drawings
    3. Review and adjust the result

    Content preview

    Files

    • claw.json0.5 KB
    • instructions.md1.5 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md18.8 KB

    Origin and licence

    Listed unmodified

    Author
    datadrivenconstruction
    Source
    github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/tree/410ed1e71e4a5c6fd231afd0c8d1e586a9f546e8/2_DDC_Book/2.4-PDF-CAD-to-Data/image-to-data
    Licence
    MIT

    Notice

    « image-to-data » (datadrivenconstruction, 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.