Extract Text From Image

Extract text from images, scanned documents, and PDFs using OCR

46 stars 56 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add zocomputer/skills --skill extract-text-from-image
Manual install
git clone --depth 1 https://github.com/zocomputer/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/Official/zo-extract-text-from-image ~/.claude/skills/extract-text-from-image

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Extract Text from Images (OCR)

## Purpose

Extract text from images, scanned documents, screenshots, and image-based PDFs using Tesseract OCR.

## Input

- Path to the image or PDF file containing text you want to extract

## Steps

1. Install Tesseract and required packages:

```bash
apt-get update && apt-get install -y tesseract-ocr imagemagick ghostscript
```

2. Extract text based on the file type:

```bash
# For image files (PNG, JPG, TIFF, etc.)
tesseract "<user's_image_path>" output.txt
cat output.txt

# For better accuracy with preprocessing
convert "<user's_image_path>" -resize 150% -type Grayscale -sharpen 0x1 enhanced.png
tesseract enhanced.png output.txt
cat output.txt

# For PDF files (converts to images first)
convert -density 300 "<user's_pdf_path>" -depth 8 -strip -background white -alpha off page_%d.png
for img in page_*.png; do tesseract "$img" "$img.txt"; done
cat page_*.png.txt > combined_output.txt
cat combined_output.txt

# For multi-language text (install language packs as needed)
apt-get install -y tesseract-ocr-fra tesseract-ocr-deu tesseract-ocr-spa
tesseract "<user's_image_path>" output.txt -l eng+fra+deu+spa
```

3. Save the extracted text to a file and tell the user where it was saved.

## Note

OCR accuracy depends on image quality. Best results come from high-resolution scans with clear, dark text on light backgrounds. The preprocessing step can help with lower quality images.
Read the full skill on GitHub

Details

Skill name
extract-text-from-image
Path
Official/zo-extract-text-from-image/SKILL.md
License
MIT
Repo updated
29 July 2026

FAQ

What does the Extract Text From Image skill do?

Extract text from images, scanned documents, and PDFs using OCR

How do I install the Extract Text From Image skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add zocomputer/skills --skill extract-text-from-image. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Extract Text From Image popular?

It lives in zocomputer/skills, which has 46 GitHub stars and 56 forks.

Related skills

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.