paddleocr-text-recognition

PaddlePaddle/PaddleOCR · Agent Skill

Extracts text from images, photos, scans, and screenshots with high accuracy, including handwritten and small print.

Overview

Publisher	PaddlePaddleOrganization
Repository	PaddlePaddle/PaddleOCR ↗
Skill folder	`paddleocr-text-recognition`
Stars	88,975
Bundled files	1
License	Apache-2.0
Last updated	June 3, 2026
Links	Skill source ↗ · Repository ↗

Mozgi check

What we found in the skill files. Details come with a subscription.

Security

low risk · no obvious risks found — the full report shows the details

Compatibility

instructions only — works with most agents

Similar skills

37 similar skills found

Also with subscription

Installation

A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.

Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.

Install the “paddleocr-text-recognition” skill from mozgi.io (https://mozgi.io/skills/paddleocr-text-recognition/) for me.

1. Download the archive: https://mozgi.io/skills/paddleocr-text-recognition/download
   If it fails, take the skill folder from the source: https://github.com/PaddlePaddle/PaddleOCR/tree/main/skills/paddleocr-text-recognition
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “paddleocr-text-recognition” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/paddleocr-text-recognition/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/PaddlePaddle/PaddleOCR.git /tmp/PaddleOCR
mkdir -p .claude/skills
cp -r /tmp/PaddleOCR/skills/paddleocr-text-recognition .claude/skills/paddleocr-text-recognition

Restart Claude Code — the skill appears in the list; call it manually with /paddleocr-text-recognition. For all projects use ~/.claude/skills.

git clone --depth 1 --branch main https://github.com/PaddlePaddle/PaddleOCR.git /tmp/PaddleOCR
mkdir -p .agents/skills
cp -r /tmp/PaddleOCR/skills/paddleocr-text-recognition .agents/skills/paddleocr-text-recognition

Codex looks for skills in .agents/skills from the current folder up to the repo root; call one with /skills or $paddleocr-text-recognition. For all projects use ~/.agents/skills.

git clone --depth 1 --branch main https://github.com/PaddlePaddle/PaddleOCR.git /tmp/PaddleOCR
mkdir -p .cursor/skills
cp -r /tmp/PaddleOCR/skills/paddleocr-text-recognition .cursor/skills/paddleocr-text-recognition

Cursor picks the skill up on start; call it with “/” in Agent chat. Cursor also reads .claude/skills and .agents/skills. For all projects use ~/.cursor/skills.

git clone --depth 1 --branch main https://github.com/PaddlePaddle/PaddleOCR.git /tmp/PaddleOCR
mkdir -p .gemini/skills
cp -r /tmp/PaddleOCR/skills/paddleocr-text-recognition .gemini/skills/paddleocr-text-recognition

Gemini CLI offers to activate the skill when a task matches — you approve it. For all projects use ~/.gemini/skills.

Review the source files

1 file Download Zip

Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.

SKILL.md contents

Original author text · read-only

PaddleOCR Text Recognition

When to Use This Skill

Use this skill for:

Extract text from images (screenshots, photos, scans)
Extract text from PDFs or document images when the goal is line/box-level text
Extract text from URLs or local files that point to images/PDFs

Do not use for:

Documents with tables, formulas, charts, or complex layouts — use Document Parsing instead

Usage

Basic OCR

From URL:

paddleocr api \
  --model_type ocr \
  --file_url "https://example.com/image.png"

From local file:

paddleocr api \
  --model_type ocr \
  --file_path "./document.pdf"

Common Options

# With specific model
paddleocr api \
  --model_type ocr \
  --model PP-OCRv5 \
  --file_path "./report.pdf"

# Disable preprocessing (faster, for flat/well-oriented images)
paddleocr api \
  --model_type ocr \
  --file_path "./document.pdf" \
  --use_doc_unwarping False \
  --use_doc_orientation_classify False

# Save result to file
paddleocr api \
  --model_type ocr \
  --file_url "https://..." \
  --output result.json

# Page ranges
paddleocr api \
  --model_type ocr \
  --file_path "./large.pdf" \
  --page_ranges "1-5,10,15-20"

Output Format

{
  "jobId": "job-xxx",
  "pages": [
    {
      "prunedResult": {
        "rec_texts": ["Line 1", "Line 2"],
        "rec_scores": [0.98, 0.95]
      },
      "ocrImageUrl": "https://..."
    }
  ]
}

Important Notes

Preprocessing options: By default, the API enables document preprocessing (unwarping and orientation classification). For flat, well-oriented images (screenshots, properly scanned documents), you can disable preprocessing for faster results:

paddleocr api --model_type ocr --file_path "./document.pdf" --use_doc_unwarping False --use_doc_orientation_classify False

Keep preprocessing enabled when:

The input is a photo of a curved or folded document
The document has significant perspective distortion
Orientation is uncertain (rotated 90/180/270 degrees)

Display complete results: Always show the full extracted content to users. Do not truncate with "..." unless content exceeds 10,000 characters. When multiple pages are processed, summarize if needed but provide complete results when explicitly requested.

Handle errors gracefully: When the CLI returns an error, inform the user of the specific issue rather than silently failing or falling back to your own vision capabilities. Common errors:

Authentication: PADDLEOCR_ACCESS_TOKEN invalid or missing
Quota: API rate limit exceeded
No content detected: Image may be blank or contain no text

CLI Reference

Run paddleocr api --help for all options.

For full documentation, see: PaddleOCR Official Documentation ↗

Frequently asked questions

What does the paddleocr-text-recognition skill do?

Extracts text from images, photos, scans, and screenshots with high accuracy, including handwritten and small print.

How do I install paddleocr-text-recognition?

Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.

Which AI models work with paddleocr-text-recognition?

Skills are plain Markdown instructions (the Agent Skills format), so paddleocr-text-recognition works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.

Is paddleocr-text-recognition free?

The skill is published openly by PaddlePaddle under the Apache-2.0 license. The skill itself costs nothing — you only pay your AI provider for the tokens you use.

Is it safe to install skills?

A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.

How is a skill different from an MCP server or a plugin?

An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.

Related skills

All skills →

meme-maker Creates memes from ready-made templates, suggesting formats and generating images locally or hosted. openclaw390k

stable-diffusion Generates images from text descriptions, allows editing existing images, and creating new ones based on them. NousResearch245k

clip Zero-shot image classification and image-text search. Understands images from natural language. NousResearch245k

segment-anything-model Segments any objects in images without prior training, using points, boxes, or masks. NousResearch245k

imagegen Generates or edits raster images like photos, illustrations, textures, or sprites for your project. openai122k

nanobanana-ppt Generates PowerPoint presentations from document analysis, utilizing AI and styled images from the NanoBanana stack. nexu-io95.9k