#601

Global Rank · of 601 Skills

qrcode-skills AI Agent Skill

View Source: caoliao/qrcode-skills

Medium

Installation

npx skills add caoliao/qrcode-skills --skill qrcode-skills

38

Installs

English | 中文

QR Code Skills

An agent skill for generating and decoding QR codes.

Fully local — no remote API or API key required.

Declaration:

  • All dependencies are open-source: Every dependency (Python: zxingcpp, Pillow, openpyxl, qrcode; Node.js: qrcode, qr-scanner-wechat, sharp, xlsx, archiver) is a publicly available open-source project. Source code and licenses can be found on PyPI / npm.
  • All operations run locally: Generation and decoding are performed entirely on the user's machine. No remote API calls, no data uploads. The only exception is when decoding a remote image URL; the image is downloaded locally first, then decoded.

For QR code generation URLs (preview without saving files) or better decoding accuracy, use qrcode-remote-skills: npx skills add caoliao/qrcode-remote-skills.

Features

Feature Description
Generate QR code Encode text/URL into a QR code image, saved locally
Decode QR code Read QR code content from a local image or image URL
Batch generate Generate QR code images locally from Excel/CSV/TXT
Batch decode Batch decode QR codes from Excel/CSV/TXT, write results back

Installation

Via skills CLI (Recommended)

npx skills add caoliao/qrcode-skills
# Global install (available across projects)
npx skills add caoliao/qrcode-skills -g

# Install for a specific agent
npx skills add caoliao/qrcode-skills -a cursor
npx skills add caoliao/qrcode-skills -a claude-code

Manual Installation

Clone this repository into your agent's skills directory:

git clone https://github.com/caoliao/qrcode-skills

Install Dependencies (pick one)

The agent will auto-detect your environment and install dependencies on first use. You can also install manually:

Python

cd qrcode-skills
pip install -r requirements.txt

Dependencies: zxingcpp, Pillow, openpyxl, qrcode

Node.js (when Python is unavailable)

cd qrcode-skills
npm install

Dependencies: qrcode, qr-scanner-wechat, sharp, xlsx, archiver

Both script sets are functionally identical. The agent auto-detects the available runtime.

Verify Installation

After installation, simply ask your agent "Generate a QR code for me" to trigger this skill.

Examples

Generate a QR Code

You: Generate a QR code for https://example.com

AI: (runs local generation script)

QR code generated and saved locally:

Local file: D:\workspace\qrcode.png


Generate & Save to Specific Path

You: Generate a QR code and save it to the desktop, content is Hello World, SVG format

AI: (runs local generation script)

QR code generated and saved locally:

Local file: C:\Users\xxx\Desktop\qrcode.svg


Decode a QR Code (Local File)

You: Decode this QR code (paste/drag an image)

AI: (gets image path, runs decode script)

QR code decoded (via zxing):


Decode a QR Code (URL)

You: Decode this QR code https://example.com/qr.png

AI: (downloads image locally, runs decode script)

QR code decoded (via zxing):


Batch Generate

You: Batch generate QR code images from the link column in products.csv, zip them up

AI: (runs script)

Batch generation complete: 200 total, 200 succeeded, 0 failed
Output directory: D:\output\qrcodes
ZIP file: D:\output\qrcodes.zip


Batch Decode

You: Batch decode QR code images in images.xlsx

AI: Detected the following columns. Which column contains the QR code image URLs?

Index Column Name
0 Product Name
1 Image Link
2 Notes

You: Column 1

AI: (runs script)

Batch decode complete: 50 total, 48 succeeded, 2 failed
Results written to: D:\data\images.xlsx (new "Decode Result" column added)

Project Structure

qrcode-skills/
├── README.md                   # English documentation (this file)
├── README.zh-cn.md             # Chinese documentation
├── SKILL.md                    # Agent skill instructions
├── requirements.txt            # Python dependencies
├── package.json                # Node.js dependencies
└── scripts/
    ├── generate.py / .js       # Single QR code generation & save
    ├── batch_generate.py / .js # Batch generation (images)
    ├── decode.py / .js         # Single decode (fully local)
    └── batch_decode.py / .js   # Batch decode (fully local)

Technical Details

  • Dual runtime: All scripts are available in both Python and Node.js with identical parameters and output formats
  • Generation: Uses local libraries (Python: qrcode / Node: qrcode) to generate QR code images directly
  • Decoding: Uses local libraries (Python: zxingcpp / Node: qr-scanner-wechat) for decoding, no remote dependency
  • Batch operations: Supports Excel (.xlsx), CSV, TXT input; auto-detects data columns, prompts user when ambiguous
  • Fully offline: All generation and decoding operations run locally with no network required (unless decoding input is a remote image URL)
  • Open-source only: All dependencies are open-source libraries; no proprietary or closed-source components

Installs

Installs 38
Global Rank #601 of 601

Security Audit

ath Safe
socket Safe
Alerts: 0 Score: 90
snyk Medium
zeroleaks Safe
Score: 93
EU EU-Hosted Inference API

Power your AI Agents with the best open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

Explore Inference API

GLM

GLM 5

$1.00 / $3.20

per M tokens

Kimi

Kimi K2.5

$0.60 / $2.80

per M tokens

MiniMax

MiniMax M2.5

$0.30 / $1.20

per M tokens

Qwen

Qwen3.5 122B

$0.40 / $3.00

per M tokens

How to use this skill

1

Install qrcode-skills by running npx skills add caoliao/qrcode-skills --skill qrcode-skills in your project directory. Run the install command above in your project directory. The skill file will be downloaded from GitHub and placed in your project.

2

No configuration needed. Your AI agent (Claude Code, Cursor, Windsurf, etc.) automatically detects installed skills and uses them as context when generating code.

3

The skill enhances your agent's understanding of qrcode-skills, helping it follow established patterns, avoid common mistakes, and produce production-ready output.

What you get

Skills are plain-text instruction files — not executable code. They encode expert knowledge about frameworks, languages, or tools that your AI agent reads to improve its output. This means zero runtime overhead, no dependency conflicts, and full transparency: you can read and review every instruction before installing.

Compatibility

This skill works with any AI coding agent that supports the skills.sh format, including Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider, and other tools that read project-level context files. Skills are framework-agnostic at the transport level — the content inside determines which language or framework it applies to.

Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.

EU Made in Europe

Chat with 100+ AI Models in one App.

Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, GLM-5, Kimi K2.5 and many more.

Customer Support