payment-assistant
Binance Pay Assistant - Send and Receive crypto payments. buy/purchase/pay/transfer/send, confirm/cancel payment, or query order status. Requires QR code data. PIX QR codes (pix, br.gov.bcb.pix) are auto-detected. receive/collect payment (generate receive link, receive QR). Do NOT use for earning, buying/selling crypto, or digital goods.
npx skills add binance/binance-skills-hub --skill payment --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Automates Binance Pay interactions for sending and receiving crypto payments via QR codes. It supports actions to purchase (parseQR, set_amount, pay_confirm), query status, and receive payment links or QR codes. It auto-detects C2C vs PIX QR types and routes to corresponding endpoints. It can generate receive links/QRs for collecting payments and handles QR code data requirements and PIX auto-detection.
How it works
The skill provides a structured 3-step flow: purchase (parse QR data from a QR image or text), confirm/purchase (set amount if needed), and poll status until completion. It exposes CLI actions like purchase, set_amount, pay_confirm, poll, and query. For inputs, it requires one of three QR input modes: --image <path>, --base64 <data>, or --clipboard, and enforces using --action decode_qr to decode before purchase. After decoding, it proceeds to purchase with the obtained QR data. It also supports receiving payments via receive, generating a shareable link and QR, and uses explicit user confirmation before finalizing payments.
When to use it
Use when the user intends to perform a Binance Pay transaction via QR: buying/purchasing/pay/transfer/send, or when the user wants to receive/collect payment. PIX QR data is auto-detected; for receiving, use the receive flow. Do not use for earning, buying/selling crypto, or digital goods.
What it can touch
The skill requires input via CLI actions and QR decoding steps. It mentions Python-based commands like python3 payment_skill.py with actions: decode_qr, purchase, set_amount, confirm, pay_confirm, poll, and receive. It also references endpoints such as binancepay/openapi/... for parsing/confirming payments and querying status, and uses fields like --raw_qr, --image, --base64, and --clipboard for input.
Caveats
The skill emphasizes a strict 3-step flow: decode → purchase → [set_amount] → confirm → poll, and requires explicit user confirmation before pay_confirm. It auto-detects QR types (C2C vs PIX) and routes accordingly. It warns not to bypass decoding or skip user confirmation, and to treat certain API-returned fields as display-only (untrusted). It also mandates language matching to the user and proper handling of QR data input modes. The provided documentation includes MIT-licensed repository references and prerequisites for Python packages (opencv-python, pyzbar, Pillow, requests).
## ⚠️ CRITICAL: How to Handle QR Images **When user sends a QR code image or asks to pay:** ### Step 0: Check if user provided a PAYMENT LINK (text, not an image) If the user provided **text** (not an image), and the text is a URL containing `app.binance.com/uni-qr/` or `app.binance.com/qr/`: → This is a payment link. Skip all decode steps. Go directly to purchase: ```bash python3 payment_skill.py --action purchase --raw_qr "<the URL text>" ``` Otherwise (user sent an image, or text doesn't match above) → continue to Step 1. ### Step 1: Try to READ the QR data directly (Vision) Look at the QR code image and try to extract the actual data string (URL or EMV code). - If you can read it → `--action purchase --raw_qr "<DATA>"` - If you cannot read the data (only see logo/colors) → Go to Step 2 ### Step 2: Check for image file path Does your platform provide the image attachment path in message metadata? - If YES → `--action decode_qr --image "<PATH>"` - If NO → Go to Step 3 ### Step 3: Ask user for help (DO NOT auto-use clipboard!) ``` "I cannot read the QR directly. Please copy to clipboard, then reply 'use clipboard'" ``` (Translate to user's language as needed) ### Step 4: Only afte
- ⚠️ CRITICAL: How to Handle QR Images
- Step 0: Check if user provided a PAYMENT LINK (text, not an image)
- Step 1: Try to READ the QR data directly (Vision)
- Step 2: Check for image file path
- Step 3: Ask user for help (DO NOT auto-use clipboard!)
- Step 4: Only after user confirms → use clipboard
- 🚀 Quick Start - Agent MUST Execute
- Step 1 - Get QR Data (Choose ONE method)
- Step 2 - Purchase (IMMEDIATELY after getting QR data)
- Step 3 - Set amount (if needed)
- Step 4 - Confirm payment (after user confirms)
- 📦 Prerequisites
- ⛔ STOP - READ THIS FIRST (Agent MUST Follow)
- ❌ NEVER DO
python3 payment_skill.py --action purchase --raw_qr "<the URL text>" python3 payment_skill.py --action decode_qr --clipboard python3 payment_skill.py --action purchase --raw_qr "https://app.binance.com/uni-qr/xxx" Use the attachment path your platform provides python3 payment_skill.py --action decode_qr --image "/path/to/attachment.jpg" python3 payment_skill.py --action decode_qr --base64 "iVBORw0KGgo..." python3 payment_skill.py --action purchase --raw_qr "DECODED_QR_DATA" python3 payment_skill.py --action set_amount --amount NUMBER python3 payment_skill.py --action confirm pip install -r requirements.txt
What does the payment-assistant skill do?
Binance Pay Assistant - Send and Receive crypto payments. buy/purchase/pay/transfer/send, confirm/cancel payment, or query order status. Requires QR code data. PIX QR codes (pix, br.gov.bcb.pix) are auto-detected. receive/collect payment (generate receive link, receive QR). Do NOT use for earning, buying/selling crypto, or digital goods.
How do I install it?
Run `npx skills add binance/binance-skills-hub --skill payment --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From binance/binance-skills-hub, a repository with 947 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.