More screenshots
Works with the AI Agents you already use
qcy watchface
Design and flash custom watch faces to QCY GT2 wearables over BLE using a reverse-engineered Python toolchain.
$5
qcy watchface
Example session with this skill installed
Generate a new watch face with a dark green accent #006400, no minute ticks, and a label that says 'LEAD'. Upload it to my QCY watch once generated.
- Read your context and instructions
- Compiled the qcy watchface
I have generated the custom watch face with your specifications. The layout features a dark green theme with the custom 'LEAD' label and a clean, tick-less interface.
Watch Face Build and Flash Log
| Step | Action | Status | Result |
|---|---|---|---|
| 1 | Generate Assets | Success | Created OUT/face.bin and OUT/face_full.png |
| 2 | Layout Validation | Success | Byte-check passed for JieLi/SMA format |
| 3 | Device Discovery | Success | Found QCY Watch GT2 (RSSI: -62 dBm) |
| 4 | Binary Transfer | Success | 114 KB uploaded in 28 seconds |
| 5 | Firmware Apply | Success | Watch reported face installed |
Next steps
- Verify Display: Check your watch screen to ensure the green accent #006400 meets your visibility needs.
- Reconnect Phone: You can now turn your phone's Bluetooth back on to resume sync services.
- Adjust Dimming: If the background is too bright, I can rebuild the face with a lower
--dimvalue.
Connects securely to your tools. The creator never sees your data.
About this skill
Designing and deploying custom firmware assets to wearable hardware usually requires proprietary apps and brittle manual steps. This skill provides a reverse-engineered toolchain for the QCY Watch GT2, allowing you to generate, preview, and flash custom watch faces directly from a Linux environment over Bluetooth LE.
What it does
- Face generation creates digital dials with custom colors, backgrounds, and labels using a specialized Python builder.
- Visual previewing generates
PNGrenders of the face at specific times to verify contrast and layout before flashing. - Automated validation performs byte-level checks on
dial.binfiles to ensure compatibility with JieLi/SMA firmware. - BLE orchestration manages the connection lifecycle, including device discovery and binary transmission.
- Hardware control executes remote commands for time synchronization, battery monitoring, and finding the device.
How it works
- Design the layout by specifying colors, accent hex codes, and background images via
makeface.py. - Review the
face_full.pngoutput to ensure all elements are visible and properly aligned. - Prepare the watch by disconnecting existing phone pairings to free up the BLE advertisement slot.
- Flash the binary to the watch using the
qcywatch facecommand, which handles the 30-second upload process.
Frameworks & tools
The toolchain is built on Python using the facekit.py library and qcywatch BLE client. It utilizes uv for dependency management and requires a Linux host with bluez (Experimental mode enabled) for Bluetooth communication.
Why this beats prompting it yourself
Generic LLMs cannot generate valid dial.bin binaries or handle the specific byte-packing requirements of the QCY firmware. This skill provides the exact logic for image masking, coordinate mapping, and BLE protocol handling that would take weeks to reverse-engineer manually.
Use cases
- Generate branded watch faces for corporate events or personal style.
- Automate time synchronization and notifications from a Linux server.
- Build complex analog layouts with custom complications using
facekit. - Recover or test watch functionality using the low-level CLI tools.
Known limitations
Requires a Linux host with Bluetooth LE hardware. Backgrounds must be exactly 454x455. Some complications like heart rate or step counters are experimental and may require layout iteration.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Requires Linux host with Bluetooth LE. Backgrounds must be exactly 454x455. High RSSI (>-85 dBm) needed for stable flashing. Some complications like HR and steps are experimental.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 21 days ago
- Software
Python
Git