xby-ocr-driver-license
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-ocr-driver-license
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-ocr-driver-license in your DeepSeek Harness terminal to install the plugin. The source is available at https://github.com/xby-skill/xby-ocr-driver-license
About this plugin
Filling in Chinese driver's license data has always meant feeding an image to a general-purpose OCR engine and then fighting with the raw text to pull out the license number, permitted vehicle types, issue date, and expiry. xby-ocr-driver-license narrows the scope: it recognises only the front (nine fields) and back (file number) of a Chinese driver's licence and returns a clean structured object in one call, so downstream parsing is no longer your problem.
Three input channels are exposed: an image URL, a BASE64-encoded string, or a local file path, covering front-end upload, backend re-encoding, and offline batch pipelines alike. The API key is set once through a chat command and auto-persisted across session restarts, eliminating repetitive configuration.
It fits developers working inside the DeepSeek Harness ecosystem who need to turn a photo of a driver's licence into database-ready fields—HR onboarding, insurance underwriting, traffic-violation handling, or any workflow where a single scan should become structured records without hand-rolled prompt engineering and regex cleanup.
Use Cases
- HR onboarding flow that captures driver's license data in bulk
- Insurance underwriting that auto-validates licence expiry and permitted vehicle types
- Traffic-violation handling where a licence photo becomes structured database fields
Best For
- Developers building workflows inside the DeepSeek Harness ecosystem
- Backend engineers who need structured data from licence photos
- Business developers on document-capture or underwriting pipelines who want to skip hand-rolled prompt engineering
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.