xby-ocr-passport
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-ocr-passport
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-ocr-passport in DeepSeek Harness to install; the source repository is at https://github.com/xby-skill/xby-ocr-passport. (Get an API key from the XiaoBenYang website and set it via set_xby_apikey before first use.)
About this plugin
In visa processing, identity verification, and border-control workflows, passport fields are keyed into systems again and again. Manual transcription is slow and error-prone, especially for passport numbers and dates that must match exactly. xby-ocr-passport hands that repetitive step to a vision model, so a single passport photo yields the structured data you need.
The plugin extracts passport number, Chinese name, English name, gender, nationality, date of birth, issue date, expiry date, and issuing authority. It also parses the MRZ (Machine Readable Zone) for cross-validation and field completion. Three input modes are supported: image URL, Base64-encoded data, and local file path, which makes integration straightforward across different stacks. You only need an API key from the XiaoBenYang platform, set once and persisted across restarts.
If you are building an identity-verification pipeline, batch-processing traveller documents, or want to slot passport recognition into an existing business system, this plugin offers a lightweight model-inference capability you can call directly without assembling your own OCR stack.
Use Cases
- Batch-entering traveller passport data into visa management systems
- Rapidly extracting key passport fields during border verification
- Embedding structured passport recognition into existing business systems
Best For
- Developers building visa or border-control systems
- Operations teams processing traveller documents at scale
- Engineers integrating passport recognition into existing pipelines
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.