xby-ocr-biz-license
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-ocr-biz-license
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-ocr-biz-license in DeepSeek Harness to install this plugin; the full source is available at https://github.com/xby-skill/xby-ocr-biz-license
About this plugin
When handling company-related tasks, the information on a business license often demands tedious manual entry — unified credit codes, legal representatives, registered capital, business scopes… Many fields, inconsistent formats, and a single typo can cause downstream errors. xby-ocr-biz-license turns that chore into a single image-recognition call.
The plugin accepts three input types: image file URLs, Base64-encoded strings, and local file paths, covering everything from web screenshots to archived documents. One invocation extracts eight fields — unified credit code, name, legal representative, registered capital, establishment date, business scope, registration authority, and registered address — and returns them as structured data ready for databases or downstream pipelines. The API key can be set during a chat session and is auto-persisted across restarts.
If your workflow involves company registration, qualification review, supplier onboarding, data cleansing, or any automation step where a business-license image needs to become structured fields, this plugin is built for exactly that.
Use Cases
- Bulk-extract business license fields during supplier onboarding and load into a database
- Automatically pull key license fields in a qualification-review pipeline to cut manual checks
- Backfill structured fields such as credit codes and registered capital from archived license images during data cleansing
Best For
- Operations or risk-control staff handling company registration and qualification review
- Data-cleansing and ETL engineers
- Developers building automated approval workflows
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.