xby-dish
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-dish
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-dish in DeepSeek Harness to install this plugin; the source repository is https://github.com/xby-skill/xby-dish
About this plugin
Snap a photo of a dish and still not sure what it is called? xby-dish is a DeepSeek Harness plugin designed for precisely that moment. It calls the Xiaobenyang dish-recognition API, takes a single photo of a plated dish, and returns a ranked list of candidate dish names with confidence scores, saving you the tedious job of scrolling through endless menus.
The plugin accepts images in three formats: a public URL, a Base64-encoded string, or a local file path, covering online screenshots, on-device captures, and batch-processing pipelines alike. The API key is configured once in chat and persisted automatically across restarts, so you are not re-entering credentials every session.
Whether you are a restaurant back-of-house team cataloguing dishes, a foodie curious about regional specialties, or a developer who needs structured dish-name extraction inside an image pipeline, xby-dish turns one clear photo into a usable, probability-ranked result.
Use Cases
- Restaurant back-of-house teams photographing dishes to catalog standard names instantly
- Food bloggers identifying regional specialties on the fly while shooting content
- Developers batch-extracting structured dish names and confidence scores in an image pipeline
Best For
- Restaurant operators and back-of-house teams
- Food enthusiasts and content creators
- Developers building AI image-recognition 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.