xby-classify
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-classify
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-classify in DeepSeek Harness to install it; the source is available at https://github.com/xby-skill/xby-classify .
About this plugin
When working inside DeepSeek Harness and you need a quick semantic label for an image—what is it and how confident is the model—assembling a separate inference pipeline, handling multiple input formats, and parsing the output can be heavy. xby-classify collapses that entire workflow into a single tool call, with no local GPU or inference framework required.
Built on an ImageNet-1000 classifier, it accepts three input formats (image URL, base64 string, or local file path) and uniformly returns the top-5 class names with their confidence scores, giving you a structured result in one call.
It is well suited for developers who want lightweight image recognition inside a DSH conversation—think content moderation, asset auto-tagging, or multimodal data preprocessing—getting on-demand classification results without any extra infrastructure.
Use Cases
- Quickly identify image content and return structured labels in conversation
- Auto-tagging and categorizing batches of visual assets
- Extracting image semantics during multimodal data preprocessing
Best For
- Developers needing lightweight image recognition inside DSH
- Automation engineers working on content moderation or asset management
- Teams building multimodal apps that require an image classification API
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.