xby-cellphone-detection
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-cellphone-detection
Paste the following prompt into your AI chat to install this plugin:
Install this plugin from https://github.com/xby-skill/xby-cellphone-detection by running dsh plugin install xby-skill/xby-cellphone-detection, then use the cellphone detection commands in your conversation.
About this plugin
Spot every cellphone in an image and get bounding boxes, confidence scores, and labels back in one call. That is what xby-cellphone-detection does. Whether you are working with e-commerce screenshots, street photos, or surveillance frames, a single image in gives you structured detection results out, with no need to build a model or write post-processing logic yourself.
The plugin accepts images three ways: a direct URL, a BASE64-encoded string, or a local file path. This covers online API calls, front-end uploads, and offline batch processing without extra serialization boilerplate. Returned results include per-object bounding box coordinates, model confidence, and class labels in a consistent format ready for downstream pipelines or database storage.
It is aimed at developers assembling image-understanding workflows, review systems that need to count or locate cellphones automatically, and anyone who wants minimal-code object detection. The built-in API key persistence means you configure once and keep working without re-entering credentials.
Use Cases
- Auto-locate cellphones in surveillance footage
- Batch-detect phone presence in e-commerce images
- Quickly generate cellphone bounding boxes in annotation pipelines
Best For
- Developers building image-understanding pipelines
- Review systems that track cellphone appearance
- Product teams wanting minimal-code phone detection
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.