xby-smoking-detection
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-smoking-detection
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-smoking-detection in your DeepSeek Harness terminal to install the plugin; the source code is hosted at https://github.com/xby-skill/xby-smoking-detection .
About this plugin
Identifying cigarette objects in images is a recurring requirement in content moderation, public-area surveillance, and compliance inspection workflows. The xby-smoking-detection plugin packages this visual detection capability into ready-to-call functions inside DeepSeek Harness, eliminating the engineering overhead of assembling a custom object-detection pipeline so developers can focus on business logic rather than model deployment.
The plugin accepts images through three input channels: a public URL, a BASE64-encoded string, or a local file path, covering remote calls, in-memory processing, and batch file scanning respectively. The API key is set once via a chat command and is persisted across restarts, removing the need for repeated configuration. Each detection call returns structured results that include bounding-box coordinates, confidence scores, and category labels for every cigarette object found in the frame, ready for downstream consumption.
It is well suited for engineering teams building content-safety pipelines, smart-monitoring dashboards, or compliance-automation tools, as well as for algorithm researchers who want to quickly validate cigarette-detection models within the DeepSeek Harness ecosystem.
Use Cases
- Image compliance moderation on content platforms
- Smoking behavior monitoring in public spaces
- Violation detection in advertising materials
Best For
- Content moderation engineers
- Smart surveillance product teams
- Algorithm researchers validating detection models
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.