xby-helmet-head
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-helmet-head
Paste the following prompt into your AI chat to install this plugin:
Run the install command in DeepSeek Harness to add this plugin; the full source repository is at https://github.com/xby-skill/xby-helmet-head
About this plugin
Manually reviewing site photos to confirm that every worker wears a hard hat is slow, repetitive, and prone to missed targets during large-scale inspections. xby-helmet-head compresses that workload into a single image upload: it simultaneously detects persons, heads, and helmets, and returns bounding-box coordinates, confidence scores, and class labels for every target in the frame, giving compliance decisions a quantitative basis.
The plugin accepts images via URL, BASE64 encoding, or local file path, so it slots naturally into online pipelines, mobile screenshot workflows, or offline batch processing. The API key is set once through a chat command and persisted automatically across session restarts, removing a common setup friction.
It is well suited for safety officers handling daily compliance spot-checks, engineers embedding helmet detection into a broader vision pipeline, and developers who want to evaluate detection quality quickly without standing up their own inference stack.
Use Cases
- Batch review of site photos during inspections to verify workers wear hard hats
- Embedding helmet detection as a node in a larger visual compliance monitoring pipeline
- Quickly validating the output quality of a helmet detection model on real-world scenes
Best For
- Site safety officers performing daily compliance spot-checks
- Algorithm engineers building visual detection pipelines
- Developers who want to evaluate detection capabilities without standing up their own inference stack
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.