dsh-layer-match
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-layer-match
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-layer-match in DeepSeek Harness to install the plugin from its source at https://github.com/uckkk/dsh-layer-match.
About this plugin
In skincare-recommendation agent workflows, product matching is often the most critical yet hardest-to-standardize step: different skin types and concerns call for different regimens, and hand-maintaining lookup tables is neither practical nor scalable. dsh-layer-match tackles exactly this pain point by exposing a ready-to-use layer_match tool that accepts structured parameters and returns a matched facial skincare product selection, eliminating repetitive matching logic.
The plugin is implemented in pure Node with zero network dependencies. All matching logic runs locally, so responses are fast and deployment is trivial. It ships no extra frameworks and requires no server configuration; once registered, the tool is available for direct invocation inside any conversation.
If you are building a conversational recommendation system for a skincare brand, adding product-selection capability to an existing agent, or simply need a lightweight, offline-capable matching module, dsh-layer-match is a low-friction starting point.
Use Cases
- Auto-recommend a facial skincare regimen in a conversational agent based on user skin type and concerns
- Provide a lightweight, offline product-selection matcher for a skincare brand chat system
- Embed a zero-network, locally-running matching module into an existing workflow pipeline
Best For
- Developers building skincare-recommendation agents
- Teams needing an offline, zero-dependency product-matching module
- Engineers adding domain-specific selection logic to agent workflows
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.