dsh-cupping
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-cupping
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-cupping in the DeepSeek Harness terminal to install the plugin; the source is available at https://github.com/uckkk/dsh-cupping .
About this plugin
Coffee lovers often hit the same wall: the exact brew recipe from last cupping session that produced the most balanced cup, yet the numbers have slipped into a notebook somewhere. dsh-cupping distills that cupping knowledge into a single callable tool—describe the conditions you care about in a conversation, and it returns the corresponding brewing recipe on the spot, eliminating the need to dig through notes.
Its core capability is deliberately narrow and focused: return a coffee cupping brew recipe based on the parameters you supply. Built entirely in Node.js with no network calls and zero external dependencies, the plugin works fully offline once installed, making it ideal for users who value privacy and minimal footprint.
It suits home pour-over enthusiasts, baristas on shift at specialty cafés, and anyone who wants to summon a cupping recipe with a single line in a chat session rather than recalling ratios from memory or hunting through a spreadsheet.
Use Cases
- Input bean variety and roast level to get instant water temperature and brew ratio recommendations
- Look up the corresponding brew time window when switching grind sizes
- Recreate the best-performing cupping recipe from your last session
Best For
- Home pour-over coffee enthusiasts
- Baristas on shift at specialty cafés
- Tech-oriented users who prefer offline, lightweight tools
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.