xby-medical-knowledge-graph
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-medical-knowledge-graph
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-medical-knowledge-graph in your DeepSeek Harness terminal to install this plugin; the full source is available at https://github.com/xby-skill/xby-medical-knowledge-graph .
About this plugin
Medical knowledge is notoriously fragmented—a single disease links to multiple drugs, a cluster of symptoms points to possible diagnoses, and a complication can trigger dietary restrictions. xby-medical-knowledge-graph organizes diseases, drugs, symptoms, diagnoses, complications, diet, and their relationships into a structured knowledge graph, giving DeepSeek Harness a dedicated memory layer for medical-domain queries without relying on scattered text fragments.
Three tools form its core: get_schema exposes every node type, property, and relationship in the graph so developers can understand the data model at a glance; execute_read_cypher runs read-only Cypher queries to traverse multi-hop connections flexibly; and set_xby_apikey persists the API key across sessions. The design is strictly read-only with no writes to the graph, minimizing the risk of accidental data corruption.
It is well suited for medical researchers, health-education content creators, and anyone who needs to answer cross-entity medical questions within a conversation. Keep in mind the graph is intended for preliminary research, and real-world applications should be validated case by case.
Use Cases
- Look up drugs, complications, and dietary restrictions linked to a given disease in conversation
- Traverse multi-hop chains from symptoms to diagnoses to drugs via read-only Cypher
- Inspect the graph schema, then craft targeted queries for specific business questions
Best For
- Medical researchers and clinical knowledge engineers
- Health education and patient communication content creators
- Developers who need to answer cross-entity medical questions in conversations
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
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.