dsh-cpr
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-cpr
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-cpr in DeepSeek Harness to install the dsh-cpr plugin from https://github.com/uckkk/dsh-cpr.
About this plugin
In the critical minutes after a sudden cardiac arrest at home, panic and forgetfulness are the biggest enemies. dsh-cpr wraps CPR (cardiopulmonary resuscitation) procedures into a tool you can invoke directly in a conversation, so you or your family member can pull up structured first-aid steps instantly without searching through a phone or connecting to the internet.
The core capability is straightforward: given a set of parameters, it returns a tailored home first-aid plan. The entire plugin is written in pure Node.js with zero network dependencies, making it fully functional in offline scenarios and ensuring information is available the moment you need it.
It is designed as an emergency reference for general households and non-medical users. Please note that it provides guidance for home scenarios and does not replace professional medical training or systematic first-aid coursework.
Use Cases
- Quickly look up CPR steps during a sudden cardiac arrest at home
- Access first-aid procedures without any network connection
- Teach basic first-aid knowledge to family members without medical training
Best For
- General users focused on home safety and emergency preparedness
- Non-medical professionals who need offline first-aid reference
- Caregivers preparing an emergency guide for their family
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.