dsh-plugin-8r
Run the following command in DeepSeek Harness:
dsh plugin install SensenMeng/dsh-plugin-8r
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, use the command 'dsh plugin install SensenMeng/dsh-plugin-8r' with the full source repository at https://github.com/SensenMeng/dsh-plugin-8r.
About this plugin
When interacting with AI, users sometimes want to automatically add playful markers to replies based on specific rules, like prefixing responses with '诶!「早八」' when '早八' is mentioned. However, traditional methods often require modifying model context or additional processing, which can disrupt the AI's thought process, pollute conversation context, or increase token overhead. dsh-plugin-8r solves this by locally determining the 8R rule, intelligently detecting user messages, and injecting a bold prefix into the AI reply stream. The entire process is done locally without the model's awareness, so it doesn't interfere with natural dialogue, consume extra resources, or impact performance. This allows users to implement rule-triggered personalized effects while maintaining the AI's native fluency. Ideal for developers or enthusiasts using DeepSeek Harness, this plugin is perfect for adding fun markers or scenario-based responses to AI interactions without complex model tuning. Whether enhancing chatbot interactivity or providing visual cues for specific content, dsh-plugin-8r integrates seamlessly to make conversations more creative and efficient.
Use Cases
- Automatically add bold '诶!' prefix when user messages trigger the 8R rule
- Inject playful markers into AI reply streams without affecting model thinking
- Enable personalized response rules for dialogue scenarios
Best For
- Developers and users of DeepSeek Harness
- Enthusiasts wanting to enhance AI interaction fun without performance loss
- Technicians needing local rule processing integrated into 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.