dsh-experts
Run the following command in DeepSeek Harness:
dsh plugin install libinyam/dsh-experts
Paste the following prompt into your AI chat to install this plugin:
To install the dsh-experts plugin in DeepSeek Harness, run the command dsh plugin install libinyam/dsh-experts, or clone the source repository https://github.com/libinyam/dsh-experts into your project directory.
About this plugin
How can an AI model collaborate like a team rather than acting alone in complex workflows? The dsh-experts plugin is designed to solve this by bringing the concept of an "expert team" to life. It allows users to define expert teams through simple configuration files and Markdown cards, effectively addressing the lack of structured collaboration capabilities in AI. This enables the model to simulate real-world role division—such as coordinators, front-end, back-end, and testers—allowing it to handle more complex tasks.
Use Cases
- Evaluate code quality and promotion readiness of a project
- Simulate real team collaboration to complete complex development tasks
- Configure exclusive expert routing strategies for specific domains
Best For
- Users of the DeepSeek Harness platform
- AI engineers requiring complex workflow orchestration
- Team leads wanting customized expert models
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.