xby-ai-persona
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-ai-persona
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-ai-persona in your DeepSeek Harness terminal to install this plugin; source repository at https://github.com/xby-skill/xby-ai-persona
About this plugin
In real projects, a single AI persona struggles to cover code review, product thinking, and architecture design at the same time. xby-ai-persona lets developers summon different AI personas to collaborate within one conversation, delivering multi-perspective intelligent analysis on demand.
As an MCP protocol server, it exposes core tools such as summon_persona to invoke a specific persona, interactive_persona to auto-select the most fitting persona based on conversation context and perform step-by-step analysis, and list_personas to browse all available personas. API keys are persisted automatically, so a restart does not wipe your configuration.
It is well suited for developers and product teams who want to integrate multi-role intelligent collaboration into their DeepSeek Harness workflow, especially those who need both an engineer perspective and a designer perspective on code reviews or product strategy.
Use Cases
- Summon multiple personas during code review for multi-angle quality analysis
- Let different personas offer user-side and business-side suggestions in product design sessions
- Auto-select the best-fit persona based on conversation context for everyday development decisions
Best For
- Developers who want multi-role AI collaboration in a DSH workflow
- Product teams needing both engineering and design perspective feedback
- Technical users extending AI collaboration capabilities via the MCP protocol
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.