dsh-plugin-xquant
Run the following command in DeepSeek Harness:
dsh plugin install codingDuan/dsh-plugin-xquant
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install the plugin using the command dsh plugin install codingDuan/dsh-plugin-xquant from GitHub, with the full source address at https://github.com/codingDuan/dsh-plugin-xquant.
About this plugin
In quantitative research, analysts often grapple with complex factor data and strategy logic, where tool integration and data access can be cumbersome and fragmented. The dsh-plugin-xquant addresses this by seamlessly integrating xquant's quantitative research MCP tools into DeepSeek Harness, allowing users to access quantitative research resources directly via the dsh Web interface. Its core capabilities include querying available factors and their definitions, computing factor time series for supported assets and time windows, and browsing strategy logic, historical performance, and signals within permissions, all while translating tool outputs into more readable research conclusions through a 'XiaoLiang'-style research guide. This empowers quantitative researchers and analysts to focus on analysis rather than tool switching and data consolidation. As a research tool, it does not provide specific investment advice, making it suitable for aiding academic or internal research scenarios.
Use Cases
- Query quantitative factor definitions to aid research analysis.
- Compute factor time series for specific assets and time windows.
- Browse strategy logic and historical performance for back-testing.
Best For
- Quantitative researchers conducting factor and strategy analysis.
- Financial analysts exploring historical data and signals.
- Data scientists integrating quantitative tools 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.