dsh-a-stock-select
Run the following command in DeepSeek Harness:
dsh plugin install ct188579/dsh-a-stock-select
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install ct188579/dsh-a-stock-select in your DeepSeek Harness terminal to install this plugin (source at https://github.com/ct188579/dsh-a-stock-select), then restart dsh to use it in any session.
About this plugin
A-share investors often struggle with fragmented data sources, intuition-driven stock picking, and the lack of a structured process for reviewing their holdings. dsh-a-stock-select consolidates all 47 data endpoints from a-stock-data V3.6.1—spanning quotes, research reports, capital flows, dragon-tiger lists, lockup expiries, limit-up pools, financial statements, and announcements—into a single self-contained skill with a complete data-fetch, filtering, and output pipeline, removing the need to juggle multiple external tools.
The plugin ships with four investment-horizon strategies covering ultra-short (1-3 trading days), short (1-4 weeks), medium (1-6 months), and long (6+ months) timeframes. Every strategy enforces strict stop-loss discipline, automatically excludes ST stocks, monitored-pool names, and limit-down candidates, and appends a risk disclaimer to each output. The position-diagnosis workflow runs a seven-step data-verification process and delivers a clear hold, trim, or exit verdict along with identified support, resistance, and stop-loss levels plus trigger conditions, turning vague market intuition into an actionable decision framework.
It is designed for individual A-share investors who want a systematic approach to stock selection and portfolio management, as well as DSH or Claude Code workflow developers seeking a zero-dependency, out-of-the-box data and strategy layer that can be embedded into their own pipelines without configuring external APIs.
Use Cases
- Systematically screen A-share stocks across ultra-short, short, medium, and long timeframes
- Run a seven-step data verification on existing holdings and get a clear hold, trim, or exit verdict
- Invoke a self-contained selection and diagnosis skill directly inside DSH or Claude Code sessions
Best For
- Individual A-share investors who want to move beyond fragmented data sources and manage holdings systematically
- Quant-research enthusiasts who need multi-endpoint data aggregation combined with strategy-based filtering
- DSH or Claude Code plugin developers looking for a zero-dependency data and strategy layer to embed in their 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.