dsh-gaokao-split
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-gaokao-split
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-gaokao-split in the DeepSeek Harness terminal to install; the source repository is https://github.com/uckkk/dsh-gaokao-split .
About this plugin
When planning gaokao preparation, students and teachers often rely on gut feel to split months of study into phases, with no structured tool to back up the decisions. dsh-gaao-split, an agent-workflow plugin, registers a gaokao_split tool that lets an AI workflow compute a precise preparation-time breakdown from user-supplied parameters and return detailed, structured results, turning a vague 'study for a few months' into an actionable phase-by-phase plan.
The plugin is implemented in pure Node.js with zero network dependencies at runtime. All calculation logic runs locally, keeping it lightweight and privacy-friendly. After installation there is no extra configuration to manage; simply invoke the registered tool in a conversation and receive the result immediately, making integration cost extremely low.
It is a good fit for developers building preparation-planning workflows, as well as students and teachers who want AI-assisted study scheduling. The MIT license allows free forking, modification, and integration into any custom project.
Use Cases
- Auto-split a multi-phase preparation plan by subject and total days
- Generate a study-time allocation plan with one prompt in an AI chat
- Serve as a local computation node inside a preparation-assistant workflow
Best For
- Students and teachers preparing for the gaokao
- Developers building AI agent workflows
- App developers needing a local time-calculation utility
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.