dsh-mcmp
Run the following command in DeepSeek Harness:
dsh plugin install Aampidy/dsh-mcmp
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install the plugin using the command 'dsh plugin install Aampidy/dsh-mcmp', with the full source code address at https://github.com/Aampidy/dsh-mcmp.
About this plugin
dsh-mcmp is an automated paper-writing system designed for math modeling competitions, addressing the challenges of time-consuming, complex, and error-prone manual paper drafting during tight contest schedules. By automating the entire process from pasting the contest problem, it generates a structured, logically sound paper, allowing participants to focus more on problem analysis and innovative modeling. The plugin's core capabilities include a five-stage pipeline with 22 sub-stages: initialization, Exploratory Data Analysis (EDA), modeling, writing, and formatting. Each sub-stage is executed by specialized sub-agents and verified in real-time through a dual control-center verification mechanism to ensure content quality. If issues arise, the system automatically rolls back or makes precise modifications based on a P0-P3 grading scale, while persisting lessons learned to prevent recurrence, ultimately outputting a clean, compliant Markdown paper. dsh-mcmp is particularly suited for students participating in national math modeling contests, enabling both beginners and experienced teams to simplify the paper-writing process, boosting efficiency and quality.
Use Cases
- Automatically generate full papers in math modeling competitions
- For quick paper writing and validation in academic projects
- Learn paper structure and modeling processes in educational settings
Best For
- Students participating in national math modeling contests
- Researchers requiring efficient paper-writing tools
- Teachers and students in educational institutions
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.