dsh-engineering-workflow
Run the following command in DeepSeek Harness:
dsh plugin install 82c86b8z86-stack/dsh-engineering-workflow
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command: dsh plugin install 82c86b8z86-stack/dsh-engineering-workflow, or visit the GitHub repository at https://github.com/82c86b8z86-stack/dsh-engineering-workflow for more details.
About this plugin
In software development, handling complex engineering tasks often lacks a structured workflow, leading to inefficiencies and ad-hoc decision-making. The dsh-engineering-workflow plugin addresses this by providing an engineering workflow layer for DeepSeek Harness. At its core is the engineering workflow preset, which incorporates five hard-gated phases: requirements clarification, plan approval, TDD implementation, parallel subagent execution, and verified finishing. Each phase enforces discipline rules through corresponding skills like workflow-requirements and workflow-planning, ensuring every step is based on clear intent and verified evidence, with methodology adapted from obra/superpowers and tailored to dsh's native tools. This plugin is ideal for all engineers and developers using DeepSeek Harness, especially those seeking to enhance the rigor and repeatability of their development process, helping manage tasks systematically, reduce arbitrary decisions, and improve code quality.
Use Cases
- Managing complex engineering projects from requirements clarification to verified finishing.
- Implementing structured, disciplined workflows within development teams.
- Improving code quality, reducing ad-hoc decisions, and boosting development efficiency.
Best For
- Software engineers and developers using DeepSeek Harness.
- Teams requiring rigorous engineering practices and repeatable processes.
- DevOps professionals or technical leaders seeking efficient collaboration and high-quality delivery.
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.