AI Agent Hub
Back to plugins
⚙️

dsh-mattpocock-skills

Workflow Updated 2026.08.20

Run the following command in DeepSeek Harness:

dsh plugin install GongYuanCaiJi/dsh-mattpocock-skills

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install GongYuanCaiJi/dsh-mattpocock-skills in DeepSeek Harness to install; the source is available at https://github.com/GongYuanCaiJi/dsh-mattpocock-skills

About this plugin

The most common pitfall of AI-assisted coding is the absence of structured engineering discipline: the model either guesses or waits for you to re-prompt every single turn. This plugin ports 25 battle-tested engineering and productivity skills verbatim into DeepSeek Harness. On the engineering side you get TDD red-green loops, two-axis code review, stress-test questioning, requirement-to-spec and requirement-to-ticket workflows, domain modeling, codebase design, and bug diagnosis. On the productivity side the pack adds grilling, teach, handoff, and writing-for-agents. The model loads a full structured workflow when a task matches, instead of starting from scratch every turn.

All 76 skill files are byte-identical to the upstream release, with hashes pinned and a copy-paste diff command available for verification. There are zero runtime dependencies and no build scripts, and skills load lazily so there is no boot-time cost. You can let the model auto-match a skill during a session, or invoke one explicitly by starting a message with the skill name.

This is for developers who treat dsh as a daily engineering companion and want the AI to behave like a disciplined team member rather than a chat partner. If you just want a ready-to-use set of engineering workflows without worrying about upstream versioning details, this plugin is all you need.

Use Cases

  • Drive the model through red-green test cycles with /tdd during feature development
  • Run a two-axis review before committing with /code-review
  • Break requirements into specs and tickets with /to-spec or /to-tickets

Best For

  • Full-stack developers who use AI as a daily engineering companion
  • Teams that want structured tooling integrated into their coding workflow
  • Indie developers who follow Matt Pocock's engineering methodology