dsh-first-week
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-first-week
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-first-week in your terminal to install this plugin; the source is available at https://github.com/uckkk/dsh-first-week .
About this plugin
The first week on a new role is often the most fragmented: which docs to read, who to sync with, what to deliver—all scattered across chat threads and verbal handoffs. dsh-first-week turns that fuzzy period into a single, reusable workflow node. One call, and you get a structured first-week playbook filtered by the parameters you supply, instead of piecing together advice from ten different sources.
The entire capability lives in one tool called first_week. It is implemented in plain Node with zero network calls, so it runs entirely inside your local DeepSeek session—fast, deterministic, and free of external dependencies. Once installed, the tool is registered in your conversation; pass in your parameters and receive a step-by-step, well-structured onboarding outline.
Who is it for? Team leads who need to spin up a first-week checklist for different roles, freelancers who want a self-contained onboarding framework, or anyone who prefers to pull a structured workflow directly from an AI conversation rather than hunting through wiki pages. Lightweight, offline, MIT-licensed, and ready to use immediately.
Use Cases
- Generate a structured first-week checklist for new hires
- Pull step-by-step onboarding guidance directly in conversation
- Customize reusable onboarding workflows for different roles
Best For
- Team leads who need to build onboarding flows quickly
- Freelancers seeking a self-contained onboarding framework
- Users who prefer offline, network-free local AI 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.