dsh-pack-skill
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-pack-skill
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-pack-skill in your terminal to install the plugin in DeepSeek Harness; the source code is hosted at https://github.com/uckkk/dsh-pack-skill, and you can call the registered tool directly in a session after installation.
About this plugin
In agent workflows, planning a relocation or packing schedule typically requires hand-crafted prompt orchestration, and there is rarely a lightweight, offline-ready tool node to handle it. dsh-pack-skill closes that gap: it registers a tool called pack_skill that accepts relocation parameters and returns a structured packing plan in one shot, so your agent can complete the planning step inside the conversation without calling any external service.
The entire implementation is written in pure Node.js with zero network dependencies. It runs reliably in fully offline sandboxes, edge environments, and air-gapped corporate networks, and it will never stall your pipeline because an upstream API is down.
If you are building an agent workflow around moving, warehousing, or logistics and want a minimal, plug-and-play planning node with no external dependencies, dsh-pack-skill offers a clean and dependable solution.
Use Cases
- Generating a packing plan for a move or relocation via an agent
- Running logistics planning nodes in offline or air-gapped environments
- Plugging a lightweight packing-decision step into an agent workflow
Best For
- Developers building agent workflows for moving or logistics
- Teams running agents in offline sandboxes or corporate air-gapped networks
- Engineers looking for a dependency-free planning node
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.