dsh-plugin-advisor
Run the following command in DeepSeek Harness:
dsh plugin install haveanote06/dsh-plugin-advisor
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install haveanote06/dsh-plugin-advisor in your terminal to install; the source repository is available at https://github.com/haveanote06/dsh-plugin-advisor
About this plugin
When running tasks in DeepSeek Harness, you will often hit a wall where the current toolset is not enough and you need an extra plugin. The old workflow meant digging through the dsh-plugin topic on GitHub, comparing a dozen repositories, guessing which one is reliable, and typing the install command by hand — slow and error-prone.
dsh-plugin-advisor turns that into a single conversational exchange. You describe your need in plain language, and the advisor walks a clear pipeline: first check whether an already-installed local plugin covers the requirement (if yes, stop), then search the community ecosystem, score every candidate using objective signals such as curated-list inclusion, Stars, npm weekly downloads, recent activity, and repo structure completeness, and finally present a ranked list with a transparent score breakdown. Installation only happens after you explicitly confirm — it never installs silently.
It is built for developers who work with Agent workflows in DeepSeek Harness and want a fast, explainable, and safety-first path from "I need a plugin" to "it is installed" without switching to a browser tab or second-guessing which repo to pick.
Use Cases
- Extend capabilities mid-conversation when the current toolset falls short
- Compare similar community plugins at a glance using multi-signal quality scores
- Describe a requirement in one sentence and get a scored, confirmed plugin install
Best For
- Developers building Agent workflows on DeepSeek Harness
- Solo developers who prefer automated plugin discovery over manual GitHub browsing
- Teams that prioritize install safety and explainable plugin recommendations
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.