dsh-shop-assistant
Run the following command in DeepSeek Harness:
dsh plugin install pengzhou267-ai/dsh-shop-assistant
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install pengzhou267-ai/dsh-shop-assistant inside DeepSeek Harness to install this plugin; see https://github.com/pengzhou267-ai/dsh-shop-assistant for details.
About this plugin
Running a shop means three tasks eat up the most hours: replying to bad reviews one by one, squeezing new-listing copy out of a competitor page, and re-checking whether a given price actually makes money. Throwing these into a web AI chat quickly runs into problems - context overflow on long tables, re-typing your return policy every turn, profit numbers that shift whenever you ask again. The copy-paste loop ends up slower than doing it by hand.
dsh-shop-assistant locks these three high-frequency workflows into repeatable, file-driven processes. For reviews, drop a full CSV into the workspace folder and the plugin generates grouped, paste-ready replies aligned to your own policy file, keeping wording consistent across every row. For new listings, paste a public product URL and the assistant snapshots the page, then drafts titles, bullets, and FAQs using a built-in playbook, preferring on-page price data over guesses. For pre-listing checks, enter cost, price, and 1-5 scores; a fixed formula returns profit and a Go or No-Go verdict, so identical inputs always produce identical outputs.
The plugin is built for shop owners, CS leads, and operations staff who do not write code. You never need to type an internal tool name; plain-language instructions plus a file in the workspace folder are all it takes. Sample data and a return-policy template ship with the package, so you can validate all three workflows with dummy data before swapping in your real business content.
Use Cases
- Batch-reply to bad reviews aligned with your return policy
- Generate listing titles, bullets, and FAQs from a competitor page
- Score new-product profit and risk with a fixed formula before listing
Best For
- Shop owners who do not write code
- CS and after-sales team leads
- Operations staff responsible for product selection and listing
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.