lunw/shopline-ai-toolkit-dsh

Name: lunw/shopline-ai-toolkit-dsh
Author: lunw

Plugin插件 Native原生 ⭐ 5 MIT Notifications & Remote通知与远程 Prompts & Skills提示词与技能

SHOPLINE AI 工具包 for DeepSeek Harness（dsh-plugin）：官方 SHOPLINE 开发者 MCP 桥接器 + SHOPLINE 代理技能，镜像 Shopify AI 工具包架构。dsh-plugin

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This repository is a native DSH plugin built specifically for SHOPLINE developers working within the DeepSeek Harness AI coding environment. It ports the popular three-layer Shopify AI Toolkit architecture to the SHOPLINE platform, bringing SHOPLINE-specific development context, agent skills, and MCP-powered tool access to DSH. To install the full plugin bundle, you can run the DSH CLI command dsh plugin --profile <name> add shopline-ai-toolkit-dsh, then add the plugin to your profile's bundle list and restart your DSH session. If you only want the SHOPLINE skills, you can manually copy the skill files to your local DSH skills directory.

The toolkit includes 8 pre-built SHOPLINE agent skills that cover onboarding, REST API, GraphQL, OAuth, webhooks, the Sline template engine, MCP usage, and a supplement for undocumented SHOPLINE app development gaps. The official SHOPLINE Developer MCP is bridged through DSH's native MCP client, giving you access to tools like endpoint search, schema retrieval, and GraphQL code validation. An optional community MCP from sline.dev that adds admin schema introspection and Sline theme validation is also included, though it is commented out by default for new users. When you run a SHOPLINE-related development task, DSH will automatically load the relevant skills and call the corresponding MCP tools.

This project is released under the open source MIT license, and it is not affiliated with or endorsed by the official SHOPLINE team. All skill content is sourced from SHOPLINE's official developer documentation and community developer experience, so official SHOPLINE resources remain the authoritative source of truth for all platform information. The supplementary skill for undocumented development gaps will be retired incrementally once SHOPLINE's official documentation covers those missing areas. You will need Node.js installed to run the MCP server dependencies required by this toolkit.

本项目是专为 DeepSeek Harness (DSH) 打造的原生插件，面向 SHOPLINE 开发者，将 SHOPLINE 开发者 MCP 官方工具与 SHOPLINE 平台开发知识整合进 DSH AI 编程助手。它参照 Shopify AI Toolkit 的三层架构实现，包含代理技能、官方 Dev MCP 桥接和可选社区 MCP 支持，可通过 DSH 内置插件命令直接安装。

面向开发 SHOPLINE 应用的开发者，帮助 AI 编程助手获取 SHOPLINE 平台上下文，完成接口查询、文档检索、GraphQL Schema 获取、代码校验等常见开发任务。用户提出开发相关问题后，助手会自动加载对应技能，调用 MCP 工具获取所需信息后给出回答，适配 SHOPLINE 开发全流程。

本项目采用 MIT 许可证，与 SHOPLINE 官方无隶属关系，所有内容均来自官方文档和社区实践，其中文档盲区补充技能会在官方文档完善后逐步撤回。安装完整包可通过 DSH 插件命令，仅需技能也可手动复制，官方 MCP 需要安装对应 npm 依赖，社区 MCP 默认关闭。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：shopline-ai-toolkit-dsh（lunw/shopline-ai-toolkit-dsh）
仓库：https://github.com/lunw/shopline-ai-toolkit-dsh
本站详情页：https://www.yhbd.top/plugins/lunw-shopline-ai-toolkit-dsh/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 5 · 最近提交 2026-08-27 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 5 stars - very few users, little community feedback星标只有 5，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add shopline-ai-toolkit-dsh

把 lunw/shopline-ai-toolkit-dsh 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

6.9 KB · 缓存于 2026-08-23 03:42:18 · 6.9 KB

SHOPLINE AI Toolkit for DeepSeek Harness (DSH)

🛍️ SHOPLINE AI Toolkit — a DeepSeek Harness (dsh) plugin that brings SHOPLINE 开发者 MCP 官方工具与 SHOPLINE 平台知识技能 到你的 AI 编程助手。架构参照 Shopify AI Toolkit：Skills + Dev MCP Server + Agent Plugin。

dsh-plugin · SHOPLINE · MCP · AI Toolkit · DeepSeek Harness

English · 简体中文

English

What is this?

The Shopify AI Toolkit gives AI coding agents Shopify-aware context through three layers: agent skills, a Dev MCP server, and per-tool plugins. This project brings the same architecture to SHOPLINE developers working inside DeepSeek Harness (dsh):

Layer	What you get
🧠 Agent skills (`skills/`)	8 SKILL.md bundles: `shopline-onboarding-dev`, `shopline-admin-rest`, `shopline-graphql`, `shopline-oauth`, `shopline-webhook`, `shopline-sline`, `shopline-dev-mcp` (documented behavior) + `shopline-app-dev-doc-gaps` (app-dev doc-gap supplement, withdrawable once official docs cover it) — endpoint URLs, signing rules, error codes, retry policies, all grounded in developer.shopline.com docs and community experience
🔌 Dev MCP bridge	The official SHOPLINE Developer MCP (`@shoplineos/shopline-developer-mcp`, local stdio, no auth) is wired through dsh's native MCP client — tools appear as `mcp__shopline__search_shopline_docs`, `mcp__shopline__get_admin_rest_endpoint_detail`, `mcp__shopline__get_graphql_schema`, `mcp__shopline__validate_graphql_codes`, …
🎛️ Optional community MCP	sline.dev server (`@shopline/dev-mcp`) adds `mcp__sline__introspect_admin_schema`, `mcp__sline__validate_theme`, … (commented out by default)
📦 dsh bundle	`cordis.patch.yml` + `lib/index.js`, installable with `dsh plugin --profile <name> add shopline-ai-toolkit-dsh`

Install

See docs/install.md. Quick start (full bundle):

dsh plugin --profile web add shopline-ai-toolkit-dsh
# add "shopline-ai-toolkit-dsh" to dsh.profile.bundles in ~/.dsh/profiles/web/package.json
dsh web

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 lunw/shopline-ai-toolkit-dsh 的 README.md。在 GitHub 查看原文 →