dsh-product
用于产品战略、POC、MVP、测试版、PMF、发布准备和增长交接的 DeepSeek Harness 工具。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:winyh/dsh-product#ed21d4eae523ae93fedf79e45afe1600a5c5918dProduct 以 dsh-product 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 中文
dsh-product 是一个“互联网资讯查询 + 本地项目上下文”的 DeepSeek Harness 插件，用于把已经确认的产品机会转化为可验证、可交付、可迭代的产品。
dsh-product is a web-aware DeepSeek Harness plugin that combines public internet research with local product context to turn a validated opportunity handoff into a shippable, observable and iterated product.
Its workflow is:
Demand → Product → Marketing → Monetization → Product iteration / new opportunity discovery
It complements dsh-idea and dsh-growth:
dsh-idea owns demand and opportunity discovery.dsh-product owns product definition, feasibility, delivery gates and PMF evidence.dsh-business owns the cross-cutting commercial strategy: value, business model, pricing and profitability.dsh-geo and dsh-growth own the marketing stage: discoverability, acquisition, activation and growth operations.dsh-sales owns monetization execution: qualification, closing, expansion and renewal.dsh-product is the product-delivery and PMF layer in the six-plugin system. It turns an evidence-backed opportunity into a shippable, observable and iterated product, using PMF evidence to decide whether to continue, adjust or pause.
The six plugins work together to turn a real demand signal into a deliverable product, reach target customers through marketing, and use monetization results to drive product iteration or discover new opportunities.
flowchart TB
S["dsh-business<br/>Commercial strategy layer<br/>Value · model · pricing · profit"]
subgraph MAIN["Four-stage core flow"]
direction LR
A["1. Demand<br/>dsh-idea"] --> B["2. Product<br/>dsh-product"]
B --> C["3. Marketing<br/>dsh-geo + dsh-growth"]
C --> D["4. Monetization execution<br/>dsh-sales"]
end
S -. "Sets commercial direction and guardrails" .-> A
D --> R["Feedback<br/>Deals · renewals · revenue · cost"]
R -->|Product iteration| B
R -->|New discovery| A
classDef strategy fill:#FFF4D6,stroke:#B7791F,color:#5C4500
classDef stage fill:#E8F1FF,stroke:#3366CC,color:#173A7A
classDef feedback fill:#E8F7EE,stroke:#2F855A,color:#1C4532
class S strategy
class A,B,C,D stage
class R feedback
This plugin owns the product stage: after dsh-idea proves that a problem is worth testing, it defines what to build, how small to start and how to measure the result. dsh-business supplies commercial constraints; dsh-geo and dsh-growth take the product into marketing; and dsh-sales returns close, loss, renewal and unmet-need evidence.
| Plugin | Clear responsibility | Direct link |
|---|---|---|
| dsh-idea | External opportunities, demand signals, candidate directions and smallest useful tests | README |
| dsh-product | Product definition, POC/MVP, release gates and PMF (this plugin) | README |
| dsh-business | Cross-cutting commercial strategy, value, pricing and profitability | README |
| dsh-sales | Monetization execution: qualification, deal progression, closing, expansion and renewal | README |
| dsh-growth | Acquisition, activation, retention, revenue analysis and growth experiments | README |
| dsh-geo | SEO/GEO/AEO, content production and search/answer-engine discoverability | README |
| Output from this plugin | Hand off to | Handoff question |
|---|---|---|
| Product brief, POC/MVP scope and user-value evidence | dsh-business | How should we package and price it, and can the unit economics work? |
| PMF review, behavior data and core usage contexts | dsh-growth | Which funnel, retention or revenue lever should we test first? |
| Confirmed value proposition, capability boundaries and sales inputs | dsh-sales | Which customers are worth pursuing and how should we progress the deal? |
| Product language, user problems and release content | dsh-geo | How can target users discover the product through search and answer engines? |
The plugin reads local Markdown and bounded CSV/JSON/JSONL evidence, can query public product information, preserves lineage and uses preview-plus-confirmation for file writes. Web research does not automatically send local files, cookies or login state to a provider. It does not create code, design files, CRM records or external campaigns.
See the Chinese README for the Chinese workflow and examples.