Product Diagnosis

by Stanshy

Product Diagnosis is an AI Engineering skill for Claude Code, published by Stanshy in AgentHub.

201 stars23 forkson Stanshy/AgentHubAdded 2026/09/05+1% in starsRepository updated 2026/04/09

View source on GitHub Download repo ZIP

ai-agentsai-workflowclaude-codedeveloper-toolselectronharness-engineeringopen-sourceteam-managementtypescriptvue

Install in seconds

Install Product Diagnosis

Copy Product Diagnosis into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Stanshy/AgentHub/tree/main/.knowledge/company/skill-templates/product-diagnosis ~/.claude/skills/product-diagnosis

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Stanshy/AgentHub.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .knowledge/company/skill-templates/product-diagnosis/SKILL.md in Stanshy/AgentHub
Installs to: ~/.claude/skills/product-diagnosis
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3101 skills

What Product Diagnosis does

Product Diagnosis uses a six-question framework to validate product direction before development starts. Use it to assess problem fit, user needs, scope, architecture alignment, and risk for G0 proposals.

Product Diagnosis is cataloged under AI Engineering on DirSkills. Product Diagnosis comes from a repository tagged ai-agents, ai-workflow, claude-code, developer-tools and electron.

Documentation

README

Excerpt

產品診斷（G0 前置檢查）

在開發啟動前，用六問框架診斷產品方向，確保 G0 提案品質。

使用方式

/product-diagnosis <project-name>

參數

$ARGUMENTS: 專案名稱或描述（可選，若不提供則詢問）

適用時機

Sprint 提案書撰寫前
新功能規劃前
PM 提出需求但方向不明確時
老闆要求進行可行性評估時

六問診斷框架

依序回答以下六個問題，每個問題必須有明確結論：

Q1: 問題存在嗎？（Problem Validation）

我們要解決的問題，用戶真的有感嗎？

檢查項	說明
痛點來源	這個問題從哪裡來的？（用戶回饋 / 數據異常 / 老闆直覺 / 競品觀察）
頻率	這個問題多常發生？（每天 / 每週 / 偶爾）
嚴重度	不解決會怎樣？（流失用戶 / 降低效率 / 無影響）
現有替代方案	用戶現在怎麼解決？成本高嗎？

結論: [ ] 問題真實存在且值得解決 / [ ] 問題存在但優先級低 / [ ] 問題不成立

Q2: 目標用戶是誰？（User Definition）

這個功能是給誰用的？他們的使用場景是什麼？

檢查項	說明
用戶角色	老闆 / Agent / 兩者皆是
使用頻率	每天 / 每週 / 每個 Sprint / 一次性
技術水平	需要理解底層原理嗎？
關鍵場景	描述 1-2 個最核心的使用場景

結論: [ ] 用戶輪廓清晰 / [ ] 需要進一步釐清

This is the opening of the README. Read the full README on GitHub.

Commands Product Diagnosis provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/product-diagnosis

Frequently asked about Product Diagnosis

What else does Stanshy publish alongside Product Diagnosis?
Product Diagnosis is one of 25 skills that DirSkills catalogs from Stanshy/AgentHub, the repository it ships in. Its siblings there include Development Plan Generator, Gate Record and Harness Audit. Each one is a separate skill with its own page in this directory, installs the same way Product Diagnosis does, and is maintained by Stanshy in that same repository. The rest of the collection is listed on the Stanshy/AgentHub page.
How does Product Diagnosis compare to other AI Engineering skills?
Product Diagnosis ranks #2847 by stars among the 3101 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Product Diagnosis against them. Open each page to compare what they document and how they install.