product-analysis

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Product Analysis

产品分析

Multi-path parallel product analysis that combines Claude Code agent teams and Codex CLI for cross-model test-time compute scaling.

Core principle: Same analysis task, multiple AI perspectives, deep synthesis.

结合Claude Code代理团队与Codex CLI的跨模型测试时计算扩展多路径并行产品分析。

核心原则：同一分析任务，多AI视角，深度整合。

How It Works

工作原理

/product-analysis full
         │
         ├─ Step 0: Auto-detect available tools (codex? competitors?)
         │
    ┌────┼──────────────┐
    │    │              │
 Claude Code         Codex CLI (auto-detected)
 Task Agents         (background Bash)
 (Explore ×3-5)      (×2-3 parallel)
    │                   │
    └────────┬──────────┘
             │
      Synthesis (main context)
             │
      Structured Report

/product-analysis full
         │
         ├─ 步骤0：自动检测可用工具（codex？竞品分析？）
         │
    ┌────┼──────────────┐
    │    │              │
 Claude Code         Codex CLI（自动检测）
 任务代理           （后台Bash运行）
 （3-5个并行探索）    （2-3个并行）
    │                   │
    └────────┬──────────┘
             │
      结果整合（主会话上下文）
             │
      结构化报告

Step 0: Auto-Detect Available Tools

步骤0：自动检测可用工具

Before launching any agents, detect what tools are available:

bash

undefined

在启动任何代理之前，先检测可用工具：

bash

undefined

Check if Codex CLI is installed

检查Codex CLI是否已安装

which codex 2>/dev/null && codex --version


**Decision logic**:
- If `codex` is found: Inform the user — "Codex CLI detected (version X). Will run cross-model analysis for richer perspectives."
- If `codex` is not found: Silently proceed with Claude Code agents only. Do NOT ask the user to install anything.

Also detect the project type to tailor agent prompts:
```bash

which codex 2>/dev/null && codex --version


**决策逻辑**：
- 若检测到`codex`：告知用户 — "已检测到Codex CLI（版本X）。将运行跨模型分析以获取更丰富的视角。"
- 若未检测到`codex`：仅使用Claude Code代理静默执行，**请勿**要求用户安装任何工具。

同时检测项目类型以适配代理提示词：
```bash

Detect project type

检测项目类型

ls package.json 2>/dev/null # Node.js/React ls pyproject.toml 2>/dev/null # Python ls Cargo.toml 2>/dev/null # Rust ls go.mod 2>/dev/null # Go

undefined

ls package.json 2>/dev/null # Node.js/React ls pyproject.toml 2>/dev/null # Python ls Cargo.toml 2>/dev/null # Rust ls go.mod 2>/dev/null # Go

undefined

Scope Modes

范围模式

Parse

$ARGUMENTS

to determine analysis scope:

Scope	What it covers	Typical agents
`full`	UX + API + Architecture + Docs (default)	5 Claude + Codex (if available)
`ux`	Frontend navigation, information density, user journey, empty state, onboarding	3 Claude + Codex (if available)
`api`	Backend API coverage, endpoint health, error handling, consistency	2 Claude + Codex (if available)
`arch`	Module structure, dependency graph, code duplication, separation of concerns	2 Claude + Codex (if available)
`compare X Y`	Self-audit + competitive benchmarking (invokes `/competitors-analysis` )	3 Claude + competitors-analysis

解析

$ARGUMENTS

以确定分析范围：

范围	覆盖内容	典型代理配置
`full`	UX + API + 架构 + 文档（默认）	5个Claude代理 + Codex（若可用）
`ux`	前端导航、信息密度、用户旅程、空状态、新手引导	3个Claude代理 + Codex（若可用）
`api`	后端API覆盖范围、端点健康度、错误处理、一致性	2个Claude代理 + Codex（若可用）
`arch`	模块结构、依赖图谱、代码重复、关注点分离	2个Claude代理 + Codex（若可用）
`compare X Y`	自我审计 + 竞品对标（调用 `/competitors-analysis` ）	3个Claude代理 + 竞品分析

Phase 1: Parallel Exploration

阶段1：并行探索

Launch all exploration agents simultaneously using Task tool (background mode).

使用Task工具（后台模式）同时启动所有探索代理。

Claude Code Agents (always)

Claude Code代理（始终启用）

For each dimension, spawn a Task agent with

subagent_type: Explore

and

run_in_background: true

Agent A — Frontend Navigation & Information Density

Explore the frontend navigation structure and entry points:
1. App.tsx: How many top-level components are mounted simultaneously?
2. Left sidebar: How many buttons/entries? What does each link to?
3. Right sidebar: How many tabs? How many sections per tab?
4. Floating panels: How many drawers/modals? Which overlap in functionality?
5. Count total first-screen interactive elements for a new user.
6. Identify duplicate entry points (same feature accessible from 2+ places).
Give specific file paths, line numbers, and element counts.

Agent B — User Journey & Empty State

Explore the new user experience:
1. Empty state page: What does a user with no sessions see? Count clickable elements.
2. Onboarding flow: How many steps? What information is presented?
3. Prompt input area: How many buttons/controls surround the input box? Which are high-frequency vs low-frequency?
4. Mobile adaptation: How many nav items? How does it differ from desktop?
5. Estimate: Can a new user complete their first conversation in 3 minutes?
Give specific file paths, line numbers, and UX assessment.

Agent C — Backend API & Health

Explore the backend API surface:
1. List ALL API endpoints (method + path + purpose).
2. Identify endpoints that are unused or have no frontend consumer.
3. Check error handling consistency (do all endpoints return structured errors?).
4. Check authentication/authorization patterns (which endpoints require auth?).
5. Identify any endpoints that duplicate functionality.
Give specific file paths and line numbers.

Agent D — Architecture & Module Structure (full/arch scope only)

Explore the module structure and dependencies:
1. Map the module dependency graph (which modules import which).
2. Identify circular dependencies or tight coupling.
3. Find code duplication across modules (same pattern in 3+ places).
4. Check separation of concerns (does each module have a single responsibility?).
5. Identify dead code or unused exports.
Give specific file paths and line numbers.

Agent E — Documentation & Config Consistency (full scope only)

Explore documentation and configuration:
1. Compare README claims vs actual implemented features.
2. Check config file consistency (base.yaml vs .env.example vs code defaults).
3. Find outdated documentation (references to removed features/files).
4. Check test coverage gaps (which modules have no tests?).
Give specific file paths and line numbers.

针对每个维度，启动一个

subagent_type: Explore

且

run_in_background: true

的Task代理：

代理A — 前端导航与信息密度

探索前端导航结构与入口点：
1. App.tsx：同时挂载了多少个顶级组件？
2. 左侧侧边栏：有多少个按钮/入口？每个链接指向哪里？
3. 右侧侧边栏：有多少个标签页？每个标签页包含多少个板块？
4. 浮动面板：有多少个抽屉/模态框？哪些功能存在重叠？
5. 统计新用户首屏的交互式元素总数。
6. 识别重复入口点（同一功能可从2个及以上位置访问）。
提供具体文件路径、行号和元素数量。

代理B — 用户旅程与空状态

探索新用户体验：
1. 空状态页面：无会话的用户会看到什么？统计可点击元素数量。
2. 新手引导流程：有多少个步骤？展示了哪些信息？
3. 提示输入区域：输入框周围有多少个按钮/控件？哪些是高频操作，哪些是低频操作？
4. 移动端适配：有多少个导航项？与桌面端有何不同？
5. 评估：新用户能否在3分钟内完成首次对话？
提供具体文件路径、行号和UX评估。

代理C — 后端API与健康度

探索后端API表面：
1. 列出所有API端点（方法 + 路径 + 用途）。
2. 识别未被使用或无前端消费者的端点。
3. 检查错误处理一致性（所有端点是否都返回结构化错误？）。
4. 检查认证/授权模式（哪些端点需要认证？）。
5. 识别功能重复的端点。
提供具体文件路径和行号。

代理D — 架构与模块结构（仅full/arch范围）

探索模块结构与依赖关系：
1. 绘制模块依赖图谱（哪些模块导入了哪些模块）。
2. 识别循环依赖或紧耦合。
3. 查找跨模块的代码重复（同一模式出现3次及以上）。
4. 检查关注点分离（每个模块是否只承担单一职责？）。
5. 识别死代码或未使用的导出。
提供具体文件路径和行号。

代理E — 文档与配置一致性（仅full范围）

探索文档与配置：
1. 对比README声明与实际实现的功能。
2. 检查配置文件一致性（base.yaml vs .env.example vs 代码默认值）。
3. 查找过时文档（提及已移除的功能/文件）。
4. 检查测试覆盖缺口（哪些模块没有测试？）。
提供具体文件路径和行号。

Codex CLI Agents (auto-detected)

Codex CLI代理（自动检测）

If Codex CLI was detected in Step 0, launch parallel Codex analyses via background Bash.

Each Codex invocation gets the same dimensional prompt but from a different model's perspective:

bash

codex -m o4-mini \
  -c model_reasoning_effort="high" \
  --full-auto \
  "Analyze the frontend navigation structure of this project. Count all interactive elements visible to a new user on first screen. Identify duplicate entry points where the same feature is accessible from 2+ places. Give specific file paths and counts."

Run 2-3 Codex commands in parallel (background Bash), one per major dimension.

Important: Codex runs in the project's working directory. It has full filesystem access. The

--full-auto

flag (or

--dangerously-bypass-approvals-and-sandbox

for older versions) enables autonomous execution.

若步骤0中检测到Codex CLI，则通过后台Bash启动并行Codex分析。

每个Codex调用使用相同维度的提示词，但基于不同模型视角：

bash

codex -m o4-mini \
  -c model_reasoning_effort="high" \
  --full-auto \
  "Analyze the frontend navigation structure of this project. Count all interactive elements visible to a new user on first screen. Identify duplicate entry points where the same feature is accessible from 2+ places. Give specific file paths and counts."

并行运行2-3个Codex命令（后台Bash），每个对应一个主要维度。

重要提示：Codex在项目工作目录中运行，拥有完整文件系统访问权限。

--full-auto

标志（旧版本使用

--dangerously-bypass-approvals-and-sandbox

）启用自主执行。

Phase 2: Competitive Benchmarking (compare scope only)

阶段2：竞品对标（仅compare范围）

When scope is

compare

, invoke the competitors-analysis skill for each competitor:

Use the Skill tool to invoke: /competitors-analysis {competitor-name} {competitor-url}

This delegates to the orthogonal

competitors-analysis

skill which handles:

Repository cloning and validation
Evidence-based code analysis (file:line citations)
Competitor profile generation

当范围为

compare

时，针对每个竞品调用竞品分析技能：

使用Skill工具调用：/competitors-analysis {competitor-name} {competitor-url}

此操作将委托给独立的

competitors-analysis

技能，该技能负责：

仓库克隆与验证
基于证据的代码分析（文件:行引用）
竞品档案生成

Phase 3: Synthesis

阶段3：结果整合

After all agents complete, synthesize findings in the main conversation context.

所有代理完成后，在主会话上下文中整合分析结果。

Cross-Validation

交叉验证

Compare findings across agents (Claude vs Claude, Claude vs Codex):

Agreement = high confidence finding
Disagreement = investigate deeper (one agent may have missed context)
Codex-only finding = different model perspective, validate manually

对比不同代理的结果（Claude vs Claude，Claude vs Codex）：

一致结果 = 高可信度发现
不一致结果 = 深入调查（某代理可能遗漏上下文）
仅Codex发现 = 不同模型视角，需手动验证

Quantification

量化分析

Extract hard numbers from agent reports:

Metric	What to measure
First-screen interactive elements	Total count of buttons/links/inputs visible to new user
Feature entry point duplication	Number of features with 2+ entry points
API endpoints without frontend consumer	Count of unused backend routes
Onboarding steps to first value	Steps from launch to first successful action
Module coupling score	Number of circular or bi-directional dependencies

从代理报告中提取硬数据：

指标	测量内容
首屏交互式元素	新用户可见的按钮/链接/输入框总数
功能入口点重复数	存在2个及以上入口点的功能数量
无前端消费者的API端点	未使用的后端路由数量
首次价值达成的引导步骤数	从启动到首次成功操作的步骤数
模块耦合度得分	循环或双向依赖的数量

Structured Output

结构化输出

Produce a layered optimization report:

markdown

undefined

生成分层优化报告：

markdown

undefined

Product Analysis Report

产品分析报告

Executive Summary

执行摘要

[1-2 sentences: key finding]

[1-2句话：核心发现]

Quantified Findings

量化结果

Metric	Value	Assessment
...	...	...

指标	数值	评估
...	...	...

P0: Critical (block launch)

P0：关键问题（阻碍发布）

[Issues that prevent basic usability]

[影响基础可用性的问题]

P1: High Priority (launch week)

P1：高优先级（发布周解决）

[Issues that significantly degrade experience]

[显著影响体验的问题]

P2: Medium Priority (next sprint)

P2：中优先级（下一个迭代解决）

[Issues worth addressing but not blocking]

[值得处理但不阻碍发布的问题]

Cross-Model Insights

跨模型洞察

[Findings that only one model identified — worth investigating]

[仅单个模型识别出的发现 — 值得深入调查]

Competitive Position (if compare scope)

竞品定位（若为compare范围）

[How we compare on key dimensions]

undefined

[关键维度上的竞品对比情况]

undefined

Workflow Checklist

工作流检查清单

Parse
```
$ARGUMENTS
```
for scope
Auto-detect Codex CLI availability (
```
which codex
```
)
Auto-detect project type (package.json / pyproject.toml / etc.)
Launch Claude Code Explore agents (3-5 parallel, background)
Launch Codex CLI commands (2-3 parallel, background) if detected
Invoke
```
/competitors-analysis
```
if
```
compare
```
scope
Collect all agent results
Cross-validate findings
Quantify metrics
Generate structured report with P0/P1/P2 priorities

解析
```
$ARGUMENTS
```
确定范围
自动检测Codex CLI可用性（
```
which codex
```
）
自动检测项目类型（package.json / pyproject.toml等）
启动Claude Code探索代理（3-5个并行，后台运行）
若检测到则启动Codex CLI命令（2-3个并行，后台运行）
若为compare范围则调用
```
/competitors-analysis
```
收集所有代理结果
交叉验证结果
量化指标
生成带P0/P1/P2优先级的结构化报告

References

参考资料

references/analysis_dimensions.md — Detailed audit dimension definitions and prompts
references/synthesis_methodology.md — How to weight and merge multi-agent findings
references/codex_patterns.md — Codex CLI invocation patterns and flag reference

references/analysis_dimensions.md — 详细审计维度定义与提示词
references/synthesis_methodology.md — 多代理结果加权与整合方法
references/codex_patterns.md — Codex CLI调用模式与参数参考