Back to Details

doc-prd-autopilot

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

doc-prd-autopilot

doc-prd-autopilot

Purpose

用途

Automated Product Requirements Document (PRD) generation pipeline that processes one or more BRD documents and generates their corresponding PRDs with dependency awareness, readiness validation, and parallel execution support.
Layer: 2 (PRD Generation)
Upstream: BRD (Layer 1)
Downstream: EARS (Layer 3), BDD (Layer 4), ADR (Layer 5)
可自动处理一个或多个BRD文档并生成对应PRD的流水线，具备依赖感知、就绪状态验证和并行执行支持。
层级：2（PRD生成）
上游：BRD（层级1）
下游：EARS（层级3）、BDD（层级4）、ADR（层级5）

Skill Dependencies

技能依赖

This autopilot orchestrates the following skills:
SkillPurposePhase
doc-naming
Element ID format, threshold tags, legacy pattern detectionAll Phases
doc-brd-validator
Validate BRD PRD-Ready scorePhase 2: BRD Readiness
doc-prd
PRD creation rules, template, section structurePhase 3: PRD Generation
quality-advisor
Real-time quality feedback during PRD generationPhase 3: PRD Generation
doc-prd-validator
Validate PRD structure, content, EARS-Ready scorePhase 4: PRD Validation
doc-prd-reviewer
Content review, link validation, quality scoringPhase 5: Review
doc-prd-fixer
Apply fixes from review report, create missing filesPhase 5: Fix
Delegation Principle: The autopilot orchestrates workflow but delegates:
  • PRD structure/content rules → 
    doc-prd
    skill
  • Real-time quality feedback → 
    quality-advisor
    skill
  • PRD validation logic → 
    doc-prd-validator
    skill
  • BRD validation logic → 
    doc-brd-validator
    skill
  • Content review and scoring → 
    doc-prd-reviewer
    skill
  • Issue resolution and fixes → 
    doc-prd-fixer
    skill
该自动流水线编排以下技能：
技能用途阶段
doc-naming
元素ID格式、阈值标签、遗留模式检测所有阶段
doc-brd-validator
验证BRD的PRD就绪分数阶段2：BRD就绪性
doc-prd
PRD创建规则、模板、章节结构阶段3：PRD生成
quality-advisor
PRD生成期间的实时质量反馈阶段3：PRD生成
doc-prd-validator
验证PRD结构、内容、EARS就绪分数阶段4：PRD验证
doc-prd-reviewer
内容审查、链接验证、质量评分阶段5：审查
doc-prd-fixer
应用审查报告中的修复、创建缺失文件阶段5：修复
委托原则：自动流水线编排工作流，但将以下任务委托给对应技能：
  • PRD结构/内容规则 → 
    doc-prd
    技能
  • 实时质量反馈 → 
    quality-advisor
    技能
  • PRD验证逻辑 → 
    doc-prd-validator
    技能
  • BRD验证逻辑 → 
    doc-brd-validator
    技能
  • 内容审查与评分 → 
    doc-prd-reviewer
    技能
  • 问题解决与修复 → 
    doc-prd-fixer
    技能

Smart Document Detection

智能文档检测

The autopilot automatically determines the action based on the input document type.
自动流水线会根据输入文档类型自动确定操作。

Input Type Recognition

输入类型识别

InputDetected AsAction
PRD-NN
Self typeReview existing PRD document
BRD-NN
Upstream typeGenerate if missing, review if exists
输入识别类型操作
PRD-NN
自身类型审查现有PRD文档
BRD-NN
上游类型缺失则生成，存在则审查

Detection Algorithm

检测算法

1. Parse input: Extract TYPE and NN from "{TYPE}-{NN}"
2. Determine action:
   - IF TYPE == "PRD": Review Mode
   - ELSE IF TYPE == "BRD": Generate/Find Mode
   - ELSE: Error (invalid type for this autopilot)
3. For Generate/Find Mode:
   - Check: Does PRD-{NN} exist in docs/02_PRD/?
   - IF exists: Switch to Review Mode for PRD-{NN}
   - ELSE: Proceed with Generation from BRD-{NN}
1. 解析输入：从"{TYPE}-{NN}"中提取TYPE和NN
2. 确定操作：
   - 若TYPE == "PRD"：审查模式
   - 若TYPE == "BRD"：生成/查找模式
   - 否则：错误（该自动流水线不支持的类型）
3. 对于生成/查找模式：
   - 检查：PRD-{NN}是否存在于docs/02_PRD/中？
   - 若存在：切换为PRD-{NN}的审查模式
   - 否则：从BRD-{NN}开始生成流程

File Existence Check

文件存在性检查

bash
undefined
bash
undefined

Check for nested folder structure (mandatory)

检查嵌套文件夹结构（必填）

ls docs/02_PRD/PRD-{NN}_*/
undefined
ls docs/02_PRD/PRD-{NN}_*/
undefined

Examples

示例

bash
undefined
bash
undefined

Review mode (same type - PRD input)

审查模式（同类型 - PRD输入）

/doc-prd-autopilot PRD-01 # Reviews existing PRD-01
/doc-prd-autopilot PRD-01 # 审查现有PRD-01

Generate/Find mode (upstream type - BRD input)

生成/查找模式（上游类型 - BRD输入）

/doc-prd-autopilot BRD-01 # Generates PRD-01 if missing, or reviews existing PRD-01
/doc-prd-autopilot BRD-01 # 若PRD-01缺失则生成，若存在则审查

Multiple inputs

多输入

/doc-prd-autopilot BRD-01,BRD-02 # Generates/reviews PRD-01 and PRD-02 /doc-prd-autopilot PRD-01,PRD-02 # Reviews PRD-01 and PRD-02
undefined
/doc-prd-autopilot BRD-01,BRD-02 # 生成/审查PRD-01和PRD-02 /doc-prd-autopilot PRD-01,PRD-02 # 审查PRD-01和PRD-02
undefined

Action Determination Output

操作确定输出

Input: BRD-01
├── Detected Type: BRD (upstream)
├── Expected PRD: PRD-01
├── PRD Exists: Yes → docs/02_PRD/PRD-01_f1_iam/
└── Action: REVIEW MODE - Running doc-prd-reviewer on PRD-01

Input: BRD-05
├── Detected Type: BRD (upstream)
├── Expected PRD: PRD-05
├── PRD Exists: No
└── Action: GENERATE MODE - Creating PRD-05 from BRD-05

Input: PRD-03
├── Detected Type: PRD (self)
└── Action: REVIEW MODE - Running doc-prd-reviewer on PRD-03
输入：BRD-01
├── 检测类型：BRD（上游）
├── 预期PRD：PRD-01
├── PRD是否存在：是 → docs/02_PRD/PRD-01_f1_iam/
└── 操作：审查模式 - 对PRD-01运行doc-prd-reviewer

输入：BRD-05
├── 检测类型：BRD（上游）
├── 预期PRD：PRD-05
├── PRD是否存在：否
└── 操作：生成模式 - 从BRD-05创建PRD-05

输入：PRD-03
├── 检测类型：PRD（自身）
└── 操作：审查模式 - 对PRD-03运行doc-prd-reviewer

When to Use This Skill

何时使用该技能

Use 
doc-prd-autopilot
when:
  • You have one or more completed BRD documents ready for PRD generation
  • You want automated dependency analysis to determine optimal PRD creation order
  • You need PRD-Ready score validation before generation
  • You want automatic EARS-Ready score validation after PRD creation
  • You need parallel PRD generation for independent BRDs
Do NOT use when:
  • Creating a single PRD with extensive manual customization (use 
    doc-prd
    instead)
  • BRDs are incomplete or in Draft status
  • You need fine-grained control over each PRD section
在以下场景使用
doc-prd-autopilot
：
  • 您有一个或多个已完成的BRD文档，准备生成PRD
  • 您需要自动分析依赖关系以确定最优PRD创建顺序
  • 您需要在生成前验证PRD就绪分数
  • 您需要在PRD创建后自动验证EARS就绪分数
  • 您需要为独立的BRD并行生成PRD
请勿在以下场景使用：
  • 需要大量手动定制的单个PRD生成（改用
    doc-prd
    ）
  • BRD文档不完整或处于草稿状态
  • 您需要对每个PRD章节进行细粒度控制

8-Step Autopilot Workflow

8步自动流水线工作流

Overview Diagram

概览图

mermaid
flowchart TD
    subgraph Phase1["Phase 1: Dependency Analysis"]
        A[Input: BRD List] --> B[Analyze Dependencies]
        B --> C[Build Dependency Graph]
        C --> D[Topological Sort]
        D --> E[Define Creation Order]
    end

    subgraph Phase2["Phase 2: BRD Readiness"]
        E --> F{Next BRD}
        F --> G[Check PRD-Ready Score]
        G --> H{Score >= 90?}
        H -->|No| I[Auto-Fix Issues]
        I --> J[Re-validate]
        J --> H
        H -->|Yes| K[Mark BRD Ready]
    end

    subgraph Phase3["Phase 3: PRD Generation"]
        K --> L[Load BRD Content]
        L --> M[Apply PRD Template]
        M --> N[Generate PRD Sections]
        N --> N2[quality-advisor: Real-time Feedback]
        N2 --> O[Add Traceability Tags]
        O --> P[Write PRD Files]
    end

    subgraph Phase4["Phase 4: PRD Validation"]
        P --> Q[Check EARS-Ready Score]
        Q --> R{Score >= 90?}
        R -->|No| S[Auto-Fix PRD Issues]
        S --> T[Re-validate PRD]
        T --> R
        R -->|Yes| U[Validation Passed]
    end

    subgraph Phase5["Phase 5: Final Review"]
        U --> U1[Check Link Integrity]
        U1 --> U2[Verify Threshold Consistency]
        U2 --> U3[Validate BRD Alignment]
        U3 --> U4[Check Placeholder Text]
        U4 --> U5{Review Passed?}
        U5 -->|No| U6[Flag Issues]
        U6 --> U7[Auto-Fix or Manual]
        U7 --> U5
        U5 -->|Yes| U8[Mark PRD Complete]
    end

    subgraph Phase6["Phase 6: Parallel/Continue"]
        U8 --> V{More BRDs?}
        V -->|Yes| W{Independent?}
        W -->|Yes| X[Parallel Generation]
        W -->|No| F
        X --> F
        V -->|No| Y[Generate Summary Report]
    end

    Y --> Z[Complete]
mermaid
flowchart TD
    subgraph Phase1["Phase 1: Dependency Analysis"]
        A[Input: BRD List] --> B[Analyze Dependencies]
        B --> C[Build Dependency Graph]
        C --> D[Topological Sort]
        D --> E[Define Creation Order]
    end

    subgraph Phase2["Phase 2: BRD Readiness"]
        E --> F{Next BRD}
        F --> G[Check PRD-Ready Score]
        G --> H{Score >= 90?}
        H -->|No| I[Auto-Fix Issues]
        I --> J[Re-validate]
        J --> H
        H -->|Yes| K[Mark BRD Ready]
    end

    subgraph Phase3["Phase 3: PRD Generation"]
        K --> L[Load BRD Content]
        L --> M[Apply PRD Template]
        M --> N[Generate PRD Sections]
        N --> N2[quality-advisor: Real-time Feedback]
        N2 --> O[Add Traceability Tags]
        O --> P[Write PRD Files]
    end

    subgraph Phase4["Phase 4: PRD Validation"]
        P --> Q[Check EARS-Ready Score]
        Q --> R{Score >= 90?}
        R -->|No| S[Auto-Fix PRD Issues]
        S --> T[Re-validate PRD]
        T --> R
        R -->|Yes| U[Validation Passed]
    end

    subgraph Phase5["Phase 5: Final Review"]
        U --> U1[Check Link Integrity]
        U1 --> U2[Verify Threshold Consistency]
        U2 --> U3[Validate BRD Alignment]
        U3 --> U4[Check Placeholder Text]
        U4 --> U5{Review Passed?}
        U5 -->|No| U6[Flag Issues]
        U6 --> U7[Auto-Fix or Manual]
        U7 --> U5
        U5 -->|Yes| U8[Mark PRD Complete]
    end

    subgraph Phase6["Phase 6: Parallel/Continue"]
        U8 --> V{More BRDs?}
        V -->|Yes| W{Independent?}
        W -->|Yes| X[Parallel Generation]
        W -->|No| F
        X --> F
        V -->|No| Y[Generate Summary Report]
    end

    Y --> Z[Complete]

Step 1: Input Document List

步骤1：输入文档列表

Command Format:
/doc-prd-autopilot <DOCUMENT_LIST>
Input Patterns (Smart Detection):
PatternTypeAction
BRD-NN
UpstreamGenerate PRD if missing, review if exists
PRD-NN
SelfReview existing PRD document
BRD-NN,BRD-MM
Multiple upstreamBatch generate/review
PRD-NN,PRD-MM
Multiple selfBatch review
all
All upstreamProcess all BRDs
Input Options:
  • Single BRD (generate/find): 
    BRD-01
    or 
    docs/01_BRD/BRD-01_f1_iam/
  • Single PRD (review): 
    PRD-01
    or 
    docs/02_PRD/PRD-01_f1_iam/
  • Multiple BRDs: 
    BRD-01,BRD-02,BRD-03
    (comma-separated)
  • Multiple PRDs: 
    PRD-01,PRD-02,PRD-03
    (comma-separated)
  • All BRDs: 
    all
    or 
    *
    (scan entire docs/01_BRD/ directory)
  • Pattern Match: 
    BRD-0*
    or 
    PRD-0*
    (glob patterns)
Example Invocations:
bash
undefined
命令格式:
/doc-prd-autopilot <DOCUMENT_LIST>
输入模式（智能检测）:
模式类型操作
BRD-NN
上游缺失则生成PRD，存在则审查
PRD-NN
自身审查现有PRD文档
BRD-NN,BRD-MM
多个上游批量生成/审查
PRD-NN,PRD-MM
多个自身批量审查
all
所有上游处理所有BRD
输入选项:
  • 单个BRD（生成/查找）: 
    BRD-01
    或 
    docs/01_BRD/BRD-01_f1_iam/
  • 单个PRD（审查）: 
    PRD-01
    或 
    docs/02_PRD/PRD-01_f1_iam/
  • 多个BRD: 
    BRD-01,BRD-02,BRD-03
    （逗号分隔）
  • 多个PRD: 
    PRD-01,PRD-02,PRD-03
    （逗号分隔）
  • 所有BRD: 
    all
    或 
    *
    （扫描整个docs/01_BRD/目录）
  • 模式匹配: 
    BRD-0*
    或 
    PRD-0*
    （通配符模式）
调用示例:
bash
undefined

Generate/Find mode (BRD input)

生成/查找模式（BRD输入）

/doc-prd-autopilot BRD-01 # Generates PRD-01 if missing, reviews if exists
/doc-prd-autopilot BRD-01 # 若PRD-01缺失则生成，若存在则审查

Review mode (PRD input)

审查模式（PRD输入）

/doc-prd-autopilot PRD-01 # Reviews existing PRD-01
/doc-prd-autopilot PRD-01 # 审查现有PRD-01

Multiple specific BRDs (generate/find)

多个指定BRD（生成/查找）

/doc-prd-autopilot BRD-01,BRD-02,BRD-05
/doc-prd-autopilot BRD-01,BRD-02,BRD-05

Multiple specific PRDs (review)

多个指定PRD（审查）

/doc-prd-autopilot PRD-01,PRD-02,PRD-05
/doc-prd-autopilot PRD-01,PRD-02,PRD-05

All available BRDs

所有可用BRD

/doc-prd-autopilot all
/doc-prd-autopilot all

Pattern match (foundation modules)

模式匹配（基础模块）

/doc-prd-autopilot BRD-0[1-7]
undefined
/doc-prd-autopilot BRD-0[1-7]
undefined

Step 2: Dependency Analysis & Creation Order

步骤2：依赖分析与创建顺序

The autopilot analyzes cross-BRD dependencies to determine optimal PRD creation order.
Dependency Sources:
  1. Explicit References: 
    @depends-brd: BRD-NN
    tags in BRD documents
  2. Cross-BRD References: References to other BRDs in Traceability sections
  3. Module Dependencies: Foundation module (F1-F7) vs Domain module (D1-D7) hierarchy
  4. Platform vs Feature: Platform BRDs before Feature BRDs
Algorithm:
python
def analyze_dependencies(brd_list):
    """
    1. Build directed graph of BRD dependencies
    2. Detect circular dependencies (error if found)
    3. Perform topological sort
    4. Group independent BRDs for parallel processing
    5. Return ordered execution plan
    """
    graph = build_dependency_graph(brd_list)

    if has_cycle(graph):
        raise CircularDependencyError()

    sorted_order = topological_sort(graph)
    parallel_groups = identify_independent_groups(sorted_order)

    return ExecutionPlan(sorted_order, parallel_groups)
Output Example:
Dependency Analysis Complete:
├── Execution Order: BRD-06 → BRD-07 → [BRD-01, BRD-02] → BRD-03 → BRD-04 → BRD-05
├── Parallel Groups:
│   ├── Group 1: [BRD-06] (Infrastructure)
│   ├── Group 2: [BRD-07] (Config)
│   ├── Group 3: [BRD-01, BRD-02] (Parallel - no dependencies)
│   ├── Group 4: [BRD-03] (depends on BRD-01)
│   └── Group 5: [BRD-04, BRD-05] (Parallel - depend on BRD-03)
└── Estimated Time: Sequential 7 units, Parallel 4 units
自动流水线会分析跨BRD的依赖关系，以确定最优PRD创建顺序。
依赖来源:
  1. 显式引用: BRD文档中的
    @depends-brd: BRD-NN
    标签
  2. 跨BRD引用: 可追溯性章节中对其他BRD的引用
  3. 模块依赖: 基础模块（F1-F7）与领域模块（D1-D7）的层级关系
  4. 平台与功能: 平台BRD优先于功能BRD
算法:
python
def analyze_dependencies(brd_list):
    """
    1. 构建BRD依赖的有向图
    2. 检测循环依赖（若发现则报错）
    3. 执行拓扑排序
    4. 对独立BRD分组以进行并行处理
    5. 返回有序执行计划
    """
    graph = build_dependency_graph(brd_list)

    if has_cycle(graph):
        raise CircularDependencyError()

    sorted_order = topological_sort(graph)
    parallel_groups = identify_independent_groups(sorted_order)

    return ExecutionPlan(sorted_order, parallel_groups)
输出示例:
依赖分析完成:
├── 执行顺序: BRD-06 → BRD-07 → [BRD-01, BRD-02] → BRD-03 → BRD-04 → BRD-05
├── 并行分组:
│   ├── 分组1: [BRD-06]（基础设施）
│   ├── 分组2: [BRD-07]（配置）
│   ├── 分组3: [BRD-01, BRD-02]（并行 - 无依赖）
│   ├── 分组4: [BRD-03]（依赖BRD-01）
│   └── 分组5: [BRD-04, BRD-05]（并行 - 依赖BRD-03）
└── 预计时间: 串行7单位，并行4单位

Step 3: PRD-Ready Score Validation

步骤3：PRD就绪分数验证

Before generating a PRD, validate that the source BRD meets PRD-Ready requirements.
Skill Delegation: This phase uses validation rules from 
doc-brd-validator
skill. See: 
.claude/skills/doc-brd-validator/SKILL.md
for complete BRD validation rules.
PRD-Ready Scoring Criteria (100%):
CategoryWeightCriteria
Business Requirements Completeness40%All 18 BRD sections present, objectives defined, stakeholders identified
Technical Readiness30%Architecture Decision Requirements section complete, technology prerequisites documented
Business Alignment20%Success criteria quantified, risks assessed, constraints documented
Traceability10%Strategy references included, downstream placeholders defined
Minimum Score: 90% (configurable)
Auto-Fix Actions:
IssueAuto-Fix Action
Missing timing profiles (p50/p95/p99)Add template timing table
Pending ADR topics without elaborationAdd business driver and constraints placeholders
Missing threshold registryAdd Appendix with threshold template
Incomplete Document ControlAdd missing required fields
Missing section numbersRenumber sections sequentially
Validation Command (internal):
bash
python ai_dev_flow/scripts/validate_prd_ready.py \
  --brd docs/01_BRD/BRD-01_f1_iam/ \
  --min-score 90 \
  --auto-fix
在生成PRD前，需验证源BRD是否满足PRD就绪要求。
技能委托: 该阶段使用
doc-brd-validator
技能的验证规则。 详见: 
.claude/skills/doc-brd-validator/SKILL.md
中的完整BRD验证规则。
PRD就绪评分标准（100%）:
类别权重标准
业务需求完整性40%所有18个BRD章节齐全、目标明确、干系人已识别
技术就绪性30%架构决策需求章节完整、技术前提已文档化
业务对齐20%成功标准可量化、风险已评估、约束已文档化
可追溯性10%包含战略引用、已定义下游占位符
最低分数: 90%（可配置）
自动修复操作:
问题自动修复操作
缺失时间配置文件（p50/p95/p99）添加模板时间表格
未详细说明的待处理ADR主题添加业务驱动因素和约束占位符
缺失阈值注册表添加带阈值模板的附录
不完整的文档控制添加缺失的必填字段
缺失章节编号按顺序重新编号章节
验证命令（内部）:
bash
python ai_dev_flow/scripts/validate_prd_ready.py \
  --brd docs/01_BRD/BRD-01_f1_iam/ \
  --min-score 90 \
  --auto-fix

Step 4: PRD Generation

步骤4：PRD生成

Generate the PRD document from the validated BRD with real-time quality feedback.
Skill Delegation: This phase follows rules defined in 
doc-prd
skill. See: 
.claude/skills/doc-prd/SKILL.md
for complete PRD creation guidance.
Quality Guidance: Uses 
quality-advisor
skill for real-time feedback during generation. See: 
.claude/skills/quality-advisor/SKILL.md
for quality monitoring.
Generation Process:
  1. Load BRD Content:
    • Read all BRD section files (for sectioned BRDs)
    • Extract business requirements, objectives, stakeholders
    • Parse Architecture Decision Requirements topics
  2. Template Selection (per 
    doc-prd
    skill):
    • MVP Template (default): 
      ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md
      (17 sections, ≥85% thresholds)
    • Full Template: For enterprise/regulatory projects (21 sections, ≥90% thresholds)
    • Section Templates: For sectioned PRDs (>25KB)
  3. Section Mapping (BRD → PRD):
BRD SectionPRD Section(s)
0. Document Control1. Document Control
1. Executive Summary2. Executive Summary
2. Business Context3. Problem Statement
3. Stakeholder Analysis4. Target Audience & User Personas
4. Business Requirements6. Goals & Objectives, 9. Functional Requirements
5. Success Criteria5. Success Metrics (KPIs)
6. Constraints12. Constraints & Assumptions
7. Architecture Decision Requirements18. Traceability (Architecture Decision Requirements)
8. Risk Assessment13. Risk Assessment
9. Traceability18. Traceability
  1. PRD-Specific Content Generation:
    • Section 7: Scope & Requirements (derive from BRD scope)
    • Section 8: User Stories & User Roles (extract from stakeholders)
    • Section 10: Customer-Facing Content & Messaging (MANDATORY)
    • Section 11: Acceptance Criteria (from BRD success criteria)
    • Section 14: Success Definition (go-live criteria)
    • Section 15: Stakeholders & Communication
    • Section 16: Implementation Approach
    • Section 17: Budget & Resources
    • Section 19: References
    • Section 20: EARS Enhancement Appendix (timing, boundary, state, fallback)
    • Section 21: Quality Assurance & Testing Strategy
  2. Real-Time Quality Feedback (via 
    quality-advisor
    skill):
    • Monitor section completion as content is generated
    • Detect anti-patterns (AP-001 to AP-017) during creation
    • Validate cumulative tagging (@brd requirement for Layer 2)
    • Check element ID format compliance (PRD.NN.TT.SS)
    • Flag issues early to reduce post-generation rework
  3. Traceability Tags:
    markdown
    @brd: BRD.01.01.01, BRD.01.01.02, BRD.01.23.01
  4. File Output (ALWAYS use nested folder):
    • Monolithic (<20k tokens): 
      docs/02_PRD/PRD-NN_{slug}/PRD-NN_{slug}.md
    • Sectioned (≥20k tokens): 
      docs/02_PRD/PRD-NN_{slug}/PRD-NN.0_index.md
      , 
      PRD-NN.1_core.md
      , etc.
    • Master Index (always): 
      docs/02_PRD/PRD-00_index.md
      (create or update)
    Nested Folder Rule: ALL PRDs use nested folders (
    PRD-NN_{slug}/
    ) regardless of size. This keeps companion files (review reports, fix reports, drift cache) organized with their parent document.
从已验证的BRD生成PRD文档，并提供实时质量反馈。
技能委托: 该阶段遵循
doc-prd
技能定义的规则。 详见: 
.claude/skills/doc-prd/SKILL.md
中的完整PRD创建指南。
质量指导: 使用
quality-advisor
技能在生成期间提供实时反馈。 详见: 
.claude/skills/quality-advisor/SKILL.md
中的质量监控说明。
生成流程:
  1. 加载BRD内容:
    • 读取所有BRD章节文件（针对分章节的BRD）
    • 提取业务需求、目标、干系人
    • 解析架构决策需求主题
  2. 模板选择（基于
    doc-prd
    技能）:
    • MVP模板（默认）: 
      ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md
      （17个章节，≥85%阈值）
    • 完整模板: 适用于企业/监管项目（21个章节，≥90%阈值）
    • 章节模板: 适用于分章节的PRD（>25KB）
  3. 章节映射（BRD → PRD）:
BRD章节PRD章节
0. 文档控制1. 文档控制
1. 执行摘要2. 执行摘要
2. 业务背景3. 问题陈述
3. 干系人分析4. 目标受众与用户画像
4. 业务需求6. 目标与目的、9. 功能需求
5. 成功标准5. 成功指标（KPI）
6. 约束12. 约束与假设
7. 架构决策需求18. 可追溯性（架构决策需求）
8. 风险评估13. 风险评估
9. 可追溯性18. 可追溯性
  1. PRD专属内容生成:
    • 章节7: 范围与需求（从BRD范围推导）
    • 章节8: 用户故事与用户角色（从干系人提取）
    • 章节10: 面向客户的内容与消息（必填）
    • 章节11: 验收标准（从BRD成功标准提取）
    • 章节14: 成功定义（上线标准）
    • 章节15: 干系人与沟通
    • 章节16: 实施方法
    • 章节17: 预算与资源
    • 章节19: 参考资料
    • 章节20: EARS增强附录（时间、边界、状态、回退）
    • 章节21: 质量保证与测试策略
  2. 实时质量反馈（通过
    quality-advisor
    技能）:
    • 在内容生成时监控章节完成情况
    • 在创建过程中检测反模式（AP-001至AP-017）
    • 验证累积标签（层级2所需的@brd要求）
    • 检查元素ID格式合规性（PRD.NN.TT.SS）
    • 提前标记问题以减少生成后的返工
  3. 可追溯性标签:
    markdown
    @brd: BRD.01.01.01, BRD.01.01.02, BRD.01.23.01
  4. 文件输出（始终使用嵌套文件夹）:
    • 单文件（<20k tokens）: 
      docs/02_PRD/PRD-NN_{slug}/PRD-NN_{slug}.md
    • 分章节（≥20k tokens）: 
      docs/02_PRD/PRD-NN_{slug}/PRD-NN.0_index.md
      , 
      PRD-NN.1_core.md
      等
    • 主索引（始终生成）: 
      docs/02_PRD/PRD-00_index.md
      （创建或更新）
    嵌套文件夹规则: 所有PRD无论大小都使用嵌套文件夹（
    PRD-NN_{slug}/
    ）。这将使配套文件（审查报告、修复报告、漂移缓存）与父文档保持有序。

Step 5: EARS-Ready Score Validation

步骤5：EARS就绪分数验证

After PRD generation, validate EARS-Ready score.
Skill Delegation: This phase uses validation rules from 
doc-prd-validator
skill. See: 
.claude/skills/doc-prd-validator/SKILL.md
for complete validation rules and error codes.
EARS-Ready Scoring Criteria (100%):
CategoryWeightCriteria
Business Requirements Clarity40%SMART objectives, functional requirements, acceptance criteria
Requirements Maturity35%System boundaries, stakeholder requirements, problem statement
EARS Translation Readiness20%User journeys, quality attributes quantified, timing profiles
Strategic Alignment5%Domain-specific business logic references
Minimum Score: 85% for MVP (90% for full template) - configurable
Auto-Fix Actions (per 
doc-prd-validator
error codes):
IssueError CodeAuto-Fix Action
Missing timing profile matrixPRD-W002Add Section 20.1 template
Missing boundary value matrixPRD-W002Add Section 20.2 template
Missing state transition diagramPRD-W002Add Section 20.3 Mermaid template
Missing fallback documentationPRD-W002Add Section 20.4 template
Incomplete customer-facing contentPRD-E006Flag for manual review (Section 10)
PRD生成完成后，验证EARS就绪分数。
技能委托: 该阶段使用
doc-prd-validator
技能的验证规则。 详见: 
.claude/skills/doc-prd-validator/SKILL.md
中的完整验证规则和错误代码。
EARS就绪评分标准（100%）:
类别权重标准
业务需求清晰度40%SMART目标、功能需求、验收标准
需求成熟度35%系统边界、干系人需求、问题陈述
EARS转换就绪性20%用户旅程、质量属性量化、时间配置文件
战略对齐5%领域特定业务逻辑引用
最低分数: MVP模板为85%（完整模板为90%）- 可配置
自动修复操作（基于
doc-prd-validator
错误代码）:
问题错误代码自动修复操作
缺失时间配置文件矩阵PRD-W002添加章节20.1模板
缺失边界值矩阵PRD-W002添加章节20.2模板
缺失状态转换图PRD-W002添加章节20.3 Mermaid模板
缺失回退文档PRD-W002添加章节20.4模板
不完整的面向客户内容PRD-E006标记为需要手动审查（章节10）

Step 6: Review & Fix Cycle (v2.3)

步骤6：审查与修复循环（v2.3）

Iterative review and fix cycle to ensure PRD quality before completion.
mermaid
flowchart TD
    A[Phase 5 Start] --> B[Run doc-prd-reviewer]
    B --> C[Generate Review Report]
    C --> D{Review Score >= 90?}

    D -->|Yes| E[PASS - Proceed to Phase 6]
    D -->|No| F{Iteration < Max?}

    F -->|Yes| G[Run doc-prd-fixer]
    G --> H[Apply Fixes]
    H --> I[Generate Fix Report]
    I --> J[Increment Iteration]
    J --> B

    F -->|No| K[Flag for Manual Review]
    K --> L[Generate Final Report with Remaining Issues]
    L --> E
迭代式审查与修复循环，确保PRD在完成前达到质量要求。
mermaid
flowchart TD
    A[Phase 5 Start] --> B[Run doc-prd-reviewer]
    B --> C[Generate Review Report]
    C --> D{Review Score >= 90?}

    D -->|Yes| E[PASS - Proceed to Phase 6]
    D -->|No| F{Iteration < Max?}

    F -->|Yes| G[Run doc-prd-fixer]
    G --> H[Apply Fixes]
    H --> I[Generate Fix Report]
    I --> J[Increment Iteration]
    J --> B

    F -->|No| K[Flag for Manual Review]
    K --> L[Generate Final Report with Remaining Issues]
    L --> E

5.1 Initial Review

5.1 初始审查

Run 
doc-prd-reviewer
to identify issues.
bash
/doc-prd-reviewer PRD-NN
Output: 
PRD-NN.R_review_report_v001.md
Review Checklist:
CheckDescriptionAuto-FixManual
Link IntegrityAll internal links between sections resolveYes-
Threshold ConsistencyPerformance metrics match across sectionsYes-
BRD AlignmentPRD content accurately reflects BRD requirements-Review
Placeholder DetectionNo 
[TODO]
, 
[TBD]
, 
YYYY-MM-DD
remaining		Yes-
Traceability TagsAll 
@brd:
tags reference valid BRD IDs		Yes-
Cross-Reference Validity
@depends:
and 
@discoverability:
tags valid		Yes-
Section CompletenessNo empty or stub sections-Flag
Customer ContentSection 10 has substantive content-Flag
运行
doc-prd-reviewer
以识别问题。
bash
/doc-prd-reviewer PRD-NN
输出: 
PRD-NN.R_review_report_v001.md
审查清单:
检查项描述自动修复手动处理
链接完整性章节间所有内部链接均可解析是-
阈值一致性各章节性能指标匹配是-
BRD对齐PRD内容准确反映BRD需求-审查
占位符检测无
[TODO]
、
[TBD]
、
YYYY-MM-DD
残留		是-
可追溯性标签所有
@brd:
标签均引用有效的BRD ID		是-
交叉引用有效性
@depends:
和
@discoverability:
标签有效		是-
章节完整性无空章节或 stub 章节-标记
客户内容章节10包含实质性内容-标记

5.2 Fix Cycle

5.2 修复循环

If review score < 90%, invoke 
doc-prd-fixer
.
bash
/doc-prd-fixer PRD-NN --revalidate
Fix Categories:
CategoryFixes Applied
Missing FilesCreate glossary, reference docs
Broken LinksUpdate paths, create targets
Element IDsConvert legacy patterns, fix invalid type codes
ContentReplace template placeholders, dates
ReferencesUpdate traceability tags
ThresholdsAlign inconsistent values to BRD source
Output: 
PRD-NN.F_fix_report_v001.md
若审查分数<90%，调用
doc-prd-fixer
。
bash
/doc-prd-fixer PRD-NN --revalidate
修复类别:
类别应用的修复
缺失文件创建术语表、参考文档
损坏链接更新路径、创建目标
元素ID转换遗留模式、修复无效类型代码
内容替换模板占位符、日期
引用更新可追溯性标签
阈值将不一致的值与BRD源对齐
输出: 
PRD-NN.F_fix_report_v001.md

5.3 Re-Review

5.3 重新审查

After fixes, automatically re-run reviewer.
bash
/doc-prd-reviewer PRD-NN
Output: 
PRD-NN.R_review_report_v002.md
修复完成后，自动重新运行审查器。
bash
/doc-prd-reviewer PRD-NN
输出: 
PRD-NN.R_review_report_v002.md

5.4 Iteration Control

5.4 迭代控制

ParameterDefaultDescription
max_iterations
3Maximum fix-review cycles
target_score
90Minimum passing score
stop_on_manual
falseStop if only manual issues remain
Iteration Example:
Iteration 1:
  Review v001: Score 85 (2 errors, 4 warnings)
  Fix v001: Fixed 5 issues, created 1 file

Iteration 2:
  Review v002: Score 94 (0 errors, 2 warnings)
  Status: PASS (score >= 90)
参数默认值描述
max_iterations
3最大修复-审查循环次数
target_score
90最低合格分数
stop_on_manual
false若仅剩余手动问题则停止
迭代示例:
迭代1:
  审查v001: 分数85（2个错误，4个警告）
  修复v001: 修复5个问题，创建1个文件

迭代2:
  审查v002: 分数94（0个错误，2个警告）
  状态: 通过（分数≥90）

5.5 Quality Checks (Post-Fix)

5.5 修复后质量检查

After passing the fix cycle:
  1. Link Integrity Check:
    Scanning PRD-01 for internal links...
├── PRD-01.0_index.md: 17 links found
│   ├── PRD-01.1_document_control.md ✓
│   ├── PRD-01.2_executive_summary.md ✓
│   └── ... (all valid)
└── Result: 0 broken links
  2. Threshold Consistency Check:
    Comparing thresholds across sections...
├── Section 5 (Success Metrics): auth.p99 = 100ms
├── Section 9 (Quality Attributes): auth.p99 = 100ms
├── Section 17 (Appendix B.1): auth.p99 = 100ms
└── Result: Consistent ✓
  3. BRD Alignment Check:
    Verifying PRD requirements map to BRD source...
├── PRD.01.01.01 → BRD.01.01.01 (Multi-Provider Auth) ✓
├── PRD.01.01.02 → BRD.01.01.02 (4D Authorization) ✓
└── Result: 12/12 requirements aligned ✓
  4. EARS-Ready Report:
    EARS-Ready Score Breakdown
=========================
Business Requirements Clarity: 40/40
Requirements Maturity:         35/35
EARS Translation Readiness:    20/20
Strategic Alignment:           5/5
----------------------------
Total EARS-Ready Score:        100/100 (Target: >= 90)
Status: READY FOR EARS GENERATION
  5. Traceability Matrix Update:
    bash
    # Update PRD-00_TRACEABILITY_MATRIX.md
python ai_dev_flow/scripts/update_traceability_matrix.py \
  --prd docs/02_PRD/PRD-NN_{slug}/PRD-NN_{slug}.md \
  --matrix docs/02_PRD/PRD-00_TRACEABILITY_MATRIX.md
通过修复循环后:
  1. 链接完整性检查:
    扫描PRD-01的内部链接...
├── PRD-01.0_index.md: 发现17个链接
│   ├── PRD-01.1_document_control.md ✓
│   ├── PRD-01.2_executive_summary.md ✓
│   └── ...（全部有效）
└── 结果: 0个损坏链接
  2. 阈值一致性检查:
    跨章节比较阈值...
├── 章节5（成功指标）: auth.p99 = 100ms
├── 章节9（质量属性）: auth.p99 = 100ms
├── 章节17（附录B.1）: auth.p99 = 100ms
└── 结果: 一致 ✓
  3. BRD对齐检查:
    验证PRD需求与BRD源的映射...
├── PRD.01.01.01 → BRD.01.01.01（多提供商认证） ✓
├── PRD.01.01.02 → BRD.01.01.02（4D授权） ✓
└── 结果: 12/12需求对齐 ✓
  4. EARS就绪报告:
    EARS就绪分数明细
=========================
业务需求清晰度: 40/40
需求成熟度:         35/35
EARS转换就绪性:    20/20
战略对齐:           5/5
----------------------------
总EARS就绪分数:        100/100（目标: ≥90）
状态: 已准备好生成EARS
  5. 可追溯性矩阵更新:
    bash
    # 更新PRD-00_TRACEABILITY_MATRIX.md
python ai_dev_flow/scripts/update_traceability_matrix.py \
  --prd docs/02_PRD/PRD-NN_{slug}/PRD-NN_{slug}.md \
  --matrix docs/02_PRD/PRD-00_TRACEABILITY_MATRIX.md

Step 7: Process Next BRD

步骤7：处理下一个BRD

After completing one PRD:
  1. Mark current BRD→PRD as complete
  2. Update traceability matrix
  3. Move to next BRD in execution order
  4. Repeat Steps 3-5
Progress Tracking:
PRD Generation Progress:
[████████░░░░░░░░] 3/7 Complete

Completed:
  ✓ PRD-06 (from BRD-06) - EARS-Ready: 94%
  ✓ PRD-07 (from BRD-07) - EARS-Ready: 92%
  ✓ PRD-01 (from BRD-01) - EARS-Ready: 96%

In Progress:
  ⟳ PRD-02 (from BRD-02) - Generating Section 10...

Pending:
  ○ PRD-03 (from BRD-03) - Awaiting BRD-01 completion
  ○ PRD-04 (from BRD-04)
  ○ PRD-05 (from BRD-05)
完成一个PRD后:
  1. 将当前BRD→PRD标记为完成
  2. 更新可追溯性矩阵
  3. 按执行顺序处理下一个BRD
  4. 重复步骤3-5
进度跟踪:
PRD生成进度:
[████████░░░░░░░░] 3/7 完成

已完成:
  ✓ PRD-06（来自BRD-06）- EARS就绪: 94%
  ✓ PRD-07（来自BRD-07）- EARS就绪: 92%
  ✓ PRD-01（来自BRD-01）- EARS就绪: 96%

处理中:
  ⟳ PRD-02（来自BRD-02）- 正在生成章节10...

待处理:
  ○ PRD-03（来自BRD-03）- 等待BRD-01完成
  ○ PRD-04（来自BRD-04）
  ○ PRD-05（来自BRD-05）

Step 8: Parallel Generation

步骤8：并行生成

For independent BRDs (no cross-dependencies), generate PRDs in parallel.
Parallel Execution Rules:
  1. Independence Check: No shared 
    @depends-brd
    references
  2. Resource Limits: Maximum 3 parallel generations (configurable)
  3. Failure Isolation: One failure doesn't block others
  4. Progress Reporting: Aggregate status updates
Parallel Execution Example:
Parallel Group Execution:
├── Thread 1: BRD-01 → PRD-01 [████████████████] 100%
├── Thread 2: BRD-02 → PRD-02 [████████████░░░░] 75%
└── Thread 3: BRD-05 → PRD-05 [████████░░░░░░░░] 50%
对于独立的BRD（无跨依赖），并行生成PRD。
并行执行规则:
  1. 独立性检查: 无共享的
    @depends-brd
    引用
  2. 资源限制: 最大并行生成数为3（可配置）
  3. 故障隔离: 一个失败不会阻塞其他任务
  4. 进度报告: 汇总状态更新
并行执行示例:
并行分组执行:
├── 线程1: BRD-01 → PRD-01 [████████████████] 100%
├── 线程2: BRD-02 → PRD-02 [████████████░░░░] 75%
└── 线程3: BRD-05 → PRD-05 [████████░░░░░░░░] 50%

Configuration

配置

Default Configuration

默认配置

yaml
undefined
yaml
undefined

config/prd_autopilot.yaml

config/prd_autopilot.yaml

prd_autopilot: version: "1.2"
scoring: prd_ready_min: 90 ears_ready_min: 90 review_score_min: 90 strict_mode: false
execution: max_parallel: 3 auto_fix: true continue_on_error: false timeout_per_brd: 300 # seconds
output: structure: auto # auto, monolithic, sectioned size_threshold_kb: 25 report_format: markdown
validation: skip_validation: false fix_iterations_max: 3
review: enabled: true check_links: true check_thresholds: true check_brd_alignment: true check_placeholders: true check_traceability: true auto_fix_links: true auto_fix_placeholders: true flag_customer_content: true
undefined
prd_autopilot: version: "1.2"
scoring: prd_ready_min: 90 ears_ready_min: 90 review_score_min: 90 strict_mode: false
execution: max_parallel: 3 auto_fix: true continue_on_error: false timeout_per_brd: 300 # seconds
output: structure: auto # auto, monolithic, sectioned size_threshold_kb: 25 report_format: markdown
validation: skip_validation: false fix_iterations_max: 3
review: enabled: true check_links: true check_thresholds: true check_brd_alignment: true check_placeholders: true check_traceability: true auto_fix_links: true auto_fix_placeholders: true flag_customer_content: true
undefined

Command Line Options

命令行选项

OptionDefaultDescription
--min-prd-ready
90Minimum PRD-Ready score
--min-ears-ready
90Minimum EARS-Ready score
--min-review-score
90Minimum Final Review score
--max-parallel
3Maximum parallel PRD generations
--no-auto-fix
falseDisable auto-fix (manual only)
--continue-on-error
falseContinue if one BRD fails
--dry-run
falsePreview execution plan only
--output-format
autoForce monolithic or sectioned output
--skip-review
falseSkip final content review phase
--review-only
falseRun only final review on existing PRD
选项默认值描述
--min-prd-ready
90最低PRD就绪分数
--min-ears-ready
90最低EARS就绪分数
--min-review-score
90最低最终审查分数
--max-parallel
3最大并行PRD生成数
--no-auto-fix
false禁用自动修复（仅手动）
--continue-on-error
false若一个BRD失败则继续执行
--dry-run
false仅预览执行计划
--output-format
auto强制单文件或分章节输出
--skip-review
false跳过最终内容审查阶段
--review-only
false仅对现有PRD运行最终审查

Context Management

上下文管理

Chunked Parallel Execution (MANDATORY)

分块并行执行（必填）

CRITICAL: To prevent conversation context overflow errors ("Prompt is too long", "Conversation too long"), all autopilot operations MUST follow chunked execution rules:
Chunk Size Limit: Maximum 3 documents per chunk
Chunking Rules:
  1. Chunk Formation: Group documents into chunks of maximum 3 documents each
  2. Sequential Chunk Processing: Process one chunk at a time, completing all documents in a chunk before starting the next
  3. Context Pause: After completing each chunk, provide a summary and pause for user acknowledgment
  4. Progress Tracking: Display chunk progress (e.g., "Chunk 2/5: Processing BRD-04, BRD-05, BRD-06")
Execution Pattern:
Documents: BRD-01, BRD-02, BRD-03, BRD-04, BRD-05, BRD-06, BRD-07

Chunk 1: [BRD-01, BRD-02, BRD-03] → Process → Summary → Pause
Chunk 2: [BRD-04, BRD-05, BRD-06] → Process → Summary → Pause
Chunk 3: [BRD-07]                  → Process → Summary → Complete
Chunk Completion Summary Template:
Chunk N/M Complete:
├── Generated: PRD-01, PRD-02, PRD-03
├── EARS-Ready Scores: 94%, 92%, 91%
├── Status: All validated
└── Next: Continue with Chunk N+1? [Y/n]
Why Chunking is Required:
  • Prevents "Conversation too long" errors during batch processing
  • Allows context compaction between chunks
  • Enables recovery from failures without losing all progress
  • Provides natural checkpoints for user review
Configuration Override:
yaml
execution:
  max_parallel: 3        # HARD LIMIT - do not exceed
  chunk_size: 3          # Documents per chunk
  pause_between_chunks: true
关键: 为防止对话上下文溢出错误（"Prompt is too long", "Conversation too long"），所有自动流水线操作必须遵循分块执行规则:
分块大小限制: 每个分块最多3个文档
分块规则:
  1. 分块形成: 将文档分组为每个分块最多3个文档
  2. 顺序分块处理: 一次处理一个分块，完成一个分块中的所有文档后再开始下一个
  3. 上下文暂停: 完成每个分块后，提供摘要并暂停以等待用户确认
  4. 进度跟踪: 显示分块进度（例如: "Chunk 2/5: Processing BRD-04, BRD-05, BRD-06"）
执行模式:
Documents: BRD-01, BRD-02, BRD-03, BRD-04, BRD-05, BRD-06, BRD-07

Chunk 1: [BRD-01, BRD-02, BRD-03] → 处理 → 摘要 → 暂停
Chunk 2: [BRD-04, BRD-05, BRD-06] → 处理 → 摘要 → 暂停
Chunk 3: [BRD-07]                  → 处理 → 摘要 → 完成
分块完成摘要模板:
Chunk N/M 完成:
├── 已生成: PRD-01, PRD-02, PRD-03
├── EARS就绪分数: 94%, 92%, 91%
├── 状态: 全部已验证
└── 下一步: 继续处理Chunk N+1? [Y/n]
为何需要分块:
  • 防止批量处理期间出现"Conversation too long"错误
  • 允许分块之间的上下文压缩
  • 支持从故障中恢复而不丢失所有进度
  • 为用户审查提供自然的检查点
配置覆盖:
yaml
execution:
  max_parallel: 3        # 硬限制 - 请勿超过
  chunk_size: 3          # 每个分块的文档数
  pause_between_chunks: true

Execution Modes

执行模式

Mode 1: Interactive (Default)

模式1：交互式（默认）

User confirms each step before proceeding.
bash
/doc-prd-autopilot BRD-01,BRD-02 --interactive
用户在每个步骤前确认。
bash
/doc-prd-autopilot BRD-01,BRD-02 --interactive

Output:

输出:

Dependency Analysis: BRD-01 → BRD-02 (BRD-02 depends on BRD-01)

依赖分析: BRD-01 → BRD-02（BRD-02依赖BRD-01）

[1/2] BRD-01: PRD-Ready Score = 92% (PASS)

[1/2] BRD-01: PRD就绪分数 = 92%（通过）

Generate PRD-01? [Y/n] y

生成PRD-01? [Y/n] y

PRD-01 generated. EARS-Ready Score = 94% (PASS)

PRD-01已生成。EARS就绪分数 = 94%（通过）

[2/2] BRD-02: PRD-Ready Score = 88% (FAIL)

[2/2] BRD-02: PRD就绪分数 = 88%（失败）

Auto-fix available. Apply fixes? [Y/n] y

可自动修复。应用修复? [Y/n] y

Fixes applied. New score = 91% (PASS)

已应用修复。新分数 = 91%（通过）

Generate PRD-02? [Y/n] y

生成PRD-02? [Y/n] y

PRD-02 generated. EARS-Ready Score = 90% (PASS)

PRD-02已生成。EARS就绪分数 = 90%（通过）

Summary: 2/2 PRDs generated successfully.

摘要: 2/2 PRD生成成功。

undefined
undefined

Mode 2: Automatic

模式2：自动

No user confirmation, auto-fix enabled.
bash
/doc-prd-autopilot all --auto
无需用户确认，启用自动修复。
bash
/doc-prd-autopilot all --auto

Output:

输出:

PRD Autopilot - Automatic Mode

PRD自动流水线 - 自动模式

==============================

==============================

Scanning: docs/01_BRD/

扫描: docs/01_BRD/

Found: 7 BRDs

发现: 7个BRD

Phase 1: Dependency Analysis... Done

阶段1: 依赖分析... 完成

Phase 2-4: Processing...

阶段2-4: 处理中...

[████████████████] 7/7 Complete

[████████████████] 7/7 完成

Summary:

摘要:

✓ 7 PRDs generated

✓ 7个PRD已生成

✓ 3 BRDs auto-fixed

✓ 3个BRD已自动修复

✓ Average EARS-Ready: 93%

✓ 平均EARS就绪分数: 93%

undefined
undefined

Mode 3: Dry Run

模式3：试运行

Preview execution plan without generating files.
bash
/doc-prd-autopilot all --dry-run
预览执行计划但不生成文件。
bash
/doc-prd-autopilot all --dry-run

Output:

输出:

PRD Autopilot - Dry Run Mode

PRD自动流水线 - 试运行模式

============================

============================

Execution Plan:

执行计划:

1. BRD-06 (Infrastructure) → PRD-06

1. BRD-06（基础设施）→ PRD-06

2. BRD-07 (Config) → PRD-07

2. BRD-07（配置）→ PRD-07

3. [Parallel] BRD-01, BRD-02 → PRD-01, PRD-02

3. [并行] BRD-01, BRD-02 → PRD-01, PRD-02

4. BRD-03 → PRD-03

4. BRD-03 → PRD-03

5. [Parallel] BRD-04, BRD-05 → PRD-04, PRD-05

5. [并行] BRD-04, BRD-05 → PRD-04, PRD-05

Estimated Duration: ~4 units (parallel) vs ~7 units (sequential)

预计时长: ~4单位（并行） vs ~7单位（串行）

No files will be created in dry-run mode.

试运行模式下不会创建任何文件。

undefined
undefined

Mode 4: Review Mode (v2.1)

模式4：审查模式（v2.1）

Validate existing PRD documents and generate a quality report without modification.
Purpose: Audit existing PRD documents for compliance, quality scores, and identify issues.
Command:
bash
undefined
验证现有PRD文档并生成质量报告，不修改文档。
用途: 审计现有PRD文档的合规性、质量分数并识别问题。
命令:
bash
undefined

Review single PRD

审查单个PRD

/doc-prd-autopilot PRD-01 --mode review
/doc-prd-autopilot PRD-01 --mode review

Review all PRDs

审查所有PRD

/doc-prd-autopilot all --mode review --output-report tmp/prd_review_report.md

**Review Report Structure**:

```markdown
/doc-prd-autopilot all --mode review --output-report tmp/prd_review_report.md

**审查报告结构**:

```markdown

PRD Review Report: PRD-01_f1_iam

PRD审查报告: PRD-01_f1_iam

Summary

摘要

  • EARS-Ready Score: 87% 🟡
  • Final Review Score: 85% 🟡
  • Total Issues: 14
  • Auto-Fixable: 10
  • Manual Review: 4
  • EARS就绪分数: 87% 🟡
  • 最终审查分数: 85% 🟡
  • 总问题数: 14
  • 可自动修复: 10
  • 需要手动审查: 4

Score Breakdown

分数明细

CategoryScoreStatus
Business Requirements Clarity38/40🟡
Requirements Maturity32/35🟡
EARS Translation Readiness18/20🟡
Strategic Alignment5/5✅
类别分数状态
业务需求清晰度38/40🟡
需求成熟度32/35🟡
EARS转换就绪性18/20🟡
战略对齐5/5✅

Final Review Checks

最终审查检查

CheckStatusDetails
Link Integrity✅All links valid
Threshold Consistency🟡2 mismatches found
BRD Alignment✅All requirements traced
Placeholder Detection❌3 [TODO] markers found
Traceability Tags✅Valid @brd references
Section 10 Content🟡Needs business review
检查项状态详情
链接完整性✅所有链接有效
阈值一致性🟡发现2处不匹配
BRD对齐✅所有需求均可追溯
占位符检测❌发现3个[TODO]标记
可追溯性标签✅@brd引用有效
章节10内容🟡需要业务审查

Auto-Fixable Issues

可自动修复问题

#IssueLocationFix Action
1Legacy element IDSection 9:L45Convert PO-001 to PRD.01.07.01
2Placeholder textSection 14:L78Remove [TODO] marker
3Inconsistent thresholdSection 5:L23Align to BRD value
............
#问题位置修复操作
1遗留元素ID章节9:L45将PO-001转换为PRD.01.07.01
2占位符文本章节14:L78移除[TODO]标记
3不一致的阈值章节5:L23与BRD值对齐
............

Manual Review Required

需要手动审查

#IssueLocationReason
1Incomplete Section 10Customer-Facing ContentRequires business input
2Missing timing profileSection 20.1Domain expertise needed
............

**Review Configuration**:

```yaml
review_mode:
  enabled: true
  checks:
    - structure_validation      # 17/21 sections
    - element_id_compliance     # PRD.NN.TT.SS format
    - link_integrity            # Internal link check
    - threshold_consistency     # Cross-section consistency
    - brd_alignment             # Upstream traceability
    - placeholder_detection     # [TODO], [TBD] markers
    - traceability_tags         # @brd tag validation
    - section_10_content        # Customer-facing content
    - score_calculation         # EARS-Ready score
  output:
    format: markdown
    include_fix_suggestions: true
  thresholds:
    pass: 90
    warning: 85
    fail: 0
#问题位置原因
1章节10不完整面向客户内容需要业务输入
2缺失时间配置文件章节20.1需要领域专业知识
............

**审查配置**:

```yaml
review_mode:
  enabled: true
  checks:
    - structure_validation      # 17/21章节
    - element_id_compliance     # PRD.NN.TT.SS格式
    - link_integrity            # 内部链接检查
    - threshold_consistency     # 跨章节一致性
    - brd_alignment             # 上游可追溯性
    - placeholder_detection     # [TODO], [TBD]标记
    - traceability_tags         # @brd标签验证
    - section_10_content        # 面向客户内容
    - score_calculation         # EARS就绪分数
  output:
    format: markdown
    include_fix_suggestions: true
  thresholds:
    pass: 90
    warning: 85
    fail: 0

Mode 5: Fix Mode (v2.1)

模式5：修复模式（v2.1）

Auto-repair existing PRD documents while preserving manual content.
Purpose: Apply automated fixes to PRD documents to improve quality scores and compliance.
Command:
bash
undefined
自动修复现有PRD文档，同时保留手动内容。
用途: 对PRD文档应用自动修复以提高质量分数和合规性。
命令:
bash
undefined

Fix single PRD

修复单个PRD

/doc-prd-autopilot PRD-01 --mode fix
/doc-prd-autopilot PRD-01 --mode fix

Fix with backup

修复并备份

/doc-prd-autopilot PRD-01 --mode fix --backup
/doc-prd-autopilot PRD-01 --mode fix --backup

Fix specific issue types only

仅修复特定类型的问题

/doc-prd-autopilot PRD-01 --mode fix --fix-types "element_ids,thresholds,placeholders"
/doc-prd-autopilot PRD-01 --mode fix --fix-types "element_ids,thresholds,placeholders"

Dry-run fix (preview changes)

试运行修复（预览更改）

/doc-prd-autopilot PRD-01 --mode fix --dry-run

**Fix Categories and Actions**:

| Category | Issue | Auto-Fix Action | Preserves Content |
|----------|-------|-----------------|-------------------|
| **Element IDs** | Legacy PO-XXX format | Convert to PRD.NN.07.SS | ✅ |
| **Element IDs** | Legacy FF-XXX format | Convert to PRD.NN.01.SS | ✅ |
| **Element IDs** | Legacy AC-XXX format | Convert to PRD.NN.06.SS | ✅ |
| **Thresholds** | Inconsistent values | Align to BRD source | ✅ |
| **Thresholds** | Hardcoded values | Replace with @threshold | ✅ |
| **Links** | Broken internal links | Update paths or remove | ✅ |
| **Placeholders** | [TODO], [TBD] text | Remove markers, flag content | ✅ |
| **Sections** | Missing Document Control | Add from template | ✅ |
| **Sections** | Missing EARS-Ready score | Calculate and insert | ✅ |
| **Sections** | Missing Section 20 | Add EARS Enhancement template | ✅ |
| **Traceability** | Missing @brd tags | Add with placeholder | ✅ |
| **Traceability** | Invalid @brd reference | Correct or remove | ✅ |

**Content Preservation Rules**:

1. **Never delete** existing requirements or user stories
2. **Never modify** executive summary content
3. **Never change** stakeholder analysis details
4. **Only add** missing sections and metadata
5. **Only replace** legacy element IDs and placeholders
6. **Backup first** if `--backup` flag is set

**Element ID Migration**:

| Legacy Pattern | New Format | Example |
|----------------|------------|---------|
| `PO-XXX` | `PRD.NN.07.SS` | PO-001 → PRD.01.07.01 |
| `FF-XXX` | `PRD.NN.01.SS` | FF-001 → PRD.01.01.01 |
| `AC-XXX` | `PRD.NN.06.SS` | AC-001 → PRD.01.06.01 |
| `US-XXX` | `PRD.NN.08.SS` | US-001 → PRD.01.08.01 |

**Fix Report Structure**:

```markdown
/doc-prd-autopilot PRD-01 --mode fix --dry-run

**修复类别与操作**:

| 类别 | 问题 | 自动修复操作 | 保留内容 |
|----------|-------|-----------------|-------------------|
| **元素ID** | 遗留PO-XXX格式 | 转换为PRD.NN.07.SS | ✅ |
| **元素ID** | 遗留FF-XXX格式 | 转换为PRD.NN.01.SS | ✅ |
| **元素ID** | 遗留AC-XXX格式 | 转换为PRD.NN.06.SS | ✅ |
| **元素ID** | 遗留US-XXX格式 | 转换为PRD.NN.08.SS | ✅ |
| **阈值** | 不一致的值 | 与BRD源对齐 | ✅ |
| **阈值** | 硬编码值 | 替换为@threshold | ✅ |
| **链接** | 损坏的内部链接 | 更新路径或移除 | ✅ |
| **占位符** | [TODO], [TBD]文本 | 移除标记，标记内容 | ✅ |
| **章节** | 缺失文档控制 | 从模板添加 | ✅ |
| **章节** | 缺失EARS就绪分数 | 计算并插入 | ✅ |
| **章节** | 缺失章节20 | 添加EARS增强模板 | ✅ |
| **可追溯性** | 缺失@brd标签 | 添加占位符 | ✅ |
| **可追溯性** | 无效@brd引用 | 更正或移除 | ✅ |

**内容保留规则**:

1. **永不删除**现有需求或用户故事
2. **永不修改**执行摘要内容
3. **永不更改**干系人分析详情
4. **仅添加**缺失的章节和元数据
5. **仅替换**遗留元素ID和占位符
6. **先备份**若设置`--backup`标志

**元素ID迁移**:

| 遗留模式 | 新格式 | 示例 |
|----------------|------------|---------|
| `PO-XXX` | `PRD.NN.07.SS` | PO-001 → PRD.01.07.01 |
| `FF-XXX` | `PRD.NN.01.SS` | FF-001 → PRD.01.01.01 |
| `AC-XXX` | `PRD.NN.06.SS` | AC-001 → PRD.01.06.01 |
| `US-XXX` | `PRD.NN.08.SS` | US-001 → PRD.01.08.01 |

**修复报告结构**:

```markdown

PRD Fix Report: PRD-01_f1_iam

PRD修复报告: PRD-01_f1_iam

Summary

摘要

  • Before EARS-Ready Score: 87% 🟡
  • After EARS-Ready Score: 94% ✅
  • Issues Fixed: 10
  • Issues Remaining: 4 (manual review required)
  • 修复前EARS就绪分数: 87% 🟡
  • 修复后EARS就绪分数: 94% ✅
  • 已修复问题数: 10
  • 剩余问题数: 4（需要手动审查）

Fixes Applied

已应用修复

#IssueLocationFix Applied
1Legacy element IDSection 9:L45Converted PO-001 → PRD.01.07.01
2Placeholder textSection 14:L78Removed [TODO] marker
3Inconsistent thresholdSection 5:L23Aligned to BRD.01 value
............
#问题位置应用的修复
1遗留元素ID章节9:L45已转换PO-001 → PRD.01.07.01
2占位符文本章节14:L78已移除[TODO]标记
3不一致的阈值章节5:L23已与BRD.01值对齐
............

Files Modified

修改的文件

  • docs/02_PRD/PRD-01_f1_iam/PRD-01.0_index.md
  • docs/02_PRD/PRD-01_f1_iam/PRD-01.5_success_metrics.md
  • docs/02_PRD/PRD-01_f1_iam/PRD-01.9_functional_requirements.md
  • docs/02_PRD/PRD-01_f1_iam/PRD-01.0_index.md
  • docs/02_PRD/PRD-01_f1_iam/PRD-01.5_success_metrics.md
  • docs/02_PRD/PRD-01_f1_iam/PRD-01.9_functional_requirements.md

Backup Location

备份位置

  • tmp/backup/PRD-01_f1_iam_20260209_143022/
  • tmp/backup/PRD-01_f1_iam_20260209_143022/

Score Impact

分数影响

CategoryBeforeAfterDelta
Requirements Clarity38/4040/40+2
Requirements Maturity32/3534/35+2
EARS Translation18/2019/20+1
类别修复前修复后变化
需求清晰度38/4040/40+2
需求成熟度32/3534/35+2
EARS转换18/2019/20+1

Next Steps

下一步

  1. Complete Section 10 (Customer-Facing Content)
  2. Add timing profile to Section 20.1
  3. Re-run validation to confirm score

**Fix Configuration**:

```yaml
fix_mode:
  enabled: true
  backup:
    enabled: true
    location: "tmp/backup/"
    retention_days: 7

  fix_categories:
    element_ids: true        # Legacy ID conversion
    thresholds: true         # Consistency fixes
    links: true              # Broken link repair
    placeholders: true       # [TODO]/[TBD] removal
    sections: true           # Missing sections
    traceability: true       # @brd tag fixes

  preservation:
    executive_summary: true     # Never modify
    requirements: true          # Never delete
    user_stories: true          # Never modify
    comments: true              # Preserve user comments

  validation:
    re_validate_after_fix: true
    require_score_improvement: false
    max_fix_iterations: 3

  element_id_migration:
    PO_XXX_to_PRD_NN_07_SS: true
    FF_XXX_to_PRD_NN_01_SS: true
    AC_XXX_to_PRD_NN_06_SS: true
    US_XXX_to_PRD_NN_08_SS: true
Command Line Options (Review/Fix):
OptionModeDefaultDescription
--mode review
Review-Run review mode only
--mode fix
Fix-Run fix mode
--output-report
BothautoReport output path
--backup
FixtrueCreate backup before fixing
--fix-types
FixallComma-separated fix categories
--dry-run
FixfalsePreview fixes without applying
--preserve-all
FixfalseExtra cautious preservation
  1. 完成章节10（面向客户内容）
  2. 为章节20.1添加时间配置文件
  3. 重新运行验证以确认分数

**修复配置**:

```yaml
fix_mode:
  enabled: true
  backup:
    enabled: true
    location: "tmp/backup/"
    retention_days: 7

  fix_categories:
    element_ids: true        # 遗留ID转换
    thresholds: true         # 一致性修复
    links: true              # 损坏链接修复
    placeholders: true       # [TODO]/[TBD]移除
    sections: true           # 缺失章节添加
    traceability: true       # @brd标签修复

  preservation:
    executive_summary: true     # 永不修改
    requirements: true          # 永不删除
    user_stories: true          # 永不修改
    comments: true              # 保留用户评论

  validation:
    re_validate_after_fix: true
    require_score_improvement: false
    max_fix_iterations: 3

  element_id_migration:
    PO_XXX_to_PRD_NN_07_SS: true
    FF_XXX_to_PRD_NN_01_SS: true
    AC_XXX_to_PRD_NN_06_SS: true
    US_XXX_to_PRD_NN_08_SS: true
命令行选项（审查/修复）:
选项模式默认值描述
--mode review
审查-仅运行审查模式
--mode fix
修复-运行修复模式
--output-report
两者auto报告输出路径
--backup
修复true修复前创建备份
--fix-types
修复all逗号分隔的修复类别
--dry-run
修复false预览修复但不应用
--preserve-all
修复false额外谨慎的内容保留

Output Files

输出文件

Generated PRD Structure

生成的PRD结构

Nested Folder Rule: ALL PRDs use nested folders (
PRD-NN_{slug}/
) regardless of size.
Monolithic Output (single file ≤25KB - in nested folder):
docs/02_PRD/
├── PRD-00_TRACEABILITY_MATRIX.md  # Updated
└── PRD-01_f1_iam/                  # Nested folder (REQUIRED)
    └── PRD-01_f1_iam.md            # Monolithic PRD inside folder
Sectioned Output (multiple files >25KB - in nested folder):
docs/02_PRD/
├── PRD-00_TRACEABILITY_MATRIX.md  # Updated
└── PRD-01_f1_iam/                  # Nested folder (REQUIRED)
    ├── PRD-01.0_index.md
    ├── PRD-01.1_document_control.md
    ├── PRD-01.2_executive_summary.md
    ├── PRD-01.3_problem_statement.md
    ...
    └── PRD-01.21_qa_strategy.md
嵌套文件夹规则: 所有PRD无论大小都使用嵌套文件夹（
PRD-NN_{slug}/
）。
单文件输出（单个文件≤25KB - 在嵌套文件夹中）:
docs/02_PRD/
├── PRD-00_TRACEABILITY_MATRIX.md  # 已更新
└── PRD-01_f1_iam/                  # 嵌套文件夹（必填）
    └── PRD-01_f1_iam.md            # 单文件PRD在文件夹内
分章节输出（多个文件>25KB - 在嵌套文件夹中）:
docs/02_PRD/
├── PRD-00_TRACEABILITY_MATRIX.md  # 已更新
└── PRD-01_f1_iam/                  # 嵌套文件夹（必填）
    ├── PRD-01.0_index.md
    ├── PRD-01.1_document_control.md
    ├── PRD-01.2_executive_summary.md
    ├── PRD-01.3_problem_statement.md
    ...
    └── PRD-01.21_qa_strategy.md

Summary Report

摘要报告

Generated after completion:
markdown
undefined
完成后生成:
markdown
undefined

PRD Autopilot Summary Report

PRD自动流水线摘要报告

Execution Date: 2026-02-08 Input: 7 BRDs Output: 7 PRDs
执行日期: 2026-02-08 输入: 7个BRD 输出: 7个PRD

Execution Order

执行顺序

StepBRDPRDPRD-ReadyEARS-ReadyDurationStatus
1BRD-06PRD-0694%92%45sSuccess
2BRD-07PRD-0791%90%52sSuccess
3BRD-01PRD-0196%96%48sSuccess
3BRD-02PRD-0292%91%47sSuccess (Parallel)
4BRD-03PRD-0390%93%50sSuccess
5BRD-04PRD-0488%→91%90%62sSuccess (Auto-fixed)
5BRD-05PRD-0593%94%44sSuccess (Parallel)
步骤BRDPRDPRD就绪分数EARS就绪分数时长状态
1BRD-06PRD-0694%92%45s成功
2BRD-07PRD-0791%90%52s成功
3BRD-01PRD-0196%96%48s成功
3BRD-02PRD-0292%91%47s成功（并行）
4BRD-03PRD-0390%93%50s成功
5BRD-04PRD-0488%→91%90%62s成功（已自动修复）
5BRD-05PRD-0593%94%44s成功（并行）

Auto-Fixes Applied

已应用自动修复

BRDIssueFix Applied
BRD-04Missing timing profilesAdded p50/p95/p99 table
BRD-04Pending ADR topicAdded business driver
BRD问题应用的修复
BRD-04缺失时间配置文件添加p50/p95/p99表格
BRD-04待处理ADR主题添加业务驱动因素

Next Steps

下一步

  1. Review generated PRDs for domain-specific content
  2. Complete Section 10 (Customer-Facing Content) manually if flagged
  3. Run 
    /doc-ears-autopilot
    to generate EARS from PRDs

---
  1. 审查生成的PRD中的领域特定内容
  2. 若标记则手动完成章节10（面向客户内容）
  3. 运行
    /doc-ears-autopilot
    从PRD生成EARS

---

Error Handling

错误处理

Common Errors

常见错误

ErrorCauseResolution
CircularDependencyError
BRD-A depends on BRD-B and vice versaReview and remove circular reference
BRDNotFoundError
Specified BRD does not existCheck path and BRD ID
PRDReadyScoreLow
BRD score < 90% after auto-fix attemptsManual BRD improvement required
EARSReadyScoreLow
PRD score < 90% after auto-fixManual PRD improvement required
TemplateNotFoundError
PRD template missingVerify 
ai_dev_flow/02_PRD/
exists
错误原因解决方法
CircularDependencyError
BRD-A依赖BRD-B，反之亦然审查并移除循环引用
BRDNotFoundError
指定的BRD不存在检查路径和BRD ID
PRDReadyScoreLow
自动修复后BRD分数<90%需要手动改进BRD
EARSReadyScoreLow
自动修复后PRD分数<90%需要手动改进PRD
TemplateNotFoundError
PRD模板缺失验证
ai_dev_flow/02_PRD/
存在

Recovery Actions

恢复操作

bash
undefined
bash
undefined

Resume from last successful point

从最后成功的点恢复

/doc-prd-autopilot resume
/doc-prd-autopilot resume

Skip failed BRD and continue

跳过失败的BRD并继续

/doc-prd-autopilot all --continue-on-error
/doc-prd-autopilot all --continue-on-error

Retry single failed BRD

重试单个失败的BRD

/doc-prd-autopilot BRD-04 --force

---
/doc-prd-autopilot BRD-04 --force

---

Integration with Other Skills

与其他技能的集成

Upstream Skills

上游技能

  • doc-brd
    : Create/update BRDs before running autopilot
  • doc-validator
    : Pre-validate BRDs for readiness
  • doc-brd
    : 在运行自动流水线前创建/更新BRD
  • doc-validator
    : 提前验证BRD的就绪性

Downstream Skills

下游技能

  • doc-ears-autopilot
    : Chain autopilot for EARS generation (future)
  • doc-ears
    : Manual EARS creation from PRDs
  • doc-prd
    : Manual PRD editing after autopilot
  • doc-ears-autopilot
    : 链式自动流水线以生成EARS（未来）
  • doc-ears
    : 从PRD手动创建EARS
  • doc-prd
    : 自动流水线后手动编辑PRD

Typical Workflow

典型工作流

1. doc-brd (create BRDs)
2. doc-prd-autopilot (generate PRDs) ← This skill
3. doc-ears (create EARS from PRDs)
4. doc-bdd (create BDD from EARS)
5. ... continue SDD workflow
1. doc-brd（创建BRD）
2. doc-prd-autopilot（生成PRD） ← 本技能
3. doc-ears（从PRD创建EARS）
4. doc-bdd（从EARS创建BDD）
5. ... 继续SDD工作流

Prerequisites

前提条件

Before using this skill, ensure:
  1. BRD Documents Exist: At least one BRD in 
    docs/01_BRD/
  2. Templates Available: 
    ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md
  3. Shared Standards: 
    .claude/skills/doc-flow/SHARED_CONTENT.md
使用该技能前，请确保:
  1. BRD文档存在: 
    docs/01_BRD/
    中至少有一个BRD
  2. 模板可用: 
    ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md
    存在
  3. 共享标准: 
    .claude/skills/doc-flow/SHARED_CONTENT.md
    存在

Pre-Flight Check

飞行前检查

bash
undefined
bash
undefined

Verify BRD directory

验证BRD目录

ls docs/01_BRD/
ls docs/01_BRD/

Verify PRD template

验证PRD模板

ls ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md
ls ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md

Check for existing PRDs

检查现有PRD

ls docs/02_PRD/ 2>/dev/null || echo "PRD directory will be created"

---
ls docs/02_PRD/ 2>/dev/null || echo "PRD目录将被创建"

---

Validation Checklist

验证清单

After autopilot completion:
  • All target PRDs generated
  • Each PRD has EARS-Ready score >= 90%
  • Each PRD has Final Review score >= 90%
  • Traceability matrix updated (
    PRD-00_TRACEABILITY_MATRIX.md
    )
  • Each PRD references upstream BRD with 
    @brd
    tags
  • Section 10 (Customer-Facing Content) has substantive content
  • Section 20 (EARS Enhancement Appendix) completed
  • No broken links in generated documents (verified by Final Review)
  • No placeholder text remaining (verified by Final Review)
  • Thresholds consistent across sections (verified by Final Review)
  • BRD alignment verified (all PRD requirements trace to BRD source)
自动流水线完成后:
  • 所有目标PRD已生成
  • 每个PRD的EARS就绪分数≥90%
  • 每个PRD的最终审查分数≥90%
  • 可追溯性矩阵已更新（
    PRD-00_TRACEABILITY_MATRIX.md
    ）
  • 每个PRD使用
    @brd
    标签引用上游BRD
  • 章节10（面向客户内容）包含实质性内容
  • 章节20（EARS增强附录）已完成
  • 生成的文档中无损坏链接（由最终审查验证）
  • 无残留占位符文本（由最终审查验证）
  • 各章节阈值一致（由最终审查验证）
  • BRD对齐已验证（所有PRD需求均可追溯到BRD源）

Quick Reference

快速参考

InputOutputKey Metric
BRD(s)PRD(s)EARS-Ready >= 90%
Usage:
/doc-prd-autopilot <BRD-LIST> [OPTIONS]
Common Commands:
bash
undefined
输入输出关键指标
BRD(s)PRD(s)EARS就绪分数≥90%
用法:
/doc-prd-autopilot <BRD-LIST> [OPTIONS]
常用命令:
bash
undefined

Single BRD

单个BRD

/doc-prd-autopilot BRD-01
/doc-prd-autopilot BRD-01

All BRDs (automatic)

所有BRD（自动模式）

/doc-prd-autopilot all --auto
/doc-prd-autopilot all --auto

Preview only

仅预览

/doc-prd-autopilot all --dry-run
/doc-prd-autopilot all --dry-run

Resume after failure

失败后恢复

/doc-prd-autopilot resume

---
/doc-prd-autopilot resume

---

Related Resources

相关资源

Skills (Delegated)

委托的技能

  • PRD Skill: 
    .claude/skills/doc-prd/SKILL.md
    - PRD creation rules and structure
  • PRD Validator Skill: 
    .claude/skills/doc-prd-validator/SKILL.md
    - Validation rules and error codes
  • BRD Validator Skill: 
    .claude/skills/doc-brd-validator/SKILL.md
    - BRD readiness validation
  • PRD技能: 
    .claude/skills/doc-prd/SKILL.md
    - PRD创建规则和结构
  • PRD验证器技能: 
    .claude/skills/doc-prd-validator/SKILL.md
    - 验证规则和错误代码
  • BRD验证器技能: 
    .claude/skills/doc-brd-validator/SKILL.md
    - BRD就绪性验证

Templates and Rules

模板和规则

  • PRD Template: 
    ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md
  • PRD Schema: 
    ai_dev_flow/02_PRD/PRD_MVP_SCHEMA.yaml
  • PRD Creation Rules: 
    ai_dev_flow/02_PRD/PRD_MVP_CREATION_RULES.md
  • PRD Validation Rules: 
    ai_dev_flow/02_PRD/PRD_MVP_VALIDATION_RULES.md
  • PRD模板: 
    ai_dev_flow/02_PRD/PRD-MVP-TEMPLATE.md
  • PRD Schema: 
    ai_dev_flow/02_PRD/PRD_MVP_SCHEMA.yaml
  • PRD创建规则: 
    ai_dev_flow/02_PRD/PRD_MVP_CREATION_RULES.md
  • PRD验证规则: 
    ai_dev_flow/02_PRD/PRD_MVP_VALIDATION_RULES.md

Framework References

框架参考

  • SDD Workflow: 
    ai_dev_flow/SPEC_DRIVEN_DEVELOPMENT_GUIDE.md
  • MVP Autopilot: 
    ai_dev_flow/AUTOPILOT/MVP_AUTOPILOT.md
  • SDD工作流: 
    ai_dev_flow/SPEC_DRIVEN_DEVELOPMENT_GUIDE.md
  • MVP自动流水线: 
    ai_dev_flow/AUTOPILOT/MVP_AUTOPILOT.md

Review Document Standards (v2.2)

审查文档标准（v2.2）

IMPORTANT: Review reports generated by this autopilot are formal project documents.
See: 
.claude/skills/REVIEW_DOCUMENT_STANDARDS.md
for complete standards.
重要: 该自动流水线生成的审查报告是正式项目文档。
详见: 
.claude/skills/REVIEW_DOCUMENT_STANDARDS.md
中的完整标准。

Quick Reference

快速参考

RequirementValue
Storage LocationSame folder as reviewed PRD
File Name
PRD-NN.R_review_report.md
YAML FrontmatterMANDATORY - see shared standards
Parent ReferenceMANDATORY - link to PRD index
Example Location (ALL PRDs use nested folders):
docs/02_PRD/PRD-03_f3_observability/        # Nested folder (REQUIRED)
├── PRD-03_f3_observability.md              # Monolithic PRD
├── PRD-03.R_review_report_v001.md          # Review report v001
├── PRD-03.R_review_report_v002.md          # Review report v002
├── PRD-03.F_fix_report_v001.md             # Fix report (if fixes applied)
└── .drift_cache.json                        # Drift cache

docs/02_PRD/PRD-04_f4_config/               # Sectioned PRD example
├── PRD-04.0_index.md                        # Index file
├── PRD-04.1_core.md
├── PRD-04.R_review_report_v001.md          # Review report
└── .drift_cache.json                        # Drift cache
要求值
存储位置与被审查PRD同一文件夹
文件名
PRD-NN.R_review_report.md
YAML前置元数据必填 - 详见共享标准
父文档引用必填 - 链接到PRD索引
示例位置（所有PRD使用嵌套文件夹）:
docs/02_PRD/PRD-03_f3_observability/        # 嵌套文件夹（必填）
├── PRD-03_f3_observability.md              # 单文件PRD
├── PRD-03.R_review_report_v001.md          # 审查报告v001
├── PRD-03.R_review_report_v002.md          # 审查报告v002
├── PRD-03.F_fix_report_v001.md             # 修复报告（若应用修复）
└── .drift_cache.json                        # 漂移缓存

docs/02_PRD/PRD-04_f4_config/               # 分章节PRD示例
├── PRD-04.0_index.md                        # 索引文件
├── PRD-04.1_core.md
├── PRD-04.R_review_report_v001.md          # 审查报告
└── .drift_cache.json                        # 漂移缓存

Version History

版本历史

VersionDateChanges
2.52026-02-11Smart Document Detection: Added automatic document type recognition; Self-type input (PRD-NN) triggers review mode; Upstream-type input (BRD-NN) triggers generate-if-missing or find-and-review; Updated input patterns table with type-based actions
2.42026-02-11Nested Folder Enforcement: Fixed output structure examples to show ALL PRDs in nested folders regardless of size; Removed incorrect non-nested monolithic PRD example; Updated review report location examples
2.32026-02-10Review & Fix Cycle: Replaced Phase 5 (Step 6) with iterative Review -> Fix cycle using 
doc-prd-reviewer
and 
doc-prd-fixer
; Added 
doc-prd-fixer
skill dependency; Added iteration control with max 3 cycles and 90% target score
2.22026-02-10Added Review Document Standards: review reports stored alongside reviewed documents with YAML frontmatter and parent references; references shared 
.claude/skills/REVIEW_DOCUMENT_STANDARDS.md
2.12026-02-09Added Mode 4: Review Mode for validation-only analysis with visual score indicators; Added Mode 5: Fix Mode for auto-repair with backup and content preservation; Element ID migration (PO-XXX→PRD.NN.07.SS, FF-XXX→PRD.NN.01.SS, AC-XXX→PRD.NN.06.SS, US-XXX→PRD.NN.08.SS)
1.32026-02-08Integrated quality-advisor skill for real-time quality feedback in Phase 3 (PRD Generation)
1.22026-02-08Added Phase 5: Final Content Review with link integrity, threshold consistency, BRD alignment, and placeholder detection checks
1.12026-02-08Added skill dependencies, integrated doc-prd and doc-prd-validator skills
1.02026-02-08Initial skill creation with 7-step workflow
版本日期变更
2.52026-02-11智能文档检测: 添加自动文档类型识别；自身类型输入（PRD-NN）触发审查模式；上游类型输入（BRD-NN）触发缺失则生成或查找并审查；更新输入模式表格以包含基于类型的操作
2.42026-02-11嵌套文件夹强制: 修复输出结构示例，显示所有PRD无论大小都在嵌套文件夹中；移除不正确的非嵌套单文件PRD示例；更新审查报告位置示例
2.32026-02-10审查与修复循环: 用迭代式审查→修复循环替换阶段5（步骤6），使用
doc-prd-reviewer
和
doc-prd-fixer
；添加
doc-prd-fixer
技能依赖；添加迭代控制，最大3次循环，目标分数90%
2.22026-02-10添加审查文档标准：审查报告存储在被审查文档旁，包含YAML前置元数据和父文档引用；引用共享的
.claude/skills/REVIEW_DOCUMENT_STANDARDS.md
2.12026-02-09添加模式4：审查模式，用于仅验证分析并提供可视化分数指标；添加模式5：修复模式，用于带备份和内容保留的自动修复；元素ID迁移（PO-XXX→PRD.NN.07.SS, FF-XXX→PRD.NN.01.SS, AC-XXX→PRD.NN.06.SS, US-XXX→PRD.NN.08.SS）
1.32026-02-08集成quality-advisor技能，在阶段3（PRD生成）提供实时质量反馈
1.22026-02-08添加阶段5：最终内容审查，包含链接完整性、阈值一致性、BRD对齐和占位符检测检查
1.12026-02-08添加技能依赖，集成doc-prd和doc-prd-validator技能
1.02026-02-08初始技能创建，包含7步工作流