workflow-optimizer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

workflow-optimizer

工作流优化器

Purpose

用途

Guide users through the SDD workflow by determining current position, recommending next steps, identifying parallel work opportunities, and tracking progress.

Problem Solved: Users must manually determine next steps in the 15-layer SDD workflow, leading to workflow friction, missed dependencies, and inefficient sequencing.

Solution: Analyze completed artifacts, determine workflow position, and provide prioritized recommendations for next steps with clear rationale.

通过确定当前位置、推荐下一步操作、识别并行工作机会并跟踪进度，引导用户完成SDD工作流。

解决的问题：用户必须手动确定15层SDD工作流中的下一步操作，这会导致工作流受阻、遗漏依赖关系以及顺序安排低效。

解决方案：分析已完成的工件，确定工作流位置，并提供带有清晰理由的优先级下一步操作建议。

When to Use This Skill

何时使用此技能

Use workflow-optimizer when:

Completed an artifact and need guidance on next steps
Starting documentation and need workflow overview
Want to identify parallel work opportunities
Need progress report on documentation completion
Unsure which artifacts to create next

Do NOT use when:

Need skill recommendation for specific task (use skill-recommender)
Need project context (use context-analyzer)
Validating artifacts (use trace-check or quality-advisor)

在以下场景使用workflow-optimizer：

完成一个工件后，需要下一步操作指导
开始文档创作时，需要工作流概览
想要识别并行工作机会
需要文档完成进度报告
不确定接下来要创建哪些工件

请勿在以下场景使用：

需要针对特定任务的技能推荐（使用skill-recommender）
需要项目上下文信息（使用context-analyzer）
验证工件（使用trace-check或quality-advisor）

Skill Inputs

技能输入

Input	Type	Required	Description
project_root	string	Yes	Root path of project to analyze
completed_artifact	string	No	ID of just-completed artifact (e.g., PRD-00)
focus_area	string	No	Optional filter: "core-workflow", "quality", "planning"

输入项	类型	是否必填	描述
project_root	string	是	待分析项目的根路径
completed_artifact	string	否	刚完成的工件ID（例如：PRD-00）
focus_area	string	否	可选筛选条件："core-workflow"、"quality"、"planning"

Skill Workflow

技能工作流

Step 1: Analyze Project State

步骤1：分析项目状态

Scan project to determine documentation status:

Artifact Discovery:

bash

undefined

扫描项目以确定文档状态：

工件发现：

bash

undefined

Discover all artifacts

find {project_root}/docs -name ".md" -o -name ".yaml" -o -name "*.feature"


**Status Extraction**:
Extract status from Document Control section:
- Draft
- In Review
- Approved
- Superseded
- Deprecated

**Project State Model**:
```yaml
project_state:
  scan_timestamp: 2025-11-29T14:30:00Z
  artifacts_by_type:
    BRD:
      total: 3
      approved: 2
      draft: 1
      latest: BRD-03
    PRD:
      total: 2
      approved: 1
      draft: 1
      latest: PRD-00
    EARS:
      total: 0
    # ... etc
  total_artifacts: 25
  approved_artifacts: 18
  draft_artifacts: 7

find {project_root}/docs -name ".md" -o -name ".yaml" -o -name "*.feature"


**状态提取**：
从文档控制部分提取状态：
- Draft（草稿）
- In Review（审核中）
- Approved（已批准）
- Superseded（已取代）
- Deprecated（已废弃）

**项目状态模型**：
```yaml
project_state:
  scan_timestamp: 2025-11-29T14:30:00Z
  artifacts_by_type:
    BRD:
      total: 3
      approved: 2
      draft: 1
      latest: BRD-03
    PRD:
      total: 2
      approved: 1
      draft: 1
      latest: PRD-00
    EARS:
      total: 0
    # ... etc
  total_artifacts: 25
  approved_artifacts: 18
  draft_artifacts: 7

Step 2: Determine Workflow Position

步骤2：确定工作流位置

Map artifacts to SDD workflow layers:

Layer Definition:

yaml

workflow_layers:
  layer_1:
    type: BRD
    name: Business Requirements
    prerequisite: null
    description: "Business objectives and stakeholder needs"

  layer_2:
    type: PRD
    name: Product Requirements
    prerequisite: BRD
    description: "Product features and user needs"

  layer_3:
    type: EARS
    name: Formal Requirements
    prerequisite: PRD
    description: "WHEN-THE-SHALL formal requirements"

  layer_4:
    type: BDD
    name: Behavior Tests
    prerequisite: EARS
    description: "Gherkin acceptance scenarios"

  layer_5:
    type: ADR
    name: Architecture Decisions
    prerequisite: BDD
    description: "Technical decision records"

  layer_6:
    type: SYS
    name: System Requirements
    prerequisite: ADR
    description: "Technical system specifications"

  layer_7:
    type: REQ
    name: Atomic Requirements
    prerequisite: SYS
    description: "Detailed atomic requirements"

  layer_8:
    type: IMPL
    name: Implementation Plan
    prerequisite: REQ
    optional: true
    description: "WHO/WHEN project management"

  layer_9:
    type: CTR
    name: Interface Contracts
    prerequisite: [IMPL, REQ]
    optional: true
    description: "API contracts and schemas"

  layer_10:
    type: SPEC
    name: Technical Specifications
    prerequisite: REQ
    description: "YAML implementation specs"

  layer_11:
    type: TASKS
    name: Implementation Tasks
    prerequisite: SPEC
    description: "Code generation task lists - flows to Code layer"

Position Calculation:

yaml

workflow_position:
  completed_layers: [1, 2]  # BRD, PRD done
  in_progress_layers: [3]   # EARS in progress
  blocked_layers: [4, 5, 6, 7, 10, 11]  # Waiting on prerequisites
  ready_layers: [3]         # Can start now
  optional_ready: [8, 9]    # Optional, prereqs met

  current_position:
    layer: 3
    type: EARS
    status: in_progress

  progress_percentage: 18%  # 2 of 11 layers complete

将工件映射到SDD工作流层级：

层级定义：

yaml

workflow_layers:
  layer_1:
    type: BRD
    name: Business Requirements
    prerequisite: null
    description: "Business objectives and stakeholder needs"

  layer_2:
    type: PRD
    name: Product Requirements
    prerequisite: BRD
    description: "Product features and user needs"

  layer_3:
    type: EARS
    name: Formal Requirements
    prerequisite: PRD
    description: "WHEN-THE-SHALL formal requirements"

  layer_4:
    type: BDD
    name: Behavior Tests
    prerequisite: EARS
    description: "Gherkin acceptance scenarios"

  layer_5:
    type: ADR
    name: Architecture Decisions
    prerequisite: BDD
    description: "Technical decision records"

  layer_6:
    type: SYS
    name: System Requirements
    prerequisite: ADR
    description: "Technical system specifications"

  layer_7:
    type: REQ
    name: Atomic Requirements
    prerequisite: SYS
    description: "Detailed atomic requirements"

  layer_8:
    type: IMPL
    name: Implementation Plan
    prerequisite: REQ
    optional: true
    description: "WHO/WHEN project management"

  layer_9:
    type: CTR
    name: Interface Contracts
    prerequisite: [IMPL, REQ]
    optional: true
    description: "API contracts and schemas"

  layer_10:
    type: SPEC
    name: Technical Specifications
    prerequisite: REQ
    description: "YAML implementation specs"

  layer_11:
    type: TASKS
    name: Implementation Tasks
    prerequisite: SPEC
    description: "Code generation task lists - flows to Code layer"

位置计算：

yaml

workflow_position:
  completed_layers: [1, 2]  # BRD、PRD已完成
  in_progress_layers: [3]   # EARS进行中
  blocked_layers: [4, 5, 6, 7, 10, 11]  # 等待前置依赖
  ready_layers: [3]         # 可立即开始
  optional_ready: [8, 9]    # 可选，前置依赖已满足

  current_position:
    layer: 3
    type: EARS
    status: in_progress

  progress_percentage: 18%  # 11个层级中完成2个

Step 3: Identify Required Next Steps

步骤3：确定必需的下一步操作

Determine mandatory next artifacts:

Dependency Analysis:

yaml

dependency_graph:
  PRD-00:
    completed: true
    downstream_required:
      - EARS (Layer 3) - formal requirements
      - BDD (Layer 4) - test scenarios
    downstream_optional:
      - IMPL (Layer 8) - if complex project

  EARS (to be created):
    upstream_required:
      - PRD-00 ✓ (completed)
    will_enable:
      - BDD (Layer 4)
      - ADR (Layer 5)

Next Steps Priority:

Priority	Artifact	Rationale
P0	EARS	Required downstream from PRD, blocks BDD and ADR
P1	BDD	Can start once EARS begun, enables ADR
P2	ADR	Requires BDD completion

确定强制要求的下一个工件：

依赖分析：

yaml

dependency_graph:
  PRD-00:
    completed: true
    downstream_required:
      - EARS（第3层）- 正式需求
      - BDD（第4层）- 测试场景
    downstream_optional:
      - IMPL（第8层）- 若为复杂项目

  EARS（待创建）:
    upstream_required:
      - PRD-00 ✓（已完成）
    will_enable:
      - BDD（第4层）
      - ADR（第5层）

下一步操作优先级：

优先级	工件	理由
P0	EARS	PRD的下游必需工件，会阻塞BDD和ADR
P1	BDD	EARS启动后即可开始，为ADR提供支持
P2	ADR	需要完成BDD

Step 4: Identify Parallel Opportunities

步骤4：识别并行机会

Find work that can proceed in parallel:

Parallelization Rules:

yaml

parallel_opportunities:
  rule_1:
    name: "EARS and BDD overlap"
    condition: "EARS in progress"
    parallel_work: "BDD scenarios for completed EARS"
    benefit: "Faster progress through testing layer"

  rule_2:
    name: "Multiple feature tracks"
    condition: "Multiple BRDs exist"
    parallel_work: "PRD for each BRD"
    benefit: "Parallel feature development"

  rule_3:
    name: "ADR independence"
    condition: "Technical decisions needed"
    parallel_work: "ADRs can be written in parallel"
    benefit: "Architecture decisions don't block each other"

Parallel Work Output:

yaml

parallel_opportunities:
  can_parallelize:
    - track: "Feature A"
      current: EARS-01
      parallel: "Start BDD-01 scenarios for EARS-01 requirements"

    - track: "Feature B"
      current: PRD-00 complete
      parallel: "Start EARS-02 while Feature A progresses"

  blocked_parallelization:
    - item: "SPEC creation"
      blocker: "REQ layer incomplete"
      unblock_by: "Complete REQ-01 through REQ-05"

找出可并行开展的工作：

并行化规则：

yaml

parallel_opportunities:
  rule_1:
    name: "EARS与BDD重叠"
    condition: "EARS进行中"
    parallel_work: "为已完成的EARS编写BDD场景"
    benefit: "加快测试层级的进度"

  rule_2:
    name: "多功能分支"
    condition: "存在多个BRD"
    parallel_work: "为每个BRD创建PRD"
    benefit: "并行功能开发"

  rule_3:
    name: "ADR独立性"
    condition: "需要技术决策"
    parallel_work: "可并行编写ADR"
    benefit: "架构决策互不阻塞"

并行工作输出：

yaml

parallel_opportunities:
  can_parallelize:
    - track: "Feature A"
      current: EARS-01
      parallel: "为EARS-01的需求启动BDD-01场景编写"

    - track: "Feature B"
      current: PRD-00已完成
      parallel: "在Feature A推进EARS/BDD的同时，启动EARS-02"

  blocked_parallelization:
    - item: "SPEC创建"
      blocker: "REQ层级未完成"
      unblock_by: "完成REQ-01至REQ-05"

Step 5: Calculate Progress Metrics

步骤5：计算进度指标

Generate progress report:

Progress Metrics:

yaml

progress_report:
  overall:
    layers_complete: 2
    total_layers: 12
    percentage: 17%

  by_layer:
    - layer: 1 (BRD)
      status: complete
      artifacts: 3
      approved: 2

    - layer: 2 (PRD)
      status: complete
      artifacts: 2
      approved: 1

    - layer: 3 (EARS)
      status: in_progress
      artifacts: 0
      target: 3 (based on PRD features)

    - layer: 4 (BDD)
      status: blocked
      blocker: "EARS incomplete"

  estimated_remaining:
    artifacts: 25
    layers: 10

  critical_path:
    - EARS (blocks BDD)
    - BDD (blocks ADR)
    - REQ (blocks SPEC)
    - SPEC (blocks TASKS)

生成进度报告：

进度指标：

yaml

progress_report:
  overall:
    layers_complete: 2
    total_layers: 12
    percentage: 17%

  by_layer:
    - layer: 1 (BRD)
      status: complete
      artifacts: 3
      approved: 2

    - layer: 2 (PRD)
      status: complete
      artifacts: 2
      approved: 1

    - layer: 3 (EARS)
      status: in_progress
      artifacts: 0
      target: 3（基于PRD功能）

    - layer: 4 (BDD)
      status: blocked
      blocker: "EARS未完成"

  estimated_remaining:
    artifacts: 25
    layers: 10

  critical_path:
    - EARS（阻塞BDD）
    - BDD（阻塞ADR）
    - REQ（阻塞SPEC）
    - SPEC（阻塞TASKS）

Step 6: Generate Recommendations

步骤6：生成建议

Provide actionable next-step guidance:

Recommendation Format:

yaml

recommendations:
  context:
    completed_artifact: PRD-00
    workflow_position: Layer 2 complete
    progress: 17%

  next_steps:
    - priority: P0
      action: "Create EARS document"
      artifact_type: EARS
      skill: doc-ears
      rationale: "Required downstream from PRD-00. EARS formalizes product features into WHEN-THE-SHALL requirements."
      estimated_effort: "Medium (2-4 hours)"
      blocks: [BDD, ADR]

    - priority: P1
      action: "Start BDD scenarios"
      artifact_type: BDD
      skill: doc-bdd
      rationale: "Can begin once EARS started. Write scenarios for completed requirements."
      estimated_effort: "Medium (2-4 hours)"
      parallel_with: EARS

    - priority: P2
      action: "Consider ADR for key decisions"
      artifact_type: ADR
      skill: doc-adr
      rationale: "If architectural decisions needed, document early. Requires BDD completion."
      estimated_effort: "Low-Medium (1-3 hours)"
      condition: "After BDD progress"

  parallel_opportunities:
    - "Feature B: Start PRD-03 while Feature A progresses through EARS/BDD"
    - "Technical: Draft ADRs for known architecture decisions"

  blocked_items:
    - item: "SPEC creation"
      reason: "Requires REQ completion (Layer 7)"
      unblock_path: "Complete layers 3-7 first"

  workflow_guidance:
    current_focus: "EARS creation for PRD-00 features"
    short_term: "Complete EARS → BDD → ADR sequence"
    medium_term: "Progress through SYS → REQ → SPEC"

  progress_summary:
    completed: "BRD-01, BRD-02, BRD-03, PRD-01, PRD-00"
    in_progress: "None"
    next_milestone: "Complete Layer 3 (EARS)"
    overall: "17% complete (2/12 layers)"

提供可执行的下一步操作指导：

建议格式：

yaml

recommendations:
  context:
    completed_artifact: PRD-00
    workflow_position: 第2层已完成
    progress: 17%

  next_steps:
    - priority: P0
      action: "创建EARS文档"
      artifact_type: EARS
      skill: doc-ears
      rationale: "PRD-00的下游必需工件。EARS将产品功能正式化为WHEN-THE-SHALL格式的需求。"
      estimated_effort: "中等（2-4小时）"
      blocks: [BDD, ADR]

    - priority: P1
      action: "启动BDD场景编写"
      artifact_type: BDD
      skill: doc-bdd
      rationale: "EARS启动后即可开始。为已完成的需求编写场景。"
      estimated_effort: "中等（2-4小时）"
      parallel_with: EARS

    - priority: P2
      action: "考虑为关键决策创建ADR"
      artifact_type: ADR
      skill: doc-adr
      rationale: "若需要架构决策，尽早文档化。需完成BDD。"
      estimated_effort: "低-中等（1-3小时）"
      condition: "BDD取得进展后"

  parallel_opportunities:
    - "Feature B：在Feature A推进EARS/BDD的同时，启动PRD-03"
    - "技术层面：为已知的架构决策起草ADR"

  blocked_items:
    - item: "SPEC创建"
      reason: "需要完成REQ（第7层）"
      unblock_path: "先完成第3-7层"

  workflow_guidance:
    current_focus: "为PRD-00的功能创建EARS"
    short_term: "完成EARS → BDD → ADR流程"
    medium_term: "推进SYS → REQ → SPEC"

  progress_summary:
    completed: "BRD-01、BRD-02、BRD-03、PRD-01、PRD-00"
    in_progress: "无"
    next_milestone: "完成第3层（EARS）"
    overall: "完成17%（12个层级中完成2个）"

Example Usage

使用示例

Example 1: Post-PRD Guidance

示例1：PRD完成后的指导

User Request: "I just finished PRD-00, what should I do next?"

Workflow Recommendations:

yaml

completed: PRD-00
position: Layer 2 complete

next_steps:
  1. Create EARS-01 (P0)
     - Formalize PRD-00 features into WHEN-THE-SHALL requirements
     - Run: /skill doc-ears

  2. Start BDD scenarios (P1)
     - Can begin once EARS requirements defined
     - Run: /skill doc-bdd

parallel_opportunity:
  "If other BRDs exist, you can create their PRDs in parallel"

progress: "17% → 25% after EARS completion"

用户请求："我刚完成PRD-00，接下来该做什么？"

工作流建议：

yaml

completed: PRD-00
position: 第2层已完成

next_steps:
  1. 创建EARS-01（P0）
     - 将PRD-00的功能正式化为WHEN-THE-SHALL格式的需求
     - 执行：/skill doc-ears

  2. 启动BDD场景编写（P1）
     - EARS需求定义完成后即可开始
     - 执行：/skill doc-bdd

parallel_opportunity:
  "若存在其他BRD，可并行创建其对应的PRD"

progress: "17% → 完成EARS后达到25%"

Example 2: Project Overview

示例2：项目概览

User Request: "Where am I in the documentation workflow?"

Workflow Status:

yaml

project_status:
  completed_layers:
    - Layer 1 (BRD): 3 documents ✓
    - Layer 2 (PRD): 2 documents ✓

  in_progress:
    - Layer 3 (EARS): 0 documents, target 5

  blocked:
    - Layers 4-11: Waiting on upstream completion

  progress: 18%

  critical_path:
    EARS → BDD → ADR → SYS → REQ → SPEC → TASKS

  recommended_focus:
    "Complete EARS layer to unblock BDD and ADR"

用户请求："我在文档工作流中处于什么位置？"

工作流状态：

yaml

project_status:
  completed_layers:
    - 第1层（BRD）：3个文档 ✓
    - 第2层（PRD）：2个文档 ✓

  in_progress:
    - 第3层（EARS）：0个文档，目标5个

  blocked:
    - 第4-11层：等待上游完成

  progress: 18%

  critical_path:
    EARS → BDD → ADR → SYS → REQ → SPEC → TASKS

  recommended_focus:
    "完成EARS层级以解除BDD和ADR的阻塞"

Example 3: Parallel Work Identification

示例3：并行工作识别

User Request: "What can I work on in parallel?"

Parallel Opportunities:

yaml

current_tracks:
  track_a:
    name: "Core Platform"
    position: EARS creation
    next: BDD scenarios

  track_b:
    name: "Partner Integration"
    position: BRD complete
    next: PRD creation (independent of Track A)

parallel_work:
  - "Track B PRD can proceed while Track A completes EARS"
  - "ADRs for known decisions can be drafted early"
  - "BDD scenarios can start once first EARS requirements defined"

sequential_requirements:
  - "SPEC requires REQ completion - no parallel path"
  - "TASKS requires SPEC - sequential"

用户请求："我可以并行开展哪些工作？"

并行机会：

yaml

current_tracks:
  track_a:
    name: "Core Platform"
    position: EARS创建中
    next: BDD场景编写

  track_b:
    name: "Partner Integration"
    position: BRD已完成
    next: 创建PRD（独立于Track A）

parallel_work:
  - "Track B的PRD可在Track A完成EARS的同时推进"
  - "可为已知决策起草ADR"
  - "首个EARS需求定义完成后即可启动BDD场景编写"

sequential_requirements:
  - "SPEC需要REQ完成 - 无并行路径"
  - "TASKS需要SPEC - 按顺序执行"

Integration with Other Skills

与其他技能的集成

Integration	Description
context-analyzer	Provides artifact inventory and traceability data
skill-recommender	Receives workflow position for better skill suggestions
doc-flow	Can be invoked by doc-flow for workflow orchestration
project-mngt	Shares planning concepts (MVP, phases)

集成对象	描述
context-analyzer	提供工件清单和可追溯性数据
skill-recommender	接收工作流位置信息以优化技能建议
doc-flow	可被doc-flow调用以实现工作流编排
project-mngt	共享规划概念（MVP、阶段）

Quality Gates

质量门控

Definition of Done

完成定义

Performance Targets

性能指标

Metric	Target
Analysis latency	<1s for 50 artifacts
Recommendation generation	<500ms
Progress calculation	<200ms

指标	目标
分析延迟	50个工件时<1秒
建议生成时间	<500毫秒
进度计算时间	<200毫秒

Traceability

可追溯性

Required Tags:

@prd: PRD.000.004
@adr: ADR-000

必需标签：

@prd: PRD.000.004
@adr: ADR-000

Upstream Sources

上游来源

Source	Type	Reference
PRD-00	Product Requirements	PRD-00
ADR-000	Architecture Decision	ADR-000

来源	类型	参考
PRD-00	产品需求	PRD-00
ADR-000	架构决策	ADR-000

Downstream Artifacts

下游工件

Artifact	Type	Reference
doc-flow	Skill Consumer	Workflow orchestration
project-mngt	Skill Consumer	Release planning integration

工件	类型	参考
doc-flow	技能使用者	工作流编排
project-mngt	技能使用者	发布规划集成

Version Information

版本信息

Version: 1.0.0 Created: 2025-11-29 Status: Active Author: AI Dev Flow Framework Team

版本：1.0.0 创建时间：2025-11-29 状态：活跃作者：AI Dev Flow框架团队