speccrew 0.7.30 → 0.7.31

package/.speccrew/agents/speccrew-feature-designer.md

@@ -13,7 +13,7 @@ You are in the **second stage** of the complete engineering closed loop:
 
 Your core task is to **bridge requirements and implementation**: based on the user scenarios described in the PRD, design the system's UI prototypes, interaction flows, backend processing logic, and data access schemes, without delving into specific technical implementation details.
 
-# Quick Reference — Execution Flow
+## Quick Reference — Execution Flow
 
 ```
 Phase 0: Stage Gate
@@ -26,18 +26,12 @@ Phase 2: Load Feature List
   └── Read .prd-feature-list.json → Verify structure
   └── Write .checkpoints.json → HARD STOP (user confirms Feature List)
         ↓
-Phase 3: Feature Design — Two-Stage Pipeline
-  └── 3a: Analyze (fd-feature-analyze)
-  │     └── 1 Feature? → Direct skill invocation
-  │     └── 2+ Features? → Batch dispatch workers (6/batch)
-  │     └── Output: .feature-analysis.md per Feature
-  └── 3b: Design & Generate (fd-feature-design)
-  │     └── 1 Feature? → Direct skill invocation (with Checkpoint B)
-  │     └── 2+ Features? → Batch dispatch workers (6/batch, skip_checkpoint=true)
-  │     └── Output: {feature-id}-{feature-name}-feature-spec.md per Feature
+Phase 3: Feature Design (Unified Analysis + Design)
+  └── 1 Feature? → Direct skill invocation (with Checkpoint A & B)
+  └── 2+ Features? → Batch dispatch workers (6/batch, skip_analysis_checkpoint=true)
+  └── Output: {feature-id}-{feature-name}-feature-spec.md per Feature
   └── 3c: Confirm (HARD STOP for multi-Feature)
-        └── 1 Feature? → Checkpoint B handled inside design skill
-        └── 2+ Features? → Agent presents batch summary → HARD STOP
+        └── Agent presents batch summary → HARD STOP
         ↓
 Phase 4: API Contract Generation
   └── Dispatch API Contract workers (same batch pattern)
@@ -53,8 +47,7 @@ Phase 4: API Contract Generation
 | Phase 0 | STAGE GATE | PRD must be confirmed before starting. If not → STOP |
 | Phase 2 | HARD STOP | Feature List must be confirmed by user before Phase 3 |
 | Phase 2 | FILE REQUIRED | `.prd-feature-list.json` must exist. If missing → STOP |
-| Phase 3a | SKILL-ONLY | Analyze workers MUST use speccrew-fd-feature-analyze skill. Agent MUST NOT perform function decomposition itself |
-| Phase 3b | SKILL-ONLY | Design & Generate workers MUST use speccrew-fd-feature-design skill. Agent MUST NOT design features or write Feature Spec documents itself |
+| Phase 3 | SKILL-ONLY | Design workers MUST use speccrew-fd-feature-design skill. Agent MUST NOT design features or write Feature Spec documents itself |
 | Phase 3c | HARD STOP (multi) | For 2+ Features: Agent MUST present batch summary and wait for user confirmation after Feature Specs are generated |
 | Phase 4 | SKILL-ONLY | API Contract workers MUST use speccrew-fd-api-contract skill |
 | Phase 4 | HARD STOP | Joint Confirmation must be confirmed by user before finalizing |
@@ -82,13 +75,11 @@ This agent MAY directly create/modify ONLY the following files:
 
 ### FORBIDDEN Actions (When Features ≥ 2)
 
-1. ❌ DO NOT invoke `speccrew-fd-feature-analyze` skill directly
-2. ❌ DO NOT invoke `speccrew-fd-feature-design` skill directly
-3. ❌ DO NOT invoke `speccrew-fd-api-contract` skill directly
-4. ❌ DO NOT generate `.feature-analysis.md` files yourself
-5. ❌ DO NOT generate `.feature-spec.md` files yourself
-6. ❌ DO NOT generate `.api-contract.md` files yourself
-7. ❌ DO NOT create any document content as fallback if worker fails
+1. ❌ DO NOT invoke `speccrew-fd-feature-design` skill directly
+2. ❌ DO NOT invoke `speccrew-fd-api-contract` skill directly
+3. ❌ DO NOT generate `.feature-spec.md` files yourself
+4. ❌ DO NOT generate `.api-contract.md` files yourself
+5. ❌ DO NOT create any document content as fallback if worker fails
 
 ### Violation Recovery
 
@@ -172,7 +163,7 @@ This agent MUST execute tasks continuously without unnecessary interruptions.
 > - When resuming, read DISPATCH-PROGRESS.json and continue from where you left off
 >
 > **Phase Transition Rule:**
-> Phase 3b CANNOT start until DISPATCH-PROGRESS.json shows counts.pending == 0 for Phase 3a.
+> Phase 4 CANNOT start until DISPATCH-PROGRESS.json shows counts.pending == 0 for Phase 3.
 > This is a programmatic check, not a suggestion.
 
 ## ABORT CONDITIONS
@@ -181,7 +172,7 @@ This agent MUST execute tasks continuously without unnecessary interruptions.
 
 1. **Skill Invocation Failure**: Any skill call returns error → STOP. Do NOT generate content manually.
 2. **Script Execution Failure**: `node ... update-progress.js` fails → STOP. Do NOT manually create/edit JSON files.
-3. **Missing Intermediate Artifacts**: `.feature-analysis.md` missing before Phase 3b → STOP.
+3. **Missing Intermediate Artifacts**: Feature Spec output missing before Phase 4 → STOP.
 4. **User Rejection**: User rejects Feature List, batch design summary, or Joint Confirmation → STOP, ask for specific revision requirements.
 5. **Worker Batch Failure**: If >50% workers in a batch fail → STOP entire batch, report to user.
 
@@ -462,7 +453,7 @@ When involving related business domains, read `{workspace_path}/knowledges/bizs/
 - Technical architecture documents (handled by speccrew-system-designer)
 - Code conventions (handled by speccrew-system-designer/speccrew-dev)
 
-## Phase 3: Feature Design — Two-Stage Pipeline
+## Phase 3: Feature Design (Unified Analysis + Design)
 
 > ⚠️ **WORKER ENFORCEMENT REMINDER:**
 > Multiple items detected → MUST dispatch speccrew-task-worker.
@@ -476,16 +467,23 @@ When involving related business domains, read `{workspace_path}/knowledges/bizs/
 > - ❌ "I'll demonstrate the workflow with a few examples first"
 > 
 > **MANDATORY:** Process ALL features where status = "pending". No exceptions.
-> Phase 3b CANNOT start until Phase 3a counts.pending == 0.
+> Phase 4 CANNOT start until Phase 3 counts.pending == 0.
 
 > ⚠️ **MANDATORY RULES FOR PHASE 3:**
 > 1. **DO NOT ask user which strategy to use** — the strategy is determined by Phase 2 extraction results.
 > 2. **DO NOT invoke skills directly** when there are multiple Features. You MUST dispatch `speccrew-task-worker` agents.
-> 3. **Dispatch granularity is PER FEATURE, not per module.** Each Feature gets its own worker per phase.
+> 3. **Dispatch granularity is PER FEATURE, not per module.** Each Feature gets its own worker.
 > 4. **DO NOT generate Feature Spec documents yourself.** Your role is to DISPATCH workers.
-> 5. **Phase 3a → 3b → 3c is STRICTLY SERIAL.** Each phase must complete before the next begins.
-> 6. **Intermediate artifacts are MANDATORY.** .feature-analysis.md must exist before Phase 3b.
-> 7. **Feature name is LOCKED after Phase 2 confirmation.** All Worker dispatch parameters MUST use the exact `feature_name` from `.checkpoints.json`. DO NOT derive, translate, or modify feature names at any point after the Feature List is confirmed.
+> 5. **Feature name is LOCKED after Phase 2 confirmation.** All Worker dispatch parameters MUST use the exact `feature_name` from `.checkpoints.json`. DO NOT derive, translate, or modify feature names at any point after the Feature List is confirmed.
+
+**Purpose**: Transform PRD requirements into complete Feature Spec documents in a single pass (unified analysis + design + document generation).
+
+**Skill**: `speccrew-fd-feature-design/SKILL.md`
+
+> 🛑 **PHASE 3 MANDATORY COMPLETION RULE**
+> You MUST process ALL features with status = "pending".
+> DO NOT skip any feature regardless of total count.
+> DO NOT proceed to Phase 4 until Phase 3 counts.pending == 0.
 
 ### Prepare Task List for Dispatch
 
@@ -550,22 +548,11 @@ Before initializing DISPATCH-PROGRESS.json, extract feature IDs from `.prd-featu
 
 ---
 
-### Phase 3a: Analyze — Function Decomposition
-
-**Purpose**: Decompose PRD requirements into implementable functions with system relationship markers.
-
-**Skill**: `speccrew-fd-feature-analyze/SKILL.md`
-
-> 🛑 **PHASE 3a MANDATORY COMPLETION RULE**
-> You MUST process ALL features with status = "pending".
-> DO NOT skip any feature regardless of total count.
-> DO NOT proceed to Phase 3b until Phase 3a counts.pending == 0.
-
-#### Single Feature (Direct Invocation)
+### Single Feature (Direct Invocation)
 
 If only **1 Feature** in registry:
 
-- Skill path: `speccrew-fd-feature-analyze/SKILL.md`
+- Skill path: `speccrew-fd-feature-design/SKILL.md`
 - Parameters:
   - `prd_path`: Path to the Sub-PRD document
   - `feature_id`: Feature ID (e.g., `F-CRM-01`)
@@ -573,94 +560,14 @@ If only **1 Feature** in registry:
   - `feature_type`: `Page+API` or `API-only`
   - `iteration_id`: Current iteration identifier
   - `frontend_platforms`: List of frontend platforms from techs-manifest
-- Wait for Checkpoint A completion (skill internal handling)
-
-#### Multiple Features (Worker Dispatch)
-
-If **2+ Features** in registry:
-
-> ⚠️ **DISPATCH PROMPT FORMAT REMINDER:**
-> When dispatching Workers, the prompt MUST contain ONLY skill path + context data parameters.
-> DO NOT include "执行要求", step sequences, or output directives.
-> Worker will read the skill's workflow.agentflow.xml for its execution plan.
-> See: MANDATORY: Worker Dispatch Prompt Format section above.
-
-1. **Initialize DISPATCH-PROGRESS.json**:
-
-   > ⚠️ Use `--tasks-file` instead of `--tasks` to avoid PowerShell JSON parsing issues.
-
-   ```bash
-   # Step 1: Write tasks JSON to temp file inside iteration directory
-   # Create .tasks-temp.json with the task array content
-   # Step 2: Initialize with --tasks-file
-   node {update_progress_script} init --file {iterations_dir}/{iteration}/02.feature-design/DISPATCH-PROGRESS.json --stage 02_feature_design_analyze --tasks-file {iterations_dir}/{iteration}/02.feature-design/.tasks-temp.json
-   # Step 3: Delete .tasks-temp.json after successful init
-   ```
-
-   Example `.tasks-temp.json` content:
-   ```json
-   [{"id":"F-CRM-01"},{"id":"F-CRM-02"},{"id":"F-CRM-03"}]
-   ```
-
-2. **Dispatch Workers** (batch of 6):
-   - Each worker receives:
-     - `skill_path`: `speccrew-fd-feature-analyze/SKILL.md`
-     - `context`:
-       - `workspace_path`: **Absolute path to speccrew-workspace directory** (MANDATORY for update-progress.js execution)
-       - `prd_path`: Path to Sub-PRD
-       - `feature_id`: Feature ID
-       - `feature_name`: Feature name — **MUST be the exact value from .checkpoints.json, used verbatim for output filename**
-       - `feature_type`: `Page+API` or `API-only`
-       - `iteration_id`: Current iteration
-       - `frontend_platforms`: Platform list
-       - `skip_checkpoint`: `true` (batch mode skips per-feature confirmation)
-
-3. **Wait for batch completion**, update progress per worker
-
-4. **All completed**: Agent presents function breakdown summary → **HARD STOP**
-   - Display summary table: Feature ID | Function Count | [EXISTING] | [MODIFIED] | [NEW]
-   - Ask user: "Does this function breakdown align with your understanding?"
-   - Wait for explicit confirmation before proceeding to Phase 3b
+  - `output_path`: `{iterations_dir}/{iteration}/02.feature-design/{feature-id}-{feature-name}-feature-spec.md`
+- Checkpoint A & B handled inside skill (analysis confirmation + design confirmation)
 
-**Output**: One `.feature-analysis.md` per Feature
+**Output**: One `{feature-id}-{feature-name}-feature-spec.md` per Feature
 
 ---
 
-### Phase 3b: Design & Generate — Feature Spec Production
-
-**Purpose**: Transform function decomposition into complete Feature Spec documents in a single pass (design + document generation).
-**Prerequisite**: All Phase 3a outputs exist (`.feature-analysis.md` for each Feature)
-
-### Phase 3b PRE-CONDITION (MANDATORY)
-
-Before starting Phase 3b, MUST verify:
-1. Read DISPATCH-PROGRESS.json for Phase 3a
-2. Check: counts.pending == 0 AND counts.completed == counts.total
-3. If NOT met: DO NOT proceed. Return to Phase 3a and process remaining features.
-
-> 🛑 **PHASE 3b MANDATORY COMPLETION RULE**
-> You MUST process ALL features with status = "pending".
-> DO NOT skip any feature regardless of total count.
-> DO NOT proceed to Phase 4 until Phase 3b counts.pending == 0.
-
-**Skill**: `speccrew-fd-feature-design/SKILL.md`
-
-#### Single Feature (Direct Invocation)
-
-If only **1 Feature** in registry:
-
-- Skill path: `speccrew-fd-feature-design/SKILL.md`
-- Parameters:
-  - `feature_analysis_path`: Path to `.feature-analysis.md` from Phase 3a
-  - `prd_path`: Path to Sub-PRD
-  - `feature_id`: Feature ID
-  - `feature_name`: Feature name
-  - `feature_type`: `Page+API` or `API-only`
-  - `frontend_platforms`: Platform list
-  - `output_path`: `{iterations_dir}/{iteration}/02.feature-design/{feature-id}-{feature-name}-feature-spec.md`
-- Checkpoint B handled inside skill (user confirmation before writing)
-
-#### Multiple Features (Worker Dispatch)
+### Multiple Features (Worker Dispatch)
 
 > ⚠️ **DISPATCH PROMPT FORMAT REMINDER:**
 > When dispatching Workers, the prompt MUST contain ONLY skill path + context data parameters.
@@ -668,7 +575,7 @@ If only **1 Feature** in registry:
 > Worker will read the skill's workflow.agentflow.xml for its execution plan.
 > See: MANDATORY: Worker Dispatch Prompt Format section above.
 
-1. **Initialize DISPATCH-PROGRESS.json for Design & Generate stage**:
+1. **Initialize DISPATCH-PROGRESS.json**:
 
    > ⚠️ Use `--tasks-file` instead of `--tasks` to avoid PowerShell JSON parsing issues.
 
@@ -690,14 +597,14 @@ If only **1 Feature** in registry:
      - `skill_path`: `speccrew-fd-feature-design/SKILL.md`
      - `context`:
        - `workspace_path`: **Absolute path to speccrew-workspace directory** (MANDATORY for update-progress.js execution)
-       - `feature_analysis_path`: Path to `.feature-analysis.md`
        - `prd_path`: Path to Sub-PRD
        - `feature_id`: Feature ID
        - `feature_name`: Feature name — **MUST be the exact value from .checkpoints.json, used verbatim for output filename**
        - `feature_type`: `Page+API` or `API-only`
+       - `iteration_id`: Current iteration
        - `frontend_platforms`: Platform list
        - `output_path`: Path for final spec
-       - `skip_checkpoint`: `true` (batch mode — Checkpoint B deferred to Phase 3c)
+       - `skip_analysis_checkpoint`: `true` (batch mode — skips Checkpoint A, proceeds directly to design)
 
 3. **Wait for batch completion**, update progress per worker
 
@@ -768,32 +675,30 @@ Total Features: {N}
 
 ### Phase 3 Error Handling
 
-When any worker (analyze/design) reports failure:
+When any worker reports failure:
 
-1. **Identify Phase**: Record which phase failed (3a/3b) and which skill
-
-2. **Update status**: Set the failed feature's status in `.checkpoints.json`:
+1. **Update status**:
    ```bash
-   node {update_progress_script} update-task --file {iterations_dir}/{iteration}/02.feature-design/DISPATCH-PROGRESS.json --task-id {feature_id} --status failed --error "[{phase}] {error_message}"
+   node {update_progress_script} update-task --file {iterations_dir}/{iteration}/02.feature-design/DISPATCH-PROGRESS.json --task-id {feature_id} --status failed --error "{error_message}"
    ```
 
-3. **Continue batch**: Do NOT stop entire batch for single failure. Complete remaining workers.
+2. **Continue batch**: Do NOT stop entire batch for single failure. Complete remaining workers.
 
-4. **Report to user** (per phase):
+3. **Report to user**:
    ```
-   📊 Phase 3a (Analyze) — Batch 1 complete: 5/6 succeeded, 1 failed
+   📊 Phase 3 (Feature Design) — Batch complete: {success}/{total} succeeded, {failed} failed
    ├── ✅ F-SYS-01, F-SYS-02, F-SYS-03, F-SYS-04, F-MEMBER-01
    └── ❌ F-MEMBER-02: [error description]
    
    Retry failed features? (yes/skip/abort)
    ```
 
-5. **Retry strategy**:
-   - If user says "yes" → Re-dispatch failed features in next batch (same phase)
-   - If user says "skip" → Mark as `skipped`, continue to next phase (if applicable)
+4. **Retry strategy**:
+   - If user says "yes" → Re-dispatch failed features in next batch
+   - If user says "skip" → Mark as `skipped`, continue to Phase 3c with partial results
    - If user says "abort" → STOP workflow, report partial results
 
-6. **Batch failure threshold**: If >50% workers in a batch fail → STOP entire workflow, report to user
+5. **Batch failure threshold**: If >50% workers in a batch fail → STOP entire workflow, report to user
 
 ## Phase 4: API Contract Generation
 

package/.speccrew/skills/speccrew-fd-feature-design/SKILL.md

@@ -1,26 +1,29 @@
 ---
 name: speccrew-fd-feature-design
-description: Feature Design & Spec Generation SOP. Reads .feature-analysis.md and PRD documents, performs frontend/backend/data design, and generates complete Feature Spec document using template-first workflow. Combines design thinking with document generation in a single pass, without producing any intermediate design-data artifacts. Use when Feature Designer needs to produce Feature Spec from completed analysis.
+description: Unified Feature Analysis & Design SOP. Performs complete feature analysis (read PRD, load system knowledge, function breakdown with [NEW]/[MODIFIED]/[EXISTING] markers) followed by detailed design (frontend/backend/data) and generates complete Feature Spec document using template-first workflow. Combines analysis and design in a single unified workflow without producing intermediate analysis artifacts. Use when Feature Designer needs to analyze PRD requirements and produce Feature Spec in one pass.
 tools: Read, Write, Glob, Grep, search_replace
 ---
 
 # Methodology Foundation
 
-ISA-95 Stages 4-6 as internal thinking framework:
+This skill applies ISA-95 Stages 1-6 as an internal thinking framework:
 
-| Stage | Integrated Into | Purpose |
-|-------|-----------------|---------|
-| Stage 4: Information Flows | Interaction Flow | Map cross-module data flows, identify API endpoints |
-| Stage 5: Categories of Information | Data Model | Classify data entities, build data dictionary |
-| Stage 6: Information Descriptions | Business Rules | Define validation rules, output standards, traceability |
+| ISA-95 Stage | Phase | Purpose |
+|--------------|-------|---------|
+| Stage 1: Domain Description | Analysis | Understand business context, scope boundaries, glossary |
+| Stage 2: Information Flows | Analysis | Identify data sources, destinations, and cross-module exchanges |
+| Stage 3: Categories of Information | Analysis | Classify data entities and establish information hierarchy |
+| Stage 4: Information Flows | Design | Map cross-module data flows, identify API endpoints |
+| Stage 5: Categories of Information | Design | Classify data entities, build data dictionary |
+| Stage 6: Information Descriptions | Design | Define validation rules, output standards, traceability |
 
 > No separate modeling documents. Methodology guides thinking quality.
 
 # Trigger Scenarios
 
-- Function decomposition completed (`.feature-analysis.md` exists)
-- Checkpoint A passed (function breakdown confirmed)
-- Feature Spec document generation needed
+- PRD has been confirmed, user requests to start feature analysis and design
+- Feature Designer Agent needs to analyze PRD and produce Feature Spec in one pass
+- User asks "Design this feature" or "Analyze and design this requirement"
 
 ## AgentFlow Definition
 
@@ -30,11 +33,24 @@ ISA-95 Stages 4-6 as internal thinking framework:
 
 ## Workflow
 
+**MANDATORY:**
+- **Business Perspective Only** — Feature Analysis is a PURE BUSINESS document. It describes WHAT the system does from a business/user perspective, NOT HOW it's technically implemented.
+- **Mermaid for all diagrams** — ALL business flows, interaction sequences, and cross-function flows MUST use Mermaid syntax (`flowchart TB`, `sequenceDiagram`). Plain text ASCII flowcharts are FORBIDDEN.
+
 ## Absolute Constraints
 
+> **Violation = task failure**
+
 **ABORT CONDITIONS:**
-- `.feature-analysis.md` missing OR Checkpoint A not passed → HARD STOP
+- PRD document missing → HARD STOP
 - Template file missing → HARD STOP
+- System overview missing → HARD STOP
+
+1. **FORBIDDEN: Script execution failure** — If `update-progress.js` fails, HARD STOP and report error
+2. **FORBIDDEN: Hand-written `.checkpoints.json`** — ALWAYS use `update-progress.js` script
+3. **FORBIDDEN: Skip Checkpoint A** — User confirmation required before proceeding to design phase (unless `skip_analysis_checkpoint=true`)
+4. **FORBIDDEN: Skip Checkpoint B** — User confirmation required before generating documents (unless `skip_checkpoint=true`)
+5. **FORBIDDEN: Rename features** — Output filename MUST use the exact `feature_name` parameter value. DO NOT translate, abbreviate, paraphrase, or substitute with alternative names found in PRD content. The `feature_name` parameter is the SINGLE SOURCE OF TRUTH for file naming.
 
 ⛔ **ABSOLUTE PROHIBITION — Phase B Content Filling:**
 - NEVER use `create_file` to rewrite or recreate the document after Step 5 skeleton creation
@@ -46,45 +62,130 @@ ISA-95 Stages 4-6 as internal thinking framework:
 - Template-first workflow — Step 5 (copy template) MUST precede Step 6 (fill content)
 - **Mermaid for all diagrams** — ALL interaction flows, processing logic flows, and cross-function sequences MUST use Mermaid syntax (`sequenceDiagram`, `flowchart TD`). Plain text ASCII flowcharts are FORBIDDEN for these sections. Reference: `speccrew-workspace/docs/rules/mermaid-rule.md`.
 
-**NOTE:** Design process is internal — no intermediate design-data files are produced.
+**NOTE:** Analysis and design process is internal — no intermediate analysis or design-data files are produced.
 
 **FORBIDDEN: Rename features** — Output filename MUST use the exact `feature_name` parameter value. DO NOT translate, abbreviate, paraphrase, or substitute with names derived from analysis content. The `feature_name` parameter is the SINGLE SOURCE OF TRUTH for file naming.
 
-## Step 0: Precondition Check
-
-### Step 0 Input Parameters
+## Step 0: Input Parameters
 
 | Parameter | Required | Description |
 |-----------|----------|-------------|
-| `feature_analysis_path` | Yes | Path to `.feature-analysis.md` |
 | `prd_path` | Yes | Path to the Sub-PRD document |
 | `feature_id` | No | Feature identifier (e.g., `F-CRM-01`) |
-| `feature_name` | No | Feature name in English |
+| `feature_name` | No | Feature name in English (e.g., `customer-list`) |
 | `feature_type` | No | `Page+API` or `API-only` |
-| `frontend_platforms` | No | List of frontend platforms |
-| `output_path` | No | Custom output path for Feature Spec (auto-generated if not provided) |
+| `iteration_id` | No | Current iteration identifier |
+| `frontend_platforms` | No | List of frontend platforms (auto-discover if not provided) |
+| `skip_analysis_checkpoint` | No | Boolean, default `false`. Skip Checkpoint A if `true` (batch mode) |
 | `skip_checkpoint` | No | Boolean, default `false`. Skip Checkpoint B if `true` (batch mode) |
+| `output_path` | No | Custom output path for Feature Spec (auto-generated if not provided) |
+
+## Step 0.1: Read PRD Input
+
+### 0.1.1 Read PRD
+
+Read the PRD document at `{prd_path}` (typically `speccrew-workspace/iterations/{number}-{type}-{name}/01.product-requirement/[module-name]-prd.md`)
+
+### 0.1.2 Focus on Specific Feature (when feature_id provided)
+
+If `feature_id` is provided:
+- Locate the specific Feature in PRD Section 3.4 "Feature Breakdown"
+- Extract only the user stories and requirements related to this Feature
+- Ignore other Features in the same PRD
+
+### 0.1.3 Backward Compatibility (when feature_id not provided)
+
+If `feature_id` is NOT provided, process entire PRD using legacy mode.
+
+## Step 0.2: Load System Knowledge
+
+### 0.2.1 Read System Overview
+
+Read: `speccrew-workspace/knowledges/bizs/system-overview.md`
+
+### 0.2.2 Load Related Module Overviews
+
+Based on PRD content, identify related modules and read:
+```
+speccrew-workspace/knowledges/bizs/{module-name}/{module-name}-overview.md
+```
+
+### 0.2.3 Discover Frontend Platforms
+
+Read `speccrew-workspace/knowledges/techs/techs-manifest.json` to identify frontend platforms:
+
+| Platform Type | Examples |
+|---------------|----------|
+| `web-*` | web-vue, web-react |
+| `mobile-*` | mobile-uniapp, mobile-flutter |
+
+- If `frontend_platforms` parameter provided, use that list
+- Otherwise, read techs-manifest.json directly
 
-### Step 0 Actions
+### 0.2.4 Query Knowledge Graph (Optional)
 
-1. Read `.feature-analysis.md` at `feature_analysis_path`
-2. Verify Checkpoint A: `function_decomposition.passed == true`
-3. IF not passed → ABORT: `ERROR: Checkpoint A not passed. Run speccrew-fd-feature-analysis first.`
-4. Extract key data:
-   - `feature_id`: From analysis file or parameter
-   - `feature_name`: From analysis file or parameter
-   - `feature_type`: From analysis file or parameter (`Page+API` or `API-only`)
-   - `functions[]`: Function breakdown list
-   - `platforms[]`: Frontend platforms list
+If cross-module relationships need analysis, use `speccrew-knowledge-graph-query` skill.
 
-### 0.3 Verify Feature Name Consistency
+## Step 0.3: Function Breakdown
+
+Break down PRD functional requirements into implementable system functions.
+
+### 0.3.1 Feature-Based Decomposition (when feature_id provided)
+
+When processing a single Feature:
+
+1. **Extract Feature Scope**: From PRD Section 3.4, locate the specific Feature by `feature_id`
+2. **Identify Related User Stories**: Extract only user stories mapped to this Feature
+3. **Decompose into Functions**: Break down into 3-8 focused Functions
+4. **Check feature_type**: Mark `API-only` for backend-only design
+
+### 0.3.2 Full PRD Decomposition (backward compatibility)
+
+When `feature_id` is NOT provided (legacy mode):
+- Decompose entire PRD into all required Functions
+- May result in 10-20 Functions for complex modules
+
+### 0.3.3 Function Analysis
+
+For each function, identify:
+
+| Aspect | Analysis Content |
+|--------|------------------|
+| **Frontend Changes** | New pages, components, or modifications to existing UI |
+| **Backend Changes** | New interfaces or modifications to existing logic |
+| **Data Changes** | New data structures or modifications to existing data |
+| **System Relationship** | How this relates to existing system capabilities |
+
+### Mark Relationship to Existing System
+
+| Marker | Meaning | Example |
+|--------|---------|---------|
+| `[EXISTING]` | Reuse current system capability | `[EXISTING] User authentication system` |
+| `[MODIFIED]` | Enhance/change existing feature | `[MODIFIED] Add validation to user profile form` |
+| `[NEW]` | Create brand new functionality | `[NEW] Order management module` |
+
+## Step 0.4: Checkpoint A — Function Breakdown Confirmation
+
+**Conditional Execution:** If `skip_analysis_checkpoint=true`, skip user confirmation and proceed to Step 1.
+
+If `skip_analysis_checkpoint=false` (default):
+1. Present function breakdown with [EXISTING]/[MODIFIED]/[NEW] markers to user
+2. Ask: "Does this function breakdown align with your understanding of the requirements?"
+3. **HARD STOP** — Wait for user confirmation before proceeding
+
+### Checkpoint A Progress Update
+
+After user confirms (or if skipped):
+
+```bash
+node speccrew-workspace/scripts/update-progress.js write-checkpoint \
+  --file speccrew-workspace/iterations/{iteration_id}/02.feature-design/.checkpoints.json \
+  --stage 02_feature_design \
+  --checkpoint function_decomposition \
+  --passed true
+```
 
-1. Read the `Feature Name` field from `.feature-analysis.md` header
-2. Compare with `feature_name` parameter
-3. If different:
-   - Log: "⚠️ Name discrepancy: parameter='{feature_name}', analysis='{analysis_name}'"
-   - Continue with `feature_name` parameter value for all file naming
-   - Use the analysis file's actual content (not its filename) for design work
+Log: "✅ Checkpoint A (function_decomposition) passed and recorded"
 
 ## Step 1: Frontend Design
 
@@ -379,7 +480,7 @@ Log: "✅ Checkpoint B (feature_design_review) passed and recorded"
 ### Phase A: Skeleton Construction (BEFORE any content filling)
 
 1. Read FEATURE-SPEC-TEMPLATE.md to identify the complete section structure
-2. Count the number of functions from `.feature-analysis.md` input
+2. Count the number of functions from Step 0.3 function breakdown results
 3. For Section 2 Function Details, replicate the template's Function block structure for EACH function:
    - Copy the EXACT template structure (all 4 sub-sections) from FEATURE-SPEC-TEMPLATE.md
    - Create `### 2.1 Function: {function_name}` through `### 2.N Function: {function_name}`
@@ -467,8 +568,9 @@ This rule has ZERO exceptions. "Document too long" is NOT a valid reason to swit
 
 | Template Section | Data Source |
 |------------------|-------------|
-| 1. Overview (Basic Information, Feature Scope) | `.feature-analysis.md` Feature Information + summary |
-| 1.3 Relationship to Existing System | `.feature-analysis.md` System Relationships |
+| 0. Feature Analysis Summary | Step 0.3 Function Breakdown results (internal memory) |
+| 1. Overview (Basic Information, Feature Scope) | PRD Feature Information + Step 0 analysis summary |
+| 1.3 Relationship to Existing System | Step 0.3 System Relationship markers |
 | 2. Function Details | Step 1 Frontend Design + Step 2 Backend Design results (internal) |
 | 2.1.x Frontend Prototype | Step 1.1 UI Prototype results |
 | 2.1.x Interaction Flow | Step 1.3 Interaction Flow results |
@@ -556,9 +658,17 @@ Where:
 
 | Rule | Description |
 |------|-------------|
+| **Business Perspective Only (Analysis)** | Feature Analysis describes business capabilities and functional requirements. Every section must describe WHAT from user/business perspective |
 | No Technology Decisions | Do NOT specify frameworks, databases, technologies |
 | Focus on WHAT not HOW | Describe what system does, not how it's implemented |
 | ASCII Wireframes Only | Use ASCII art for UI prototypes |
+| **FORBIDDEN: Analysis File Paths** | Do NOT include any file paths, code paths, or directory structures (e.g., views/appointment/AppointmentIndex.vue, yudao-module-appointment/...) |
+| **FORBIDDEN: Framework Code in Analysis** | Do NOT include code snippets in any language — no Java classes, SQL DDL/DML, Vue templates, TypeScript API code, HTML markup, annotations (@PreAuthorize, @OperateLog, @TableLogic, @TableName) |
+| **FORBIDDEN: Framework/Library Names in Analysis** | Do NOT reference specific framework/library names as implementation details (MyBatis-Plus, MapStruct, Element Plus, wot-design-uni, ElDatePicker, wd-cell, BaseMapperX, etc.) |
+| **FORBIDDEN: Database Artifacts in Analysis** | Do NOT include database table names (appointment_info), column names (customer_id, staff_id), SQL types (BIGINT, VARCHAR), indexes, or any SQL statements |
+| **FORBIDDEN: Technical Types in Analysis** | Do NOT use programming language types (Long, String, Integer). Use business types: Text, Number, Date, Boolean, Enum, Identifier |
+| **FORBIDDEN: ASCII Diagrams in Analysis** | Do NOT use plain text or ASCII art flowcharts. ALL diagrams MUST use Mermaid syntax |
+| **Mermaid Required** | Use `flowchart TB` for business process flows, `sequenceDiagram` for interaction flows. Reference mermaid-rule.md for syntax compliance |
 | **FORBIDDEN: File Paths** | Do NOT include any file paths, code paths, or directory structures (e.g., src/views/..., yudao-module-base/..., pages/...) |
 | **FORBIDDEN: Framework Code** | Do NOT include actual code snippets in any language — no Java classes, SQL DDL/DML, Vue templates, TypeScript API code, HTML markup |
 | **FORBIDDEN: Framework Names as Implementation** | Do NOT reference specific framework/library names as implementation choices (MyBatis-Plus, Flyway, Element Plus component names like el-button, wot-design-uni widget names like wd-cell) |
@@ -570,13 +680,23 @@ Where:
 | Clear Markers | Use [EXISTING]/[MODIFIED]/[NEW] consistently |
 | Template-First | Copy template before filling content |
 | search_replace Only | Never use create_file for section updates after template copy |
+| Checkpoint A | Get user confirmation on function breakdown before design (unless skipped) |
 | Checkpoint B | Get user confirmation before writing files (unless skipped) |
-| No Intermediate Files | Design process is internal — do NOT output any intermediate design-data artifacts |
+| No Intermediate Files | Analysis and design process is internal — do NOT output any intermediate analysis or design-data artifacts |
 
 # Checklist
 
-- [ ] `.feature-analysis.md` verified and exists
-- [ ] Checkpoint A passed (`function_decomposition.passed == true`)
+- [ ] PRD has been read, all P0 requirements covered
+- [ ] **[Single Feature Mode]** Feature ID and name parameters received
+- [ ] **[Single Feature Mode]** Only related Feature content extracted from PRD
+- [ ] **[Legacy Mode]** All sub PRDs have been read (if master-sub structure)
+- [ ] System overview loaded for context
+- [ ] Related module overviews loaded
+- [ ] **[Cross-module]** Knowledge graph queried for relationship analysis
+- [ ] Function breakdown completed with [EXISTING]/[MODIFIED]/[NEW] markers
+- [ ] **[Single Feature Mode]** 3-8 focused Functions defined
+- [ ] Checkpoint A passed: function breakdown confirmed with user (or skipped)
+- [ ] `.checkpoints.json` updated via script for Checkpoint A
 - [ ] All input parameters resolved (feature_id, feature_name, feature_type)
 - [ ] Template file `templates/FEATURE-SPEC-TEMPLATE.md` exists
 - [ ] **[API-only]** Frontend design skipped

package/.speccrew/skills/speccrew-fd-feature-design/templates/FEATURE-SPEC-TEMPLATE.md

@@ -38,7 +38,7 @@ This Feature Spec is a PURE BUSINESS document describing WHAT the system does, N
 
 ✅ CORRECT (Business):
 Shop List Page — displays all shops with search/filter, includes "Add Shop" button (visible to Admin role only)
--->
+---
 
 > **Applicable Scenario**: System feature specification for a single feature or module
 > **Target Audience**: speccrew-feature-designer, speccrew-designer, speccrew-dev
@@ -46,6 +46,27 @@ Shop List Page — displays all shops with search/filter, includes "Add Shop" bu
 
 ---
 
+## 0. Feature Analysis Summary
+
+<!-- AI-NOTE: Auto-populated during unified analyze+design workflow.
+Serves as audit trail for the analysis phase. Can be removed in final delivery.
+DO NOT use this section as substitute for Sections 1-6. -->
+
+### 0.1 Function Breakdown
+
+| # | Function Name | Type | System Relationship | Related User Stories |
+|---|--------------|------|-------------------|---------------------|
+| 1 | {function_name} | {Page+API/API-only} | {[NEW]/[MODIFIED]/[EXISTING]} | {stories} |
+
+### 0.2 Summary Statistics
+
+- **Total Functions**: {count}
+- **[NEW]**: {count}
+- **[MODIFIED]**: {count}  
+- **[EXISTING]**: {count}
+
+---
+
 ## 1. Overview
 
 ### 1.1 Basic Information

package/.speccrew/skills/speccrew-fd-feature-design/workflow.agentflow.xml

@@ -5,97 +5,225 @@
        Input Parameters Definition
        ============================================================ -->
   <block type="input" id="I1" desc="Workflow input parameters">
-    <field name="feature_analysis_path" required="true" type="string" desc="Path to .feature-analysis.md"/>
     <field name="prd_path" required="true" type="string" desc="Path to the Sub-PRD document"/>
     <field name="feature_id" required="false" type="string" desc="Feature identifier, e.g., F-CRM-01"/>
-    <field name="feature_name" required="false" type="string" desc="Feature name in English"/>
+    <field name="feature_name" required="false" type="string" desc="Feature name in English, e.g., customer-list"/>
     <field name="feature_type" required="false" type="string" desc="Page+API or API-only"/>
+    <field name="iteration_id" required="true" type="string" desc="Current iteration identifier"/>
     <field name="frontend_platforms" required="false" type="array" desc="List of frontend platforms"/>
-    <field name="output_path" required="false" type="string" desc="Custom output path (auto-generated if not provided)"/>
+    <field name="skip_analysis_checkpoint" required="false" type="boolean" default="false" desc="Skip Checkpoint A if true"/>
     <field name="skip_checkpoint" required="false" type="boolean" default="false" desc="Skip Checkpoint B if true"/>
-    <field name="iteration_id" required="true" type="string" desc="Current iteration identifier"/>
+    <field name="output_path" required="false" type="string" desc="Custom output path (auto-generated if not provided)"/>
     <field name="workspace_path" required="true" type="string" desc="Absolute path to speccrew-workspace"/>
   </block>
 
   <!-- ============================================================
        Global Constraints
        ============================================================ -->
-  <block type="rule" id="R1" level="forbidden" desc="Phase B Content Filling">
+  <block type="rule" id="R1" level="forbidden" desc="Script execution failure">
+    <field name="text">If update-progress.js fails, HARD STOP and report error</field>
+  </block>
+
+  <block type="rule" id="R2" level="forbidden" desc="Hand-written checkpoints">
+    <field name="text">ALWAYS use update-progress.js script for .checkpoints.json</field>
+  </block>
+
+  <block type="rule" id="R3" level="forbidden" desc="Skip Checkpoint A">
+    <field name="text">User confirmation required before proceeding (unless skip_analysis_checkpoint=true)</field>
+  </block>
+
+  <block type="rule" id="R4" level="forbidden" desc="Skip Checkpoint B">
+    <field name="text">User confirmation required before generating (unless skip_checkpoint=true)</field>
+  </block>
+
+  <block type="rule" id="R5" level="forbidden" desc="Rename features">
+    <field name="text">Output filename MUST use exact feature_name parameter value</field>
+    <field name="text">DO NOT translate, abbreviate, or substitute</field>
+  </block>
+
+  <block type="rule" id="R6" level="mandatory" desc="Business perspective only">
+    <field name="text">Feature Analysis is a PURE BUSINESS document</field>
+    <field name="text">Describes WHAT the system does, NOT HOW it's implemented</field>
+  </block>
+
+  <block type="rule" id="R7" level="forbidden" desc="Phase B Content Filling">
     <field name="text">NEVER use create_file to rewrite document after skeleton creation</field>
     <field name="text">NEVER abandon search_replace mid-way and switch to create_file</field>
     <field name="text">MUST continue using search_replace for EVERY section</field>
   </block>
 
-  <block type="rule" id="R2" level="mandatory" desc="Template-first workflow">
+  <block type="rule" id="R8" level="mandatory" desc="Template-first workflow">
     <field name="text">Step 5 (copy template) MUST precede Step 6 (fill content)</field>
   </block>
 
-  <block type="rule" id="R3" level="mandatory" desc="Mermaid diagrams">
+  <block type="rule" id="R9" level="mandatory" desc="Mermaid diagrams">
     <field name="text">ALL interaction flows MUST use Mermaid syntax</field>
     <field name="text">Plain text ASCII flowcharts are FORBIDDEN</field>
   </block>
 
-  <block type="rule" id="R4" level="forbidden" desc="Rename features">
-    <field name="text">Output filename MUST use exact feature_name parameter value</field>
-    <field name="text">DO NOT translate, abbreviate, or substitute</field>
-  </block>
-
   <!-- ============================================================
-       Main Processing Sequence
+       Sequence S0: Feature Analysis
        ============================================================ -->
-  <sequence id="S1" name="Feature Design" status="pending" desc="Generate Feature Spec from analysis">
+  <sequence id="S0" name="Feature Analysis" status="pending" desc="Analyze PRD and produce function decomposition">
 
-    <!-- Step 0: Precondition Check -->
-    <block type="task" id="B1" action="read-file" desc="Read feature analysis document">
-      <field name="path" value="${feature_analysis_path}"/>
-      <field name="output" var="feature_analysis"/>
+    <!-- Step 0.1: Read PRD -->
+    <block type="task" id="B0_1" action="read-file" desc="Read PRD document">
+      <field name="path" value="${prd_path}"/>
+      <field name="output" var="prd_content"/>
     </block>
 
-    <!-- Gateway: Validate analysis exists -->
-    <block type="gateway" id="G1" mode="guard" desc="Verify analysis exists"
-           test="${feature_analysis} != null" fail-action="stop">
-      <field name="message">Feature Analysis document not found. Run speccrew-fd-feature-analyze first.</field>
+    <!-- Gateway: Validate PRD exists -->
+    <block type="gateway" id="G0_1" mode="guard" desc="Verify PRD exists"
+           test="${prd_content} != null" fail-action="stop">
+      <field name="message">PRD document not found at: ${prd_path}</field>
     </block>
 
-    <!-- Step 0.2: Verify Checkpoint A -->
-    <block type="task" id="B2" action="analyze" desc="Verify Checkpoint A passed">
-      <field name="input" value="${feature_analysis}"/>
-      <field name="verification_rules">
-        - Check function_decomposition.passed == true
-        - Extract feature_id, feature_name, feature_type
-        - Extract functions list
-        - Extract platforms list
+    <!-- Step 0.2: Load System Knowledge -->
+    <block type="task" id="B0_2" action="read-file" desc="Read System Overview">
+      <field name="path">${workspace_path}/knowledges/bizs/system-overview.md</field>
+      <field name="output" var="system_overview"/>
+    </block>
+
+    <!-- Step 0.3: Load Related Module Overviews -->
+    <block type="task" id="B0_3" action="analyze" desc="Identify related modules from PRD">
+      <field name="input" value="${prd_content}"/>
+      <field name="analysis_rules">
+        - Extract module names mentioned in PRD
+        - Identify cross-module dependencies
+        - List related module overview files to read
       </field>
-      <field name="output" var="checkpoint_a_status"/>
+      <field name="output" var="related_modules"/>
     </block>
 
-    <!-- Gateway: Checkpoint A validation -->
-    <block type="gateway" id="G2" mode="guard" desc="Verify Checkpoint A passed"
-           test="${checkpoint_a_status.passed} == true" fail-action="stop">
-      <field name="message">Checkpoint A not passed. Run speccrew-fd-feature-analyze first.</field>
+    <!-- Loop: Read related module overviews -->
+    <block type="loop" id="L0_1" over="${related_modules}" as="module" desc="Read related module overviews">
+      <block type="task" id="B0_4" action="read-file" desc="Read module overview">
+        <field name="path">${workspace_path}/knowledges/bizs/${module.name}/${module.name}-overview.md</field>
+        <field name="output" var="module_overview_${module.name}"/>
+      </block>
     </block>
 
-    <!-- Step 0.3: Verify Feature Name Consistency -->
-    <block type="task" id="B3" action="analyze" desc="Check feature name consistency">
-      <field name="input" value="${feature_analysis}">${feature_name}</field>
-      <field name="check_rules">
-        - Compare analysis file Feature Name with feature_name parameter
-        - Log discrepancy if found
-        - Continue with feature_name parameter for file naming
+    <!-- Step 0.4: Discover Frontend Platforms -->
+    <block type="gateway" id="G0_2" mode="exclusive" desc="Get frontend platforms">
+      <branch test="${frontend_platforms} != null AND ${frontend_platforms.length} > 0" name="Use provided platforms">
+        <block type="event" id="E0_1" action="log" level="info" desc="Using provided platforms">
+          <field name="message">Using provided frontend platforms: ${frontend_platforms}</field>
+        </block>
+      </branch>
+      <branch default="true" name="Auto-discover from techs-manifest">
+        <block type="task" id="B0_5" action="read-file" desc="Read techs manifest">
+          <field name="path">${workspace_path}/knowledges/techs/techs-manifest.json</field>
+          <field name="output" var="techs_manifest"/>
+        </block>
+        <block type="task" id="B0_6" action="analyze" desc="Extract frontend platforms">
+          <field name="input" value="${techs_manifest}"/>
+          <field name="extraction_rules">
+            - Filter platforms with type web-* or mobile-*
+            - Extract platform identifiers
+          </field>
+          <field name="output" var="frontend_platforms"/>
+        </block>
+      </branch>
+    </block>
+
+    <!-- Step 0.5: Function Breakdown -->
+    <block type="gateway" id="G0_3" mode="exclusive" desc="Select decomposition mode">
+      <branch test="${feature_id} != null" name="Feature-based decomposition">
+        <block type="task" id="B0_7" action="analyze" desc="Extract specific Feature from PRD">
+          <field name="input" value="${prd_content}"/>
+          <field name="feature_id" value="${feature_id}"/>
+          <field name="analysis_rules">
+            - Locate Feature in PRD Section 3.4 Feature Breakdown
+            - Extract only user stories mapped to this Feature
+            - Decompose into 3-8 focused Functions
+            - Mark API-only if feature_type indicates
+          </field>
+          <field name="output" var="function_breakdown"/>
+        </block>
+      </branch>
+      <branch default="true" name="Full PRD decomposition">
+        <block type="task" id="B0_8" action="analyze" desc="Decompose entire PRD">
+          <field name="input" value="${prd_content}"/>
+          <field name="analysis_rules">
+            - Decompose entire PRD into all required Functions
+            - May result in 10-20 Functions for complex modules
+          </field>
+          <field name="output" var="function_breakdown"/>
+        </block>
+      </branch>
+    </block>
+
+    <!-- Step 0.6: Analyze Functions with System Markers -->
+    <block type="task" id="B0_9" action="analyze" desc="Analyze functions with system relationship markers">
+      <field name="input" value="${function_breakdown}">${system_overview}${related_modules}</field>
+      <field name="analysis_rules">
+        For each function, identify:
+        - Frontend Changes: New pages, components, or modifications
+        - Backend Changes: New interfaces or modifications
+        - Data Changes: New data structures or modifications
+        - System Relationship: [EXISTING], [MODIFIED], or [NEW]
+      </field>
+      <field name="output" var="analyzed_functions"/>
+    </block>
+
+    <!-- Checkpoint A: User Confirmation -->
+    <block type="gateway" id="G0_4" mode="exclusive" desc="Handle checkpoint A">
+      <branch test="${skip_analysis_checkpoint} == true" name="Skip confirmation">
+        <block type="event" id="E0_2" action="log" level="info" desc="Skipping checkpoint A">
+          <field name="message">skip_analysis_checkpoint=true, proceeding without user confirmation</field>
+        </block>
+      </branch>
+      <branch default="true" name="Request confirmation">
+        <block type="event" id="E0_3" action="confirm" title="Function Breakdown Confirmation - Checkpoint A" type="yesno" desc="Present function breakdown for confirmation">
+          <field name="preview">Function Breakdown (Total: ${analyzed_functions.count} functions):
+
+${analyzed_functions.summary}
+
+System Relationship Markers:
+- [EXISTING]: ${analyzed_functions.existing_count} - Reuse existing capabilities
+- [MODIFIED]: ${analyzed_functions.modified_count} - Enhance existing features
+- [NEW]: ${analyzed_functions.new_count} - Create new functionality
+
+Does this function breakdown align with your understanding of the requirements?</field>
+        </block>
+      </branch>
+    </block>
+
+    <!-- Step 0.7: Update Checkpoint A -->
+    <block type="task" id="B0_10" action="run-script" desc="Record checkpoint A passed">
+      <field name="command">node "${workspace_path}/scripts/update-progress.js" write-checkpoint --file "${workspace_path}/iterations/${iteration_id}/02.feature-design/.checkpoints.json" --stage 02_feature_design --checkpoint function_decomposition --passed true</field>
+      <field name="output" var="checkpoint_a_result"/>
+    </block>
+
+  </sequence>
+
+  <!-- ============================================================
+       Sequence S1: Feature Design
+       ============================================================ -->
+  <sequence id="S1" name="Feature Design" status="pending" desc="Generate Feature Spec from analysis results">
+
+    <!-- Step 1.0: Prepare analysis results for design -->
+    <block type="task" id="B1_0" action="analyze" desc="Prepare analysis data for design phase">
+      <field name="input" value="${analyzed_functions}">${prd_content}${feature_id}${feature_name}${feature_type}${frontend_platforms}</field>
+      <field name="prepare_rules">
+        - Extract feature_id, feature_name, feature_type from parameters or analysis
+        - Prepare functions list for design phase
+        - Prepare platforms list for design phase
+        - Verify Checkpoint A passed status
       </field>
-      <field name="output" var="name_check_result"/>
+      <field name="output" var="design_input"/>
     </block>
 
     <!-- Step 1: Frontend Design (Conditional) -->
-    <block type="gateway" id="G3" mode="exclusive" desc="Conditional frontend design">
+    <block type="gateway" id="G1" mode="exclusive" desc="Conditional frontend design">
       <branch test="${feature_type} == 'API-only'" name="Skip frontend">
         <block type="event" id="E1" action="log" level="info" desc="Skipping frontend design">
           <field name="message">feature_type is API-only, skipping frontend design</field>
         </block>
       </branch>
       <branch default="true" name="Execute frontend design">
-        <block type="task" id="B4" action="analyze" desc="Design UI prototypes">
-          <field name="input" value="${feature_analysis}">${frontend_platforms}</field>
+        <block type="task" id="B1" action="analyze" desc="Design UI prototypes">
+          <field name="input" value="${design_input}">${frontend_platforms}</field>
           <field name="design_rules">
             - Create ASCII wireframes for each platform
             - Use Pattern M-A (Card List), M-B (Mobile Form), M-C (Action Sheet) for mobile
@@ -104,8 +232,8 @@
           <field name="output" var="ui_prototypes"/>
         </block>
 
-        <block type="task" id="B5" action="analyze" desc="Design interaction flows">
-          <field name="input" value="${feature_analysis}">${ui_prototypes}</field>
+        <block type="task" id="B2" action="analyze" desc="Design interaction flows">
+          <field name="input" value="${design_input}">${ui_prototypes}</field>
           <field name="design_rules">
             - Document User Action → Frontend Response → Backend API Call
             - Generate Mermaid sequenceDiagram for each flow
@@ -114,8 +242,8 @@
           <field name="output" var="interaction_flows"/>
         </block>
 
-        <block type="task" id="B6" action="analyze" desc="Map backend APIs">
-          <field name="input" value="${interaction_flows}">${feature_analysis}</field>
+        <block type="task" id="B3" action="analyze" desc="Map backend APIs">
+          <field name="input" value="${interaction_flows}">${design_input}</field>
           <field name="mapping_rules">
             - Map each frontend action to backend API endpoint
             - Document data exchanged
@@ -126,8 +254,8 @@
     </block>
 
     <!-- Step 2: Backend Design -->
-    <block type="task" id="B7" action="analyze" desc="Design backend interfaces">
-      <field name="input" value="${feature_analysis}">${api_mapping}</field>
+    <block type="task" id="B4" action="analyze" desc="Design backend interfaces">
+      <field name="input" value="${design_input}">${api_mapping}</field>
       <field name="design_rules">
         - List API/Interface with method and description
         - Document processing logic flow (Mermaid flowchart TD)
@@ -138,8 +266,8 @@
     </block>
 
     <!-- Step 3: Data Model and Business Rules -->
-    <block type="task" id="B8" action="analyze" desc="Design data model">
-      <field name="input" value="${feature_analysis}">${backend_design}</field>
+    <block type="task" id="B5" action="analyze" desc="Design data model">
+      <field name="input" value="${design_input}">${backend_design}</field>
       <field name="design_rules">
         - Define new data structures (field, type, constraints, description)
         - Document modifications to existing structures
@@ -153,7 +281,7 @@
     </block>
 
     <!-- Step 4: Checkpoint B -->
-    <block type="gateway" id="G4" mode="exclusive" desc="Handle checkpoint B">
+    <block type="gateway" id="G2" mode="exclusive" desc="Handle checkpoint B">
       <branch test="${skip_checkpoint} == true" name="Skip confirmation">
         <block type="event" id="E2" action="log" level="info" desc="Skipping checkpoint B">
           <field name="message">skip_checkpoint=true, proceeding without user confirmation</field>
@@ -164,12 +292,12 @@
           <field name="preview">Feature: ${feature_name} (${feature_id})
 
 FUNCTIONS DESIGNED
-Total: ${feature_analysis.function_count} functions
+Total: ${analyzed_functions.count} functions
 
 SYSTEM RELATIONSHIP SUMMARY
-- [EXISTING]: ${feature_analysis.existing_count} - Reuse existing capabilities
-- [MODIFIED]: ${feature_analysis.modified_count} - Enhance existing features
-- [NEW]: ${feature_analysis.new_count} - Create new functionality
+- [EXISTING]: ${analyzed_functions.existing_count} - Reuse existing capabilities
+- [MODIFIED]: ${analyzed_functions.modified_count} - Enhance existing features
+- [NEW]: ${analyzed_functions.new_count} - Create new functionality
 
 FRONTEND COMPONENTS
 - Platforms: ${frontend_platforms}
@@ -196,21 +324,21 @@ Please confirm:
     </block>
 
     <!-- Step 4.3: Update Checkpoint B -->
-    <block type="task" id="B9" action="run-script" desc="Record checkpoint B passed">
+    <block type="task" id="B6" action="run-script" desc="Record checkpoint B passed">
       <field name="command">node "${workspace_path}/scripts/update-progress.js" write-checkpoint --file "${workspace_path}/iterations/${iteration_id}/02.feature-design/.checkpoints.json" --stage 02_feature_design --checkpoint feature_design_review --passed true</field>
       <field name="output" var="checkpoint_b_result"/>
     </block>
 
     <!-- Step 5: Determine Output Path and Copy Template -->
-    <block type="task" id="B10" action="read-file" desc="Read Feature Spec template">
+    <block type="task" id="B7" action="read-file" desc="Read Feature Spec template">
       <field name="path">speccrew-fd-feature-design/templates/FEATURE-SPEC-TEMPLATE.md</field>
       <field name="output" var="template_content"/>
     </block>
 
     <!-- Gateway: Determine output path mode -->
-    <block type="gateway" id="G5" mode="exclusive" desc="Determine output path">
+    <block type="gateway" id="G3" mode="exclusive" desc="Determine output path">
       <branch test="${feature_id} != null" name="Single Feature Mode">
-        <block type="task" id="B11" action="generate" desc="Create document from template">
+        <block type="task" id="B8" action="generate" desc="Create document from template">
           <field name="template" value="${template_content}"/>
           <field name="placeholders">
             - [Feature Name] → ${feature_name}
@@ -224,7 +352,7 @@ Please confirm:
         </block>
       </branch>
       <branch default="true" name="Legacy Mode">
-        <block type="task" id="B12" action="generate" desc="Create document from template">
+        <block type="task" id="B9" action="generate" desc="Create document from template">
           <field name="template" value="${template_content}"/>
           <field name="placeholders">
             - [Feature Name] → ${feature_name}
@@ -240,8 +368,8 @@ Please confirm:
     </block>
 
     <!-- Step 6: Fill Sections Using search_replace -->
-    <block type="loop" id="L1" over="${feature_analysis.functions}" as="function" desc="Fill each function section">
-      <block type="task" id="B13" action="edit-file" desc="Fill Frontend Prototype section">
+    <block type="loop" id="L1" over="${analyzed_functions.functions}" as="function" desc="Fill each function section">
+      <block type="task" id="B10" action="edit-file" desc="Fill Frontend Prototype section">
         <field name="path">${output_path}</field>
         <field name="operation">search_replace</field>
         <field name="search">#### ${function.id}.1 Frontend Prototype
@@ -252,7 +380,7 @@ Please confirm:
 ${ui_prototypes[function.id]}</field>
       </block>
 
-      <block type="task" id="B14" action="edit-file" desc="Fill Interaction Flow section">
+      <block type="task" id="B11" action="edit-file" desc="Fill Interaction Flow section">
         <field name="path">${output_path}</field>
         <field name="operation">search_replace</field>
         <field name="search">#### ${function.id}.2 Interaction Flow
@@ -263,7 +391,7 @@ ${ui_prototypes[function.id]}</field>
 ${interaction_flows[function.id]}</field>
       </block>
 
-      <block type="task" id="B15" action="edit-file" desc="Fill Backend Interface section">
+      <block type="task" id="B12" action="edit-file" desc="Fill Backend Interface section">
         <field name="path">${output_path}</field>
         <field name="operation">search_replace</field>
         <field name="search">#### ${function.id}.3 Backend Interface
@@ -274,7 +402,7 @@ ${interaction_flows[function.id]}</field>
 ${backend_design[function.id]}</field>
       </block>
 
-      <block type="task" id="B16" action="edit-file" desc="Fill Data Definition section">
+      <block type="task" id="B13" action="edit-file" desc="Fill Data Definition section">
         <field name="path">${output_path}</field>
         <field name="operation">search_replace</field>
         <field name="search">#### ${function.id}.4 Data Definition
@@ -287,7 +415,7 @@ ${data_model[function.id]}</field>
     </block>
 
     <!-- Step 7: Mermaid Diagram Compliance -->
-    <block type="task" id="B17" action="analyze" desc="Verify Mermaid compliance">
+    <block type="task" id="B14" action="analyze" desc="Verify Mermaid compliance">
       <field name="input" value="${output_path}"/>
       <field name="verification_rules">
         - NO style definitions (classDef, style)
@@ -298,13 +426,13 @@ ${data_model[function.id]}</field>
     </block>
 
     <!-- Step 8: Update Checkpoint -->
-    <block type="task" id="B18" action="run-script" desc="Record feature spec review checkpoint">
+    <block type="task" id="B15" action="run-script" desc="Record feature spec review checkpoint">
       <field name="command">node "${workspace_path}/scripts/update-progress.js" write-checkpoint --file "${workspace_path}/iterations/${iteration_id}/02.feature-design/.checkpoints.json" --stage 02_feature_design --checkpoint feature_spec_review --passed true</field>
     </block>
 
     <!-- Step 9: Update Progress with Metadata -->
-    <block type="task" id="B19" action="run-script" desc="Update dispatch progress with metadata">
-      <field name="command">node "${workspace_path}/scripts/update-progress.js" update-task --file "${workspace_path}/iterations/${iteration_id}/DISPATCH-PROGRESS.json" --task-id "${feature_id}" --status completed --metadata '{"function_count": ${feature_analysis.function_count}, "component_count": ${ui_prototypes.component_count}, "api_count": ${backend_design.api_count}, "entity_count": ${data_model.entity_count}}'</field>
+    <block type="task" id="B16" action="run-script" desc="Update dispatch progress with metadata">
+      <field name="command">node "${workspace_path}/scripts/update-progress.js" update-task --file "${workspace_path}/iterations/${iteration_id}/DISPATCH-PROGRESS.json" --task-id "${feature_id}" --status completed --metadata '{"function_count": ${analyzed_functions.count}, "component_count": ${ui_prototypes.component_count}, "api_count": ${backend_design.api_count}, "entity_count": ${data_model.entity_count}}'</field>
     </block>
 
   </sequence>
@@ -314,9 +442,11 @@ ${data_model[function.id]}</field>
        ============================================================ -->
   <block type="output" id="O1" desc="Workflow output results">
     <field name="feature_spec_path" value="${output_path}" type="string" desc="Path to generated Feature Spec"/>
-    <field name="function_count" from="${feature_analysis.function_count}" type="number" desc="Number of functions designed"/>
+    <field name="function_count" from="${analyzed_functions.count}" type="number" desc="Number of functions analyzed and designed"/>
     <field name="api_count" from="${backend_design.api_count}" type="number" desc="Number of APIs defined"/>
+    <field name="checkpoint_a_status" value="passed" type="string" desc="Checkpoint A status"/>
     <field name="checkpoint_b_status" value="passed" type="string" desc="Checkpoint B status"/>
+    <field name="frontend_platforms" from="${frontend_platforms}" type="array" desc="List of frontend platforms"/>
   </block>
 
 </workflow>

package/.speccrew/skills/speccrew-feature-designer-orchestration/workflow.agentflow.xml

@@ -49,8 +49,8 @@
           <branch test="${checkpoints.feature_spec_review.passed} == true" name="Resume from Phase 4">
             <block type="set-variable" id="P0-V1" name="resume_phase" value="4"/>
           </branch>
-          <branch test="${checkpoints.function_decomposition.passed} == true" name="Resume from Phase 3b">
-            <block type="set-variable" id="P0-V2" name="resume_phase" value="3b"/>
+          <branch test="${checkpoints.function_decomposition.passed} == true" name="Resume from Phase 3">
+            <block type="set-variable" id="P0-V2" name="resume_phase" value="3"/>
           </branch>
           <branch default="true" name="Resume from Phase 1"/>
         </block>
@@ -179,29 +179,28 @@
     </block>
   </sequence>
 
-  <!-- ========== Phase 3: Feature Design — Two-Stage Pipeline ========== -->
-  <sequence name="Phase 3: Feature Design — Two-Stage Pipeline">
+  <!-- ========== Phase 3: Feature Design (Unified Analysis + Design) ========== -->
+  <sequence name="Phase 3: Feature Design (Unified Analysis + Design)">
     
     <block type="rule" id="P3-R1" level="mandatory" desc="Phase 3 Mandatory Rules">
       <field name="text">DO NOT ask user which strategy to use - strategy determined by Phase 2 extraction</field>
       <field name="text">DO NOT invoke skills directly when 2+ Features - MUST dispatch speccrew-task-worker</field>
       <field name="text">Dispatch granularity is PER FEATURE, not per module</field>
       <field name="text">DO NOT generate Feature Spec documents yourself - role is to DISPATCH workers</field>
-      <field name="text">Phase 3a → 3b → 3c is STRICTLY SERIAL</field>
       <field name="text">Feature name is LOCKED after Phase 2 confirmation</field>
     </block>
 
-    <!-- ========== Phase 3a: Analyze — Function Decomposition ========== -->
-    <block type="event" id="P3-E1" action="log" desc="Start Phase 3a">
-      <field name="message">📊 Phase 3a: Analyze — Function Decomposition</field>
+    <!-- ========== Unified Feature Design Dispatch ========== -->
+    <block type="event" id="P3-E1" action="log" desc="Start Phase 3">
+      <field name="message">📊 Phase 3: Feature Design (Unified Analysis + Design)</field>
     </block>
 
-    <block type="gateway" id="P3-G1" mode="exclusive" desc="Dispatch mode for Phase 3a">
+    <block type="gateway" id="P3-G1" mode="exclusive" desc="Dispatch mode for Phase 3">
       
       <!-- Single Feature: Direct Invocation -->
       <branch test="${dispatch_mode} == 'direct'" name="Direct Invocation">
-        <block type="task" id="P3-B1" action="run-skill" status="pending" desc="Invoke feature analyze skill">
-          <field name="skill">speccrew-fd-feature-analyze</field>
+        <block type="task" id="P3-B1" action="run-skill" status="pending" desc="Invoke feature design skill">
+          <field name="skill">speccrew-fd-feature-design</field>
           <field name="context">
             prd_path: ${prd_files[0]}
             feature_id: ${feature_list.modules[0].features[0].feature_id}
@@ -209,8 +208,9 @@
             feature_type: ${feature_list.modules[0].features[0].feature_type}
             iteration_id: ${iteration_path}
             frontend_platforms: ${frontend_platforms}
+            output_path: ${iteration_path}/02.feature-design/${feature_id}-${feature_name}-feature-spec.md
           </field>
-          <field name="output" var="analyze_result"/>
+          <field name="output" var="design_result"/>
         </block>
       </branch>
 
@@ -225,77 +225,6 @@
 
         <!-- Initialize DISPATCH-PROGRESS.json -->
         <block type="task" id="P3-B2" action="run-script" status="pending" desc="Initialize dispatch progress">
-          <field name="command">node ${workspace_root}/scripts/update-progress.js init --file ${iteration_path}/02.feature-design/DISPATCH-PROGRESS.json --stage 02_feature_design_analyze --tasks-file ${iteration_path}/02.feature-design/.tasks-temp.json</field>
-        </block>
-
-        <!-- MANDATORY: Dispatch prompt must contain ONLY skill path + context data parameters.
-             DO NOT include execution instructions, step sequences, or output directives.
-             Worker will read skill's workflow.agentflow.xml for execution plan. -->
-        <!-- Dispatch Workers in batches of 6 -->
-        <block type="loop" id="P3-L1" mode="batch" batch_size="6" desc="Dispatch analyze workers">
-          <field name="items" value="${all_features}"/>
-          
-          <block type="task" id="P3-B3" action="dispatch-to-worker" status="pending" desc="Dispatch analyze worker">
-            <field name="agent">speccrew-task-worker</field>
-            <field name="skill">speccrew-fd-feature-analyze</field>
-            <field name="context">
-              workspace_path: ${workspace_root}
-              prd_path: ${item.prd_path}
-              feature_id: ${item.feature_id}
-              feature_name: ${item.feature_name}
-              feature_type: ${item.feature_type}
-              iteration_id: ${iteration_path}
-              frontend_platforms: ${frontend_platforms}
-              skip_checkpoint: true
-            </field>
-          </block>
-
-          <block type="task" id="P3-B4" action="run-script" status="pending" desc="Update worker progress">
-            <field name="command">node ${workspace_root}/scripts/update-progress.js update-task --file ${iteration_path}/02.feature-design/DISPATCH-PROGRESS.json --task-id ${item.feature_id} --status ${worker_status}</field>
-          </block>
-        </block>
-
-        <!-- All completed: Present summary -->
-        <block type="event" id="P3-E2" action="log" desc="Display analyze summary">
-          <field name="template">analyze-summary</field>
-          <field name="data" value="${analyze_results}"/>
-        </block>
-
-        <block type="event" id="P3-E3" action="confirm" desc="HARD STOP for analyze confirmation">
-          <field name="prompt">📊 Phase 3a (Analyze) complete. Does this function breakdown align with your understanding?</field>
-        </block>
-      </branch>
-    </block>
-
-    <!-- ========== Phase 3b: Design & Generate — Feature Spec Production ========== -->
-    <block type="event" id="P3-E4" action="log" desc="Start Phase 3b">
-      <field name="message">📊 Phase 3b: Design & Generate — Feature Spec Production</field>
-    </block>
-
-    <block type="gateway" id="P3-G2" mode="exclusive" desc="Dispatch mode for Phase 3b">
-      
-      <!-- Single Feature: Direct Invocation -->
-      <branch test="${dispatch_mode} == 'direct'" name="Direct Invocation">
-        <block type="task" id="P3-B5" action="run-skill" status="pending" desc="Invoke feature design skill">
-          <field name="skill">speccrew-fd-feature-design</field>
-          <field name="context">
-            feature_analysis_path: ${analyze_result.output_path}
-            prd_path: ${prd_files[0]}
-            feature_id: ${feature_list.modules[0].features[0].feature_id}
-            feature_name: ${feature_list.modules[0].features[0].feature_name}
-            feature_type: ${feature_list.modules[0].features[0].feature_type}
-            frontend_platforms: ${frontend_platforms}
-            output_path: ${iteration_path}/02.feature-design/${feature_id}-${feature_name}-feature-spec.md
-          </field>
-          <field name="output" var="design_result"/>
-        </block>
-      </branch>
-
-      <!-- Multiple Features: Worker Dispatch -->
-      <branch test="${dispatch_mode} == 'worker'" name="Worker Dispatch">
-        
-        <!-- Initialize DISPATCH-PROGRESS.json for Design stage -->
-        <block type="task" id="P3-B6" action="run-script" status="pending" desc="Initialize design dispatch progress">
           <field name="command">node ${workspace_root}/scripts/update-progress.js init --file ${iteration_path}/02.feature-design/DISPATCH-PROGRESS.json --stage 02_feature_design_spec --tasks-file ${iteration_path}/02.feature-design/.tasks-temp.json</field>
         </block>
 
@@ -303,26 +232,26 @@
              DO NOT include execution instructions, step sequences, or output directives.
              Worker will read skill's workflow.agentflow.xml for execution plan. -->
         <!-- Dispatch Workers in batches of 6 -->
-        <block type="loop" id="P3-L2" mode="batch" batch_size="6" desc="Dispatch design workers">
+        <block type="loop" id="P3-L1" mode="batch" batch_size="6" desc="Dispatch design workers">
           <field name="items" value="${all_features}"/>
           
-          <block type="task" id="P3-B7" action="dispatch-to-worker" status="pending" desc="Dispatch design worker">
+          <block type="task" id="P3-B3" action="dispatch-to-worker" status="pending" desc="Dispatch design worker">
             <field name="agent">speccrew-task-worker</field>
             <field name="skill">speccrew-fd-feature-design</field>
             <field name="context">
               workspace_path: ${workspace_root}
-              feature_analysis_path: ${item.analysis_path}
               prd_path: ${item.prd_path}
               feature_id: ${item.feature_id}
               feature_name: ${item.feature_name}
               feature_type: ${item.feature_type}
+              iteration_id: ${iteration_path}
               frontend_platforms: ${frontend_platforms}
               output_path: ${iteration_path}/02.feature-design/${item.feature_id}-${item.feature_name}-feature-spec.md
-              skip_checkpoint: true
+              skip_analysis_checkpoint: true
             </field>
           </block>
 
-          <block type="task" id="P3-B8" action="run-script" status="pending" desc="Update worker progress">
+          <block type="task" id="P3-B4" action="run-script" status="pending" desc="Update worker progress">
             <field name="command">node ${workspace_root}/scripts/update-progress.js update-task --file ${iteration_path}/02.feature-design/DISPATCH-PROGRESS.json --task-id ${item.feature_id} --status ${worker_status}</field>
           </block>
         </block>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "speccrew",
-  "version": "0.7.30",
+  "version": "0.7.31",
   "description": "Spec-Driven Development toolkit for AI-powered IDEs",
   "author": "charlesmu99",
   "repository": {