refactor(workflow): rename workflow-lite-plan to workflow-lite-planex and remove standalone lite-execute

- Rename skill directory from workflow-lite-plan to workflow-lite-planex (planex = plan + execute) - Remove standalone lite-execute command entry from command.json and analyze_commands.py - Update all 60+ files referencing workflow-lite-plan to use workflow-lite-planex - Update descriptions to clarify Phase 1: plan → Phase 2: execute architecture - Remove lite-execute as standalone command from orchestrator routing tables - Update docs (EN/ZH) to reflect unified planex naming and phase descriptions
2026-03-02 15:23:19 +08:00 · 2026-03-02 14:03:17 +08:00
parent 71485b89e6
commit 0d5cc4a74f
60 changed files with 277 additions and 445 deletions
--- a/.claude/skills/ccw-help/command.json
+++ b/.claude/skills/ccw-help/command.json
@@ -361,17 +361,6 @@
      "difficulty": "Intermediate",
      "source": "../../commands/workflow/init.md"
    },
-    {
-      "name": "lite-execute",
-      "command": "/workflow:lite-execute",
-      "description": "Execute tasks based on in-memory plan, prompt description, or file content",
-      "arguments": "[-y|--yes] [--in-memory] [\\\"task description\\\"|file-path]",
-      "category": "workflow",
-      "subcategory": null,
-      "usage_scenario": "implementation",
-      "difficulty": "Intermediate",
-      "source": "../../commands/workflow/lite-execute.md"
-    },
    {
      "name": "lite-fix",
      "command": "/workflow:lite-fix",
@@ -396,8 +385,8 @@
    },
    {
      "name": "lite-plan",
-      "command": "/workflow-lite-plan",
-      "description": "Lightweight interactive planning workflow with in-memory planning, code exploration, and execution execute to lite-execute after user confirmation",
+      "command": "/workflow-lite-planex",
+      "description": "Lightweight interactive planning and execution workflow (Phase 1: plan, Phase 2: execute) with in-memory planning, code exploration, and automatic execution after user confirmation",
      "arguments": "[-y|--yes] [-e|--explore] \\\"task description\\\"|file.md",
      "category": "workflow",
      "subcategory": null,
--- a/.claude/skills/ccw-help/scripts/analyze_commands.py
+++ b/.claude/skills/ccw-help/scripts/analyze_commands.py
@@ -176,21 +176,17 @@ def build_command_relationships() -> Dict[str, Any]:
            "alternatives": ["workflow:resume"],
            "related": ["workflow:session:list", "workflow:status"]
        },
-        "workflow-lite-plan": {
-            "calls_internally": ["workflow:lite-execute"],
-            "next_steps": ["workflow:lite-execute", "workflow:status"],
+        "workflow-lite-planex": {
+            "calls_internally": [],
+            "next_steps": ["workflow:status"],
            "alternatives": ["workflow-plan"],
            "prerequisites": []
        },
        "workflow:lite-fix": {
-            "next_steps": ["workflow:lite-execute", "workflow:status"],
-            "alternatives": ["workflow-lite-plan"],
+            "next_steps": ["workflow:status"],
+            "alternatives": ["workflow-lite-planex"],
            "related": ["workflow-test-fix"]
        },
-        "workflow:lite-execute": {
-            "prerequisites": ["workflow-lite-plan", "workflow:lite-fix"],
-            "related": ["workflow-execute", "workflow:status"]
-        },
        "workflow:review-session-cycle": {
            "prerequisites": ["workflow-execute"],
            "next_steps": ["workflow:review-fix"],
@@ -213,7 +209,7 @@ def build_command_relationships() -> Dict[str, Any]:
 def identify_essential_commands(all_commands: List[Dict]) -> List[Dict]:
    """Identify the most essential commands for beginners."""
    essential_names = [
-        "workflow-lite-plan", "workflow:lite-fix", "workflow-plan",
+        "workflow-lite-planex", "workflow:lite-fix", "workflow-plan",
        "workflow-execute", "workflow:status", "workflow:session:start",
        "workflow:review-session-cycle", "cli:analyze", "cli:chat",
        "memory:docs", "workflow:brainstorm:artifacts",
--- a/.claude/skills/spec-generator/README.md
+++ b/.claude/skills/spec-generator/README.md
@@ -67,7 +67,7 @@ spec-generator/
 ## Handoff

 After Phase 6, choose execution path:
- `workflow-lite-plan` - Execute per Epic
+- `workflow-lite-planex` - Execute per Epic
 - `workflow:req-plan-with-file` - Roadmap decomposition
 - `workflow-plan` - Full planning
 - `issue:new` - Create issues per Epic
--- a/.claude/skills/spec-generator/phases/06-readiness-check.md
+++ b/.claude/skills/spec-generator/phases/06-readiness-check.md
@@ -210,7 +210,7 @@ AskUserQuestion({
      options: [
        {
          label: "Execute via lite-plan",
-          description: "Start implementing with /workflow-lite-plan, one Epic at a time"
+          description: "Start implementing with /workflow-lite-planex, one Epic at a time"
        },
        {
          label: "Create roadmap",
@@ -242,7 +242,7 @@ if (selection === "Execute via lite-plan") {
  const epicContent = Read(firstMvpFile);
  const title = extractTitle(epicContent);       // First # heading
  const description = extractSection(epicContent, "Description");
-  Skill(skill="workflow-lite-plan", args=`"${title}: ${description}"`)
+  Skill(skill="workflow-lite-planex", args=`"${title}: ${description}"`)
 }

 if (selection === "Full planning" || selection === "Create roadmap") {
--- a/.claude/skills/team-ultra-analyze/roles/coordinator/role.md
+++ b/.claude/skills/team-ultra-analyze/roles/coordinator/role.md
@@ -332,7 +332,7 @@ EXPLORE-001 → ANALYZE-001 → SYNTH-001
 | Option | Description |
 |--------|-------------|
 | 创建Issue | 基于结论创建 Issue |
-| 生成任务 | 启动 workflow-lite-plan 规划实施 |
+| 生成任务 | 启动 workflow-lite-planex 规划实施 |
 | 导出报告 | 生成独立分析报告 |
 | 关闭团队 | 关闭所有 teammate 并清理 |

--- a/.claude/skills/workflow-lite-planex/SKILL.md
+++ b/.claude/skills/workflow-lite-planex/SKILL.md
@@ -1,27 +1,26 @@
 ---
-name: workflow-lite-plan
-description: Lightweight planning and execution skill - route to lite-plan or lite-execute with prompt enhancement. Triggers on "workflow-lite-plan", "workflow:lite-execute".
+name: workflow-lite-planex
+description: Lightweight planning and execution skill (Phase 1: plan, Phase 2: execute). Triggers on "workflow-lite-planex".
 allowed-tools: Skill, Task, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob, Grep
 ---

-# Workflow Lite-Plan
+# Workflow Lite-Planex

-Unified lightweight planning and execution skill. Routes to lite-plan (planning pipeline) or lite-execute (execution engine) based on trigger, with prompt enhancement for both modes.
+Unified lightweight planning and execution skill (planex = plan + execute). Phase 1 handles planning pipeline, Phase 2 handles execution.

 ## Architecture Overview

 ```
 ┌─────────────────────────────────────────────────────┐
-│  SKILL.md (Router + Prompt Enhancement)              │
-│  → Detect mode → Enhance prompt → Dispatch to phase │
+│  SKILL.md (Prompt Enhancement + Dispatch)             │
+│  → Enhance prompt → Dispatch to Phase 1 (lite-plan)  │
 └──────────────────────┬──────────────────────────────┘
                       │
-           ┌───────────┼───────────┐
-           ↓                       ↓
+                       ↓
     ┌───────────┐           ┌───────────┐
     │ lite-plan │           │lite-execute│
-     │ Phase 1   │           │ Phase 2    │
-     │ Plan+Exec │─direct──→│ Standalone │
+     │ Phase 1   │──handoff─→│ Phase 2    │
+     │ Plan      │           │ Execute    │
     └───────────┘           └───────────┘
 ```

@@ -33,24 +32,14 @@ Multi-phase execution (lite-plan → lite-execute) spans long conversations that
 > The phase currently marked `in_progress` is the active execution phase — preserve its FULL content.
 > Only compress phases marked `completed` or `pending`.

-## Mode Detection & Routing
+## Routing

-```javascript
-const args = $ARGUMENTS
-const mode = detectMode()
+Trigger `workflow-lite-planex` → dispatches to Phase 1 (lite-plan). Phase 1 internally hands off to Phase 2 (lite-execute) after plan confirmation.

-function detectMode() {
-  if (skillName === 'workflow:lite-execute') return 'execute'
-  return 'plan'  // default: workflow-lite-plan
-}
-```
-
-**Routing Table**:
-
-| Trigger | Mode | Phase Document | Description |
-|---------|------|----------------|-------------|
-| `workflow-lite-plan` | plan | [phases/01-lite-plan.md](phases/01-lite-plan.md) | Full planning pipeline (explore → plan → confirm → execute) |
-| `workflow:lite-execute` | execute | [phases/02-lite-execute.md](phases/02-lite-execute.md) | Standalone execution (in-memory / prompt / file) |
+| Phase | Document | Description |
+|-------|----------|-------------|
+| Phase 1 | [phases/01-lite-plan.md](phases/01-lite-plan.md) | Planning pipeline (explore → plan → confirm → handoff to Phase 2) |
+| Phase 2 | [phases/02-lite-execute.md](phases/02-lite-execute.md) | Execution engine (internal, called by Phase 1 Phase 5) |

 ## Interactive Preference Collection

@@ -90,25 +79,6 @@ if (autoYes) {
    autoYes: prefResponse.autoMode === 'Auto',
    forceExplore: prefResponse.exploration === 'Force explore'
  }
-} else if (mode !== 'plan') {
-  // Execute mode (standalone, not in-memory)
-  const prefResponse = AskUserQuestion({
-    questions: [
-      {
-        question: "是否跳过所有确认步骤（自动模式）？",
-        header: "Auto Mode",
-        multiSelect: false,
-        options: [
-          { label: "Interactive (Recommended)", description: "交互模式，包含确认步骤" },
-          { label: "Auto", description: "跳过所有确认，自动执行" }
-        ]
-      }
-    ]
-  })
-  workflowPreferences = {
-    autoYes: prefResponse.autoMode === 'Auto',
-    forceExplore: false
-  }
 }
 ```

@@ -125,12 +95,9 @@ Bash('ccw spec load --category planning')
 // Step 2: Log available context
 console.log('Project context loaded via: ccw spec load --category planning')

-// Step 3: Dispatch to phase (workflowPreferences available as context)
-if (mode === 'plan') {
-  // Read phases/01-lite-plan.md and execute
-} else {
-  // Read phases/02-lite-execute.md and execute
-}
+// Step 3: Dispatch to Phase 1 (workflowPreferences available as context)
+// Read phases/01-lite-plan.md and execute
+// Phase 1 internally hands off to Phase 2 (lite-execute) after plan confirmation
 ```

 ## Execution Flow
@@ -145,21 +112,11 @@ if (mode === 'plan') {
 5. lite-plan Phase 5 directly reads and executes Phase 2 (lite-execute) with executionContext
 ```

-### Execute Mode
-
-```
-1. Collect preferences via AskUserQuestion (autoYes)
-2. Enhance prompt with project context availability
-3. Read phases/02-lite-execute.md
-4. Execute lite-execute pipeline (input detection → execution → review)
-```
-
 ## Usage

-Plan mode and execute mode are triggered by skill name routing (see Mode Detection). Workflow preferences (auto mode, force explore) are collected interactively via AskUserQuestion before dispatching to phases.
+Task description provided as arguments → interactive preference collection → planning pipeline → execution.

-**Plan mode**: Task description provided as arguments → interactive preference collection → planning pipeline
-**Execute mode**: Task description, file path, or in-memory context → interactive preference collection → execution pipeline
+**Plan mode only**: lite-plan handles planning (Phase 1) and automatically hands off to lite-execute (Phase 2) for execution. There is no standalone execute mode.

 ## Phase Reference Documents

--- a/.claude/skills/workflow-lite-planex/phases/01-lite-plan.md
+++ b/.claude/skills/workflow-lite-planex/phases/01-lite-plan.md
--- a/.claude/skills/workflow-lite-planex/phases/02-lite-execute.md
+++ b/.claude/skills/workflow-lite-planex/phases/02-lite-execute.md
--- a/.claude/skills/workflow-multi-cli-plan/SKILL.md
+++ b/.claude/skills/workflow-multi-cli-plan/SKILL.md
@@ -1,27 +1,26 @@
 ---
 name: workflow-multi-cli-plan
-description: Multi-CLI collaborative planning and execution skill - route to multi-cli-plan or lite-execute with prompt enhancement. Triggers on "workflow-multi-cli-plan", "workflow:lite-execute".
+description: Multi-CLI collaborative planning and execution skill with integrated execution phase. Triggers on "workflow-multi-cli-plan".
 allowed-tools: Skill, Task, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob, Grep, mcp__ace-tool__search_context
 ---

 # Workflow Multi-CLI Plan

-Unified multi-CLI collaborative planning and execution skill. Routes to multi-cli-plan (ACE context + multi-CLI discussion + plan generation) or lite-execute (execution engine) based on trigger, with prompt enhancement for both modes.
+Unified multi-CLI collaborative planning and execution skill. Routes to multi-cli-plan (ACE context + multi-CLI discussion + plan generation) which then hands off to lite-execute (Phase 2) internally for execution.

 ## Architecture Overview

 ```
 ┌─────────────────────────────────────────────────────────┐
 │  SKILL.md (Router + Prompt Enhancement)                  │
-│  → Detect mode → Enhance prompt → Dispatch to phase     │
+│  → Enhance prompt → Dispatch to Phase 1                 │
 └──────────────────────┬──────────────────────────────────┘
                       │
-           ┌───────────┼───────────┐
-           ↓                       ↓
+                       ↓
     ┌──────────────┐        ┌───────────┐
     │multi-cli-plan│        │lite-execute│
-     │   Phase 1    │        │  Phase 2   │
-     │  Plan+Exec   │─handoff→│ Standalone │
+     │   Phase 1    │─handoff→│  Phase 2   │
+     │  Plan+Exec   │        │ (internal) │
     └──────────────┘        └───────────┘
 ```

@@ -29,12 +28,7 @@ Unified multi-CLI collaborative planning and execution skill. Routes to multi-cl

 ```javascript
 const args = $ARGUMENTS
-const mode = detectMode()
-
-function detectMode() {
-  if (skillName === 'workflow:lite-execute') return 'execute'
-  return 'plan'  // default: workflow-multi-cli-plan
-}
+const mode = 'plan'  // workflow-multi-cli-plan always starts with planning
 ```

 **Routing Table**:
@@ -42,7 +36,6 @@ function detectMode() {
 | Trigger | Mode | Phase Document | Description |
 |---------|------|----------------|-------------|
 | `workflow-multi-cli-plan` | plan | [phases/01-multi-cli-plan.md](phases/01-multi-cli-plan.md) | Multi-CLI collaborative planning (ACE context → discussion → plan → execute) |
-| `workflow:lite-execute` | execute | [phases/02-lite-execute.md](phases/02-lite-execute.md) | Standalone execution (in-memory / prompt / file) |

 ## Interactive Preference Collection

@@ -72,24 +65,6 @@ if (autoYes) {
  workflowPreferences = {
    autoYes: prefResponse.autoMode === 'Auto'
  }
-} else {
-  // Execute mode
-  const prefResponse = AskUserQuestion({
-    questions: [
-      {
-        question: "是否跳过所有确认步骤（自动模式）？",
-        header: "Auto Mode",
-        multiSelect: false,
-        options: [
-          { label: "Interactive (Recommended)", description: "交互模式，包含确认步骤" },
-          { label: "Auto", description: "跳过所有确认，自动执行" }
-        ]
-      }
-    ]
-  })
-  workflowPreferences = {
-    autoYes: prefResponse.autoMode === 'Auto'
-  }
 }
 ```

@@ -106,12 +81,9 @@ Bash('ccw spec load --category planning')
 // Step 2: Log available context
 console.log('Project context loaded via: ccw spec load --category planning')

-// Step 3: Dispatch to phase (workflowPreferences available as context)
-if (mode === 'plan') {
-  // Read phases/01-multi-cli-plan.md and execute
-} else {
-  // Read phases/02-lite-execute.md and execute
-}
+// Step 3: Dispatch to Phase 1 (workflowPreferences available as context)
+// Read phases/01-multi-cli-plan.md and execute
+// Phase 1 internally hands off to Phase 2 (lite-execute) after plan approval
 ```

 ## Compact Recovery (Phase Persistence)
@@ -134,21 +106,9 @@ Multi-phase execution (multi-cli-plan → lite-execute) spans long conversations
 5. Phase 5 directly reads and executes Phase 2 (lite-execute) with executionContext
 ```

-### Execute Mode (workflow:lite-execute)
-
-```
-1. Collect preferences via AskUserQuestion (autoYes)
-2. Enhance prompt with project context availability
-3. Read phases/02-lite-execute.md
-4. Execute lite-execute pipeline (input detection → execution → review)
-```
-
 ## Usage

-Plan mode and execute mode are triggered by skill name routing (see Mode Detection). Workflow preferences (auto mode) are collected interactively via AskUserQuestion before dispatching to phases.
-
-**Plan mode**: Task description provided as arguments → interactive preference collection → multi-CLI planning pipeline
-**Execute mode**: Task description, file path, or in-memory context → interactive preference collection → execution pipeline
+Task description provided as arguments → interactive preference collection → multi-CLI planning pipeline → internal execution handoff to Phase 2 (lite-execute).

 ## Phase Reference Documents

--- a/.claude/skills/workflow-multi-cli-plan/phases/01-multi-cli-plan.md
+++ b/.claude/skills/workflow-multi-cli-plan/phases/01-multi-cli-plan.md
@@ -24,7 +24,7 @@ When `workflowPreferences.autoYes` is true: Auto-approve plan, use recommended s
 **Output Directory**: `.workflow/.multi-cli-plan/{session-id}/`
 **Default Max Rounds**: 3 (convergence may complete earlier)
 **CLI Tools**: @cli-discuss-agent (analysis), @cli-lite-planning-agent (plan generation)
-**Execution**: Auto-hands off to `/workflow:lite-execute --in-memory` after plan approval
+**Execution**: Auto-hands off to Phase 2 (lite-execute) after plan approval

 ## What & Why

@@ -81,7 +81,7 @@ Phase 4: User Decision
 Phase 5: Plan Generation & Execution Handoff
   ├─ Generate plan.json + .task/*.json (via @cli-lite-planning-agent, two-layer output)
   ├─ Build executionContext with user selections and taskFiles
-   └─ Execute to /workflow:lite-execute --in-memory
+   └─ Execute via Phase 2 (lite-execute)
 ```

 ### Agent Roles
@@ -598,7 +598,7 @@ TodoWrite({ todos: [

 ```bash
 # Simpler single-round planning
-/workflow-lite-plan "task description"
+/workflow-lite-planex "task description"

 # Issue-driven discovery
 /issue:discover-by-prompt "find issues"
@@ -609,7 +609,7 @@ cat .workflow/.multi-cli-plan/{session-id}/rounds/1/synthesis.json
 cat .workflow/.multi-cli-plan/{session-id}/context-package.json

 # Direct execution (if you have plan.json)
-/workflow:lite-execute plan.json
+# Use workflow-lite-planex or workflow-multi-cli-plan (execution is integrated)
 ```

 ## Next Phase
--- a/.claude/skills/workflow-multi-cli-plan/phases/02-lite-execute.md
+++ b/.claude/skills/workflow-multi-cli-plan/phases/02-lite-execute.md
@@ -26,22 +26,13 @@ Flexible task execution command supporting three input modes: in-memory plan (fr

 ## Usage

-### Command Syntax
-```bash
-/workflow:lite-execute [FLAGS] <INPUT>
-
-# Flags
--in-memory                Use plan from memory (called by lite-plan)
-
-# Arguments
-<input>                    Task description string, or path to file (required)
-```
+> **Note**: This is an internal phase, not a standalone command. It is called by Phase 1 (multi-cli-plan) after plan approval, or by lite-plan after Phase 4 approval.

 ## Input Modes

 ### Mode 1: In-Memory Plan

-**Trigger**: Called by lite-plan after Phase 4 approval with `--in-memory` flag
+**Trigger**: Called by multi-cli-plan Phase 5 after plan approval, or by lite-plan after Phase 4 approval

 **Input Source**: `executionContext` global variable set by lite-plan

--- a/.claude/skills/workflow-skill-designer/SKILL.md
+++ b/.claude/skills/workflow-skill-designer/SKILL.md
@@ -141,7 +141,7 @@ Read("phases/02-lite-execute.md")
 // Execute with executionContext (Mode 1)

 // WRONG: Skill routing (unnecessary round-trip)
-Skill(skill="workflow-lite-plan", args="--in-memory")
+Skill(skill="workflow-lite-planex", args="--in-memory")
 ```

 ### Pattern 8: Phase File Hygiene
--- a/.claude/skills/workflow-skill-designer/phases/03-phase-design.md
+++ b/.claude/skills/workflow-skill-designer/phases/03-phase-design.md
@@ -60,7 +60,7 @@ Read("phases/02-lite-execute.md")
 // Execute with executionContext (Mode 1)

 // WRONG: Skill routing (unnecessary round-trip)
-Skill(skill="workflow-lite-plan", args="--in-memory")
+Skill(skill="workflow-lite-planex", args="--in-memory")
 ```

 ### Content Restriction Enforcement