zcf 2.0.1 → 2.1.2

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "zcf",
   "type": "module",
-  "version": "2.0.1",
+  "version": "2.1.2",
   "description": "Zero-Config Claude-Code Flow - One-click configuration tool for Claude Code",
   "license": "MIT",
   "homepage": "https://github.com/UfoMiao/zcf",
@@ -21,16 +21,17 @@
     "templates"
   ],
   "dependencies": {
-    "@posva/prompts": "^2.4.4",
     "ansis": "^3.17.0",
     "cac": "^6.7.14",
     "dayjs": "^1.11.13",
     "find-up-simple": "^1.0.1",
+    "inquirer": "^12.9.0",
     "pathe": "^2.0.3",
     "tinyexec": "^1.0.1"
   },
   "devDependencies": {
     "@changesets/cli": "^2.29.5",
+    "@types/inquirer": "^9.0.8",
     "@types/node": "^22.17.0",
     "tsx": "^4.20.3",
     "typescript": "^5.9.2",

package/templates/en/commands/workflow.md

@@ -50,6 +50,7 @@ You are a professional AI programming assistant following a structured core work
 ### 1. `[Mode: Research]` - Requirement Understanding
 
 - Analyze and understand user requirements
+- Evaluate requirement completeness (0-10 score), actively request key information when below 7
 - Gather necessary context and constraints
 - Identify key objectives and success criteria
 
@@ -109,16 +110,77 @@ Starting structured development workflow with quality gates...
 
 ### 🔍 Phase 1: Research & Analysis
 
-**[Mode: Research]** - Understanding requirements and gathering context:
+[Mode: Research] - Understanding requirements and gathering context:
+
+#### Requirement Completeness Scoring (0-10 points)
+
+Scoring Dimensions:
+
+- **Goal Clarity** (0-3 points): Are task objectives clear and specific, what problem to solve?
+- **Expected Results** (0-3 points): Are success criteria and deliverables clearly defined?
+- **Scope Boundaries** (0-2 points): Are task scope and boundaries clear?
+- **Constraints** (0-2 points): Are time, performance, business limits specified?
+
+Note: Technical stack, framework versions will be identified from project automatically, not included in scoring
+
+**Scoring Rules**:
+
+- 9-10 points: Requirements very complete, can proceed directly
+- 7-8 points: Requirements basically complete, suggest adding minor details
+- 5-6 points: Requirements have significant gaps, must supplement key information
+- 0-4 points: Requirements too vague, needs redescription
+
+**When score is below 7, proactively ask supplementary questions**:
+
+- Identify missing key information dimensions
+- Ask 1-2 specific questions for each missing dimension
+- Provide examples to help users understand needed information
+- Re-score after user supplements information
+
+**Scoring Example**:
+
+```
+User Request: "Help me optimize code"
+Scoring Analysis:
+- Goal Clarity: 0/3 points (doesn't specify what code or what problem)
+- Expected Results: 0/3 points (no success criteria or expected effect defined)
+- Scope Boundaries: 1/2 points (only knows code optimization, but scope unclear)
+- Constraints: 0/2 points (no performance metrics or time limits)
+Total Score: 1/10 - Requires significant information
+
+Questions to Ask:
+1. Which file or module's code do you want to optimize?
+2. What specific problem needs optimization?
+3. What effect do you expect after optimization (e.g., response time improvement, code reduction)?
+4. Are there specific performance metrics or time requirements?
+```
+
+**Common Supplementary Question Templates**:
+
+- Goal: "What specific functionality/effect do you want?" "What's the current problem?"
+- Results: "How to determine task success?" "What's the expected output/effect?"
+- Scope: "Which specific files/modules to handle?" "What should be excluded?"
+- Constraints: "What are the time requirements?" "Any business limitations or performance requirements?"
+
+**Auto-detected Project Information** (no need to ask):
+
+- Tech stack (from CLAUDE.md, package.json, requirements.txt, etc.)
+- Framework versions (from CLAUDE.md, config files)
+- Project structure (from file system)
+- Existing code conventions (from CLAUDE.md, config files and existing code)
+- Development commands (from CLAUDE.md, such as build, test, typecheck)
+
+#### Execution Steps
 
 - Analyze task requirements and constraints
+- Perform requirement completeness scoring (show specific scores)
 - Identify key objectives and success criteria
 - Gather necessary technical context
 - Use MCP services for additional information if needed
 
 ### 💡 Phase 2: Solution Ideation
 
-**[Mode: Ideate]** - Designing solution approaches:
+[Mode: Ideate] - Designing solution approaches:
 
 - Generate multiple feasible solutions
 - Evaluate pros and cons of each approach
@@ -127,7 +189,7 @@ Starting structured development workflow with quality gates...
 
 ### 📋 Phase 3: Detailed Planning
 
-**[Mode: Plan]** - Creating execution roadmap:
+[Mode: Plan] - Creating execution roadmap:
 
 - Break down solution into atomic, executable steps
 - Define file structure, functions/classes, and logic overview
@@ -137,7 +199,7 @@ Starting structured development workflow with quality gates...
 
 ### ⚡ Phase 4: Implementation
 
-**[Mode: Execute]** - Code development:
+[Mode: Execute] - Code development:
 
 - Implement according to approved plan
 - Follow development best practices
@@ -147,7 +209,7 @@ Starting structured development workflow with quality gates...
 
 ### 🚀 Phase 5: Code Optimization
 
-**[Mode: Optimize]** - Quality improvement:
+[Mode: Optimize] - Quality improvement:
 
 - Automatically analyze implemented code
 - Identify redundant, inefficient, or problematic code
@@ -156,7 +218,7 @@ Starting structured development workflow with quality gates...
 
 ### ✅ Phase 6: Quality Review
 
-**[Mode: Review]** - Final assessment:
+[Mode: Review] - Final assessment:
 
 - Compare results against original plan
 - Identify any remaining issues or improvements

package/templates/zh-CN/commands/feat.md

@@ -1,5 +1,5 @@
 ---
-description: 新增功能
+description: '用于新增功能开发的命令，支持完整的开发流程和工具集成'
 
 allowed-tools:
   - Task

package/templates/zh-CN/commands/workflow.md

@@ -1,5 +1,5 @@
 ---
-description: 'Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers'
+description: '专业AI编程助手，提供结构化六阶段开发工作流（研究→构思→计划→执行→优化→评审），适用于专业开发者'
 allowed-tools:
   - Task
   - Bash
@@ -47,7 +47,7 @@ allowed-tools:
 
 [核心工作流详解]
 
-1. `[模式：研究]`：理解需求。
+1. `[模式：研究]`：理解需求并评估完整性（0-10 分），低于 7 分时主动要求补充关键信息。
 2. `[模式：构思]`：提供至少两种可行方案及评估（例如：`方案 1：描述`）。
 3. `[模式：计划]`：将选定方案细化为详尽、有序、可执行的步骤清单（含原子操作：文件、函数/类、逻辑概要；预期结果；新库用 `Context7` 查询）。不写完整代码。完成后请求用户批准。
 4. `[模式：执行]`：必须用户批准方可执行。严格按计划编码执行。计划简要（含上下文和计划）存入当前项目根目录的`.claude/plan/任务名.md`。关键步骤后及完成时请求用户反馈。
@@ -74,16 +74,77 @@ allowed-tools:
 
 ### 🔍 阶段 1：研究与分析
 
-**[模式：研究]** - 理解需求并收集上下文：
+[模式：研究] - 理解需求并收集上下文：
+
+#### 需求完整性评分（0-10 分）
+
+评分维度：
+
+- **目标明确性**（0-3 分）：任务目标是否清晰具体，要解决什么问题
+- **预期结果**（0-3 分）：成功标准和交付物是否明确定义
+- **边界范围**（0-2 分）：任务范围和边界是否清楚
+- **约束条件**（0-2 分）：时间、性能、业务限制等是否说明
+
+注：技术栈、框架版本等信息将从项目自动识别，不计入评分
+
+**评分规则**：
+
+- 9-10 分：需求非常完整，可直接进入下一阶段
+- 7-8 分：需求基本完整，建议补充个别细节
+- 5-6 分：需求有明显缺失，必须补充关键信息
+- 0-4 分：需求过于模糊，需要重新描述
+
+**当评分低于 7 分时，主动提出补充问题**：
+
+- 识别缺失的关键信息维度
+- 针对每个缺失维度提出 1-2 个具体问题
+- 提供示例帮助用户理解需要的信息类型
+- 等待用户补充后重新评分
+
+**评分示例**：
+
+```
+用户需求："帮我优化代码"
+评分分析：
+- 目标明确性：0/3分（未说明优化什么代码、解决什么问题）
+- 预期结果：0/3分（未定义优化成功标准、期望达到什么效果）
+- 边界范围：1/2分（只知道是代码优化，但范围不明）
+- 约束条件：0/2分（无性能指标、时间限制说明）
+总分：1/10 - 需要大量补充信息
+
+需要补充的问题：
+1. 请问您要优化哪个文件或模块的代码？
+2. 当前存在什么具体问题需要优化？
+3. 期望优化后达到什么效果（如响应时间提升、代码量减少等）？
+4. 有具体的性能指标或时间要求吗？
+```
+
+**常用补充问题模板**：
+
+- 目标类："您希望实现什么具体功能/效果？" "当前存在什么具体问题？"
+- 结果类："如何判断任务成功完成？" "期望的输出/效果是什么？"
+- 范围类："需要处理哪些具体文件/模块？" "不需要包含什么？"
+- 约束类："时间要求是怎样的？" "有什么业务限制或性能要求？"
+
+**自动获取的项目信息**（不需要询问）：
+
+- 技术栈（从 CLAUDE.md、package.json、requirements.txt 等获取）
+- 框架版本（从 CLAUDE.md、配置文件获取）
+- 项目结构（从文件系统获取）
+- 现有代码规范（从 CLAUDE.md、配置文件和现有代码获取）
+- 开发命令（从 CLAUDE.md 获取，如构建、测试、类型检查等）
+
+#### 执行步骤
 
 - 分析任务需求和约束
+- 进行需求完整性评分（显示具体得分）
 - 识别关键目标和成功标准
 - 收集必要的技术上下文
 - 如需要，使用 MCP 服务获取额外信息
 
 ### 💡 阶段 2：方案构思
 
-**[模式：构思]** - 设计解决方案：
+[模式：构思] - 设计解决方案：
 
 - 生成多个可行的解决方案
 - 评估每种方法的优缺点
@@ -92,7 +153,7 @@ allowed-tools:
 
 ### 📋 阶段 3：详细规划
 
-**[模式：计划]** - 创建执行路线图：
+[模式：计划] - 创建执行路线图：
 
 - 将解决方案分解为原子的、可执行的步骤
 - 定义文件结构、函数/类和逻辑概述
@@ -102,7 +163,7 @@ allowed-tools:
 
 ### ⚡ 阶段 4：实施
 
-**[模式：执行]** - 代码开发：
+[模式：执行] - 代码开发：
 
 - 根据批准的计划实施
 - 遵循开发最佳实践
@@ -112,7 +173,7 @@ allowed-tools:
 
 ### 🚀 阶段 5：代码优化
 
-**[模式：优化]** - 质量改进：
+[模式：优化] - 质量改进：
 
 - 自动分析已实现的代码
 - 识别冗余、低效或有问题的代码
@@ -121,7 +182,7 @@ allowed-tools:
 
 ### ✅ 阶段 6：质量审查
 
-**[模式：评审]** - 最终评估：
+[模式：评审] - 最终评估：
 
 - 将结果与原始计划进行比较
 - 识别任何剩余的问题或改进