docs: add workflow-free standalone tools section to Getting Started guides

Added comprehensive "Workflow-Free Usage" section covering:

**Direct CLI Tool Usage:**
- Code analysis with /cli:analyze
- Interactive chat with /cli:chat
- Specialized modes (plan, code-analysis, bug-index)

**Semantic Gemini Invocation:**
- Read-only mode for exploration and analysis
- Write mode for document generation
- Context optimization techniques with cd

**Memory Management:**
- Full project index rebuild with /update-memory-full
- Incremental updates with /update-memory-related
- Execution timing recommendations
- Memory quality impact table

**CLI Tool Initialization:**
- Auto-configuration with /cli:cli-init
- Tool-specific setup options

Documentation style:
- Objective tone without first-person pronouns
- Clear command examples with copy-paste readiness
- Practical execution timing guidance
- Visual tables for decision making

Files updated:
- GETTING_STARTED.md (English, +167 lines)
- GETTING_STARTED_CN.md (Chinese, +167 lines)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-10-13 11:19:39 +08:00
parent 8dc7abf707
commit 9f4b0acca7
2 changed files with 336 additions and 0 deletions

View File

@@ -122,6 +122,174 @@ CCW can help you analyze and fix bugs.
---
## 🔧 Workflow-Free Usage: Standalone Tools
Beyond the full workflow mode, CCW provides standalone CLI tools and commands suitable for quick analysis, ad-hoc queries, and routine maintenance tasks.
### Direct CLI Tool Invocation
CCW supports direct invocation of external AI tools (Gemini, Qwen, Codex) through a unified CLI interface without creating workflow sessions.
#### Code Analysis
Quickly analyze project code structure and architectural patterns:
```bash
# Code analysis with Gemini
/cli:analyze --tool gemini "Analyze authentication module architecture"
# Code quality analysis with Qwen
/cli:analyze --tool qwen "Review database model design for best practices"
```
#### Interactive Chat
Direct interactive dialogue with AI tools:
```bash
# Chat with Gemini
/cli:chat --tool gemini "Explain React Hook use cases"
# Discuss implementation with Codex
/cli:chat --tool codex "How to optimize this query performance"
```
#### Specialized Analysis Modes
Use specific analysis modes for in-depth exploration:
```bash
# Architecture planning mode
/cli:mode:plan --tool gemini "Design a scalable microservices architecture"
# Deep code analysis
/cli:mode:code-analysis --tool qwen "Analyze utility functions in src/utils/"
# Bug analysis mode
/cli:mode:bug-index --tool gemini "Analyze potential causes of memory leak"
```
### Semantic Gemini Tool Invocation
CCW provides a convenient Gemini Wrapper script for semantic project analysis and document generation.
#### Basic Analysis (Read-only Mode)
By default, Gemini runs in read-only mode, suitable for code exploration and architectural analysis:
```bash
# Execute analysis in project root
cd /path/to/project && ~/.claude/scripts/gemini-wrapper -p "
PURPOSE: Analyze project modular architecture
TASK: Identify core modules and their dependencies
CONTEXT: @{src/**/*.ts,CLAUDE.md}
EXPECTED: Generate architecture diagram and module documentation
RULES: Focus on module boundaries and interface design
"
```
#### Document Generation (Write Mode)
When file generation or modification is needed, write mode must be explicitly enabled:
```bash
# Generate API documentation
cd /path/to/project && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
PURPOSE: Generate REST API documentation
TASK: Extract API endpoints from code and generate Markdown docs
MODE: write
CONTEXT: @{src/api/**/*.ts}
EXPECTED: Generate API.md with all endpoint descriptions
RULES: Follow OpenAPI specification format
"
```
#### Context Optimization Techniques
Using `cd` to switch to specific directories optimizes context scope:
```bash
# Analyze only auth module
cd src/auth && ~/.claude/scripts/gemini-wrapper -p "
PURPOSE: Security review of authentication module
TASK: Check JWT implementation and password handling
CONTEXT: @{**/*.ts}
EXPECTED: Security audit report
RULES: Focus on OWASP Top 10 security issues
"
```
### Memory Management: CLAUDE.md Updates
CCW uses a hierarchical CLAUDE.md documentation system to maintain project context. Regular updates to these documents are critical for ensuring high-quality AI outputs.
#### Full Project Index Rebuild
Suitable for large-scale refactoring, architectural changes, or first-time CCW usage:
```bash
# Rebuild entire project documentation index
/update-memory-full
# Use specific tool for indexing
/update-memory-full --tool gemini # Comprehensive analysis (recommended)
/update-memory-full --tool qwen # Architecture focus
/update-memory-full --tool codex # Implementation details
```
**When to Execute**:
- During project initialization
- After major architectural changes
- Weekly routine maintenance
- When AI output drift is detected
#### Incremental Related Module Updates
Suitable for daily development, updating only modules affected by changes:
```bash
# Update recently modified related documentation
/update-memory-related
# Specify tool for update
/update-memory-related --tool gemini
```
**When to Execute**:
- After feature development completion
- After module refactoring
- After API interface updates
- After data model modifications
#### Memory Quality Impact
| Update Frequency | Result |
|-----------------|--------|
| ❌ Never update | Outdated API references, incorrect architectural assumptions, low-quality output |
| ⚠️ Occasional updates | Partial context accuracy, potential inconsistencies |
| ✅ Timely updates | High-quality output, precise context, correct pattern references |
### CLI Tool Initialization
When using external CLI tools for the first time, initialization commands provide quick configuration:
```bash
# Auto-configure all tools
/cli:cli-init
# Configure specific tools only
/cli:cli-init --tool gemini
/cli:cli-init --tool qwen
```
This command will:
- Analyze project structure
- Generate tool configuration files
- Set up `.geminiignore` / `.qwenignore`
- Create context file references
---
## ❓ Troubleshooting
- **Problem: Prompt shows "No active session found"**

View File

@@ -122,6 +122,174 @@ CCW 可以帮助您分析并修复 Bug。
---
## 🔧 无工作流协作:独立工具使用
除了完整的工作流模式CCW 还提供独立的 CLI 工具和命令,适合快速分析、临时查询和日常维护任务。
### CLI 工具直接调用
CCW 支持通过统一的 CLI 接口直接调用外部 AI 工具Gemini、Qwen、Codex无需创建工作流会话。
#### 代码分析
快速分析项目代码结构和架构模式:
```bash
# 使用 Gemini 进行代码分析
/cli:analyze --tool gemini "分析认证模块的架构设计"
# 使用 Qwen 分析代码质量
/cli:analyze --tool qwen "检查数据库模型的设计是否合理"
```
#### 交互式对话
与 AI 工具进行直接交互式对话:
```bash
# 与 Gemini 交互
/cli:chat --tool gemini "解释一下 React Hook 的使用场景"
# 与 Codex 交互讨论实现方案
/cli:chat --tool codex "如何优化这个查询性能"
```
#### 专业模式分析
使用特定的分析模式进行深度探索:
```bash
# 架构分析模式
/cli:mode:plan --tool gemini "设计一个可扩展的微服务架构"
# 深度代码分析
/cli:mode:code-analysis --tool qwen "分析 src/utils/ 目录下的工具函数"
# Bug 分析模式
/cli:mode:bug-index --tool gemini "分析内存泄漏问题的可能原因"
```
### Gemini 工具语义调用
CCW 提供便捷的 Gemini Wrapper 脚本,支持语义化的项目分析和文档生成。
#### 基础分析(只读模式)
默认情况下Gemini 以只读模式运行,适合代码探索和架构分析:
```bash
# 在项目根目录执行分析
cd /path/to/project && ~/.claude/scripts/gemini-wrapper -p "
PURPOSE: 分析项目的模块化架构
TASK: 识别核心模块及其依赖关系
CONTEXT: @{src/**/*.ts,CLAUDE.md}
EXPECTED: 生成架构关系图和模块说明
RULES: 聚焦于模块边界和接口设计
"
```
#### 文档生成(写入模式)
当需要生成或修改文件时,需要显式启用写入模式:
```bash
# 生成 API 文档
cd /path/to/project && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
PURPOSE: 生成 REST API 文档
TASK: 从代码中提取 API 端点并生成 Markdown 文档
MODE: write
CONTEXT: @{src/api/**/*.ts}
EXPECTED: 生成 API.md 文件,包含所有端点说明
RULES: 遵循 OpenAPI 规范格式
"
```
#### 上下文优化技巧
使用 `cd` 切换到特定目录可以优化上下文范围:
```bash
# 只分析 auth 模块
cd src/auth && ~/.claude/scripts/gemini-wrapper -p "
PURPOSE: 审查认证模块的安全性
TASK: 检查 JWT 实现和密码处理
CONTEXT: @{**/*.ts}
EXPECTED: 安全审计报告
RULES: 重点关注 OWASP Top 10 安全问题
"
```
### 内存管理CLAUDE.md 更新
CCW 使用分层的 CLAUDE.md 文档系统维护项目上下文。定期更新这些文档对保证 AI 输出质量至关重要。
#### 完整项目重建索引
适用于大规模重构、架构变更或初次使用 CCW
```bash
# 重建整个项目的文档索引
/update-memory-full
# 使用特定工具进行索引
/update-memory-full --tool gemini # 全面分析(推荐)
/update-memory-full --tool qwen # 架构重点
/update-memory-full --tool codex # 实现细节
```
**执行时机**
- 项目初始化时
- 架构重大变更后
- 每周定期维护
- 发现 AI 输出偏差时
#### 增量更新相关模块
适用于日常开发,只更新变更影响的模块:
```bash
# 更新最近修改相关的文档
/update-memory-related
# 指定工具进行更新
/update-memory-related --tool gemini
```
**执行时机**
- 完成功能开发后
- 重构某个模块后
- 更新 API 接口后
- 修改数据模型后
#### 内存质量的影响
| 更新频率 | 结果 |
|---------|------|
| ❌ 从不更新 | 过时的 API 引用、错误的架构假设、低质量输出 |
| ⚠️ 偶尔更新 | 部分上下文准确、可能出现不一致 |
| ✅ 及时更新 | 高质量输出、精确的上下文、正确的模式引用 |
### CLI 工具初始化
首次使用外部 CLI 工具时,可以使用初始化命令快速配置:
```bash
# 自动配置所有工具
/cli:cli-init
# 只配置特定工具
/cli:cli-init --tool gemini
/cli:cli-init --tool qwen
```
该命令会:
- 分析项目结构
- 生成工具配置文件
- 设置 `.geminiignore` / `.qwenignore`
- 创建上下文文件引用
---
## ❓ 常见问题排查 (Troubleshooting)
- **问题:提示 "No active session found" (未找到活动会话)**