catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-12 02:37:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: Remove deprecated CLI commands, clarify semantic invocation

Browse Source 
Addresses issue #33 - /cli:mode:bug-diagnosis command not found

Changes:
- Remove deprecated /cli:* commands (/cli:analyze, /cli:chat, /cli:execute,
  /cli:codex-execute, /cli:discuss-plan, /cli:mode:*) from documentation
- Only /cli:cli-init remains as the sole CLI command
- Update all references to use /workflow:lite-plan, /workflow:lite-fix
- Clarify that CLI tools are now invoked through semantic invocation
  (natural language) - Claude auto-selects Gemini/Qwen/Codex with templates
- Update COMMAND_SPEC.md, COMMAND_REFERENCE.md, GETTING_STARTED*.md,
  FAQ.md, WORKFLOW_DECISION_GUIDE*.md, workflow-architecture.md

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-12-03 23:05:40 +08:00
parent c43a72ef46
commit 0f9adc59f9
8 changed files with 92 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.claude/workflows/workflow-architecture.md
View File

@@ -782,15 +782,11 @@ All workflows use the same file structure definition regardless of complexity. *
**Examples**: **Examples**:
*Analysis Commands (read-only):* *Workflow Commands (lightweight):*
- `/cli:analyze "security"` (no session) → `.scratchpad/analyze-security-20250105-143022.md` - `/workflow:lite-plan "feature idea"` (exploratory) → `.scratchpad/lite-plan-feature-idea-20250105-143110.md`
- `/cli:chat "build process"` (unrelated to active session) → `.scratchpad/chat-build-process-20250105-143045.md` - `/workflow:lite-fix "bug description"` (bug fixing) → `.scratchpad/lite-fix-bug-20250105-143130.md`
- `/cli:mode:plan "feature idea"` (exploratory) → `.scratchpad/plan-feature-idea-20250105-143110.md`
- `/cli:mode:code-analysis "trace auth flow"` (no session) → `.scratchpad/code-analysis-auth-flow-20250105-143130.md`
*Implementation Commands (⚠️ modifies code):* > **Note**: Direct CLI commands (`/cli:analyze`, `/cli:execute`, etc.) have been replaced by semantic invocation and workflow commands.
- `/cli:execute "implement JWT auth"` (no session) → `.scratchpad/execute-jwt-auth-20250105-143200.md`
- `/cli:codex-execute "refactor API layer"` (no session) → `.scratchpad/codex-execute-api-refactor-20250105-143230.md`
**Maintenance**: **Maintenance**:
- Periodically review and clean up old scratchpad files - Periodically review and clean up old scratchpad files

14
COMMAND_REFERENCE.md
View File

@@ -4,21 +4,13 @@ This document provides a comprehensive reference for all commands available in t
> **Version 5.9.6 Update**: Enhanced review cycle with dashboards, optimized lite-plan with parallel execution, and added lite-fix workflow for intelligent bug diagnosis. > **Version 5.9.6 Update**: Enhanced review cycle with dashboards, optimized lite-plan with parallel execution, and added lite-fix workflow for intelligent bug diagnosis.
## Unified CLI Commands (`/cli:*`) ## CLI Commands (`/cli:*`)
These commands provide direct access to AI tools for quick analysis and interaction without initiating a full workflow.
| Command | Description | | Command | Description |
|---|---| |---|---|
| `/cli:analyze` | Quick codebase analysis using CLI tools (codex/gemini/qwen). |
| `/cli:chat` | Simple CLI interaction command for direct codebase analysis. |
| `/cli:cli-init`| Initialize CLI tool configurations (Gemini and Qwen) based on workspace analysis. | | `/cli:cli-init`| Initialize CLI tool configurations (Gemini and Qwen) based on workspace analysis. |
| `/cli:codex-execute` | Automated task decomposition and execution with Codex using resume mechanism. |
| `/cli:discuss-plan` | Orchestrates an iterative, multi-model discussion for planning and analysis without implementation. | > **Note**: For analysis, planning, and bug fixing, use workflow commands (`/workflow:lite-plan`, `/workflow:lite-fix`) or semantic invocation through natural language.
| `/cli:execute` | Auto-execution of implementation tasks with YOLO permissions and intelligent context inference. |
| `/cli:mode:bug-diagnosis` | Bug analysis and fix suggestions using CLI tools. |
| `/cli:mode:code-analysis` | Deep code analysis and debugging using CLI tools with specialized template. |
| `/cli:mode:plan` | Project planning and architecture analysis using CLI tools. |
## Workflow Commands (`/workflow:*`) ## Workflow Commands (`/workflow:*`)

87
COMMAND_SPEC.md
View File

@@ -191,25 +191,7 @@ Commands for creating, listing, and managing workflow sessions.
## 5. CLI Commands ## 5. CLI Commands
Direct access to AI tools for analysis and code interaction without a full workflow structure. CLI tool configuration commands.
### **/cli:analyze**
- **Syntax**: `/cli:analyze [--agent] [--tool codex|gemini|qwen] [--enhance] <analysis target>`
- **Responsibilities**: Performs read-only codebase analysis. Can operate in standard mode (direct tool call) or agent mode (`@cli-execution-agent`) for automated context discovery.
- **Agent Calls**: `@cli-execution-agent` (if `--agent` is used).
- **Example**:
```bash
/cli:analyze "authentication patterns"
```
### **/cli:chat**
- **Syntax**: `/cli:chat [--agent] [--tool codex|gemini|qwen] [--enhance] <inquiry>`
- **Responsibilities**: Provides a direct Q&A interface with AI tools for codebase questions. Read-only.
- **Agent Calls**: `@cli-execution-agent` (if `--agent` is used).
- **Example**:
```bash
/cli:chat "how does the caching layer work?"
```
### **/cli:cli-init** ### **/cli:cli-init**
- **Syntax**: `/cli:cli-init [--tool gemini|qwen|all] [--output path] [--preview]` - **Syntax**: `/cli:cli-init [--tool gemini|qwen|all] [--output path] [--preview]`
@@ -220,59 +202,7 @@ Direct access to AI tools for analysis and code interaction without a full workf
/cli:cli-init /cli:cli-init
``` ```
### **/cli:codex-execute** > **Note**: For analysis, planning, and bug fixing, use workflow commands (`/workflow:lite-plan`, `/workflow:lite-fix`) or semantic invocation through natural language. Claude will automatically use appropriate CLI tools (Gemini/Qwen/Codex) with templates as needed.
- **Syntax**: `/cli:codex-execute [--verify-git] <description|task-id>`
- **Responsibilities**: Orchestrates automated task decomposition and sequential execution using Codex. It uses the `resume --last` mechanism for context continuity between subtasks.
- **Agent Calls**: None directly, but orchestrates `codex` CLI tool.
- **Example**:
```bash
/cli:codex-execute "implement user authentication system"
```
### **/cli:discuss-plan**
- **Syntax**: `/cli:discuss-plan [--topic '...'] [--task-id '...'] [--rounds N] <input>`
- **Responsibilities**: Orchestrates an iterative, multi-model (Gemini, Codex, Claude) discussion to perform deep analysis and planning without modifying code.
- **Agent Calls**: None directly, but orchestrates `gemini` and `codex` CLI tools.
- **Example**:
```bash
/cli:discuss-plan --topic "Design a new caching layer"
```
### **/cli:execute**
- **Syntax**: `/cli:execute [--agent] [--tool codex|gemini|qwen] [--enhance] <description|task-id>`
- **Responsibilities**: Executes implementation tasks with auto-approval (`YOLO` mode). **MODIFIES CODE**.
- **Agent Calls**: `@cli-execution-agent` (if `--agent` is used).
- **Example**:
```bash
/cli:execute "implement JWT authentication with middleware"
```
### **/cli:mode:bug-diagnosis**
- **Syntax**: `/cli:mode:bug-diagnosis [--tool ...] [--enhance] [--cd path] <bug description>`
- **Responsibilities**: Performs systematic bug analysis using the `bug-fix.md` template. Read-only.
- **Agent Calls**: `@cli-execution-agent` (default).
- **Example**:
```bash
/cli:mode:bug-diagnosis "null pointer error in login flow"
```
### **/cli:mode:code-analysis**
- **Syntax**: `/cli:mode:code-analysis [--agent] [--tool ...] [--enhance] [--cd path] <analysis target>`
- **Responsibilities**: Performs deep code analysis and execution path tracing using the `code-analysis.md` template. Read-only.
- **Agent Calls**: `@cli-execution-agent` (if `--agent` is used).
- **Example**:
```bash
/cli:mode:code-analysis "trace authentication execution flow"
```
### **/cli:mode:plan**
- **Syntax**: `/cli:mode:plan [--agent] [--tool ...] [--enhance] [--cd path] <topic>`
- **Responsibilities**: Performs comprehensive planning and architecture analysis using the `plan.md` template. Read-only.
- **Agent Calls**: `@cli-execution-agent` (if `--agent` is used).
- **Example**:
```bash
/cli:mode:plan "design user dashboard architecture"
```
--- ---
@@ -380,13 +310,14 @@ Commands for managing individual tasks within a workflow session.
``` ```
### **/enhance-prompt** ### **/enhance-prompt**
- **Syntax**: `/enhance-prompt <user input>` - **Syntax**: `/enhance-prompt <user input>` or use `-e` flag in conversation
- **Responsibilities**: A system-level skill that enhances a user's prompt by adding context from session memory and codebase analysis. It is typically triggered automatically by other commands that include the `--enhance` flag. - **Responsibilities**: A system-level skill that enhances a user's prompt by adding context from session memory and codebase analysis. It is typically triggered by the `-e` flag in natural conversation.
- **Skill Invocation**: This is a core skill, invoked when `--enhance` is used. - **Skill Invocation**: This is a core skill, invoked when `-e` is used in conversation.
- **Agent Calls**: None. - **Agent Calls**: None.
- **Example (as part of another command)**: - **Example (in natural conversation)**:
```bash ```
/cli:execute --enhance "fix the login button" User: "fix the login button -e"
→ Prompt-enhancer expands and enhances the request
``` ```
--- ---

24
FAQ.md
View File

@@ -248,16 +248,16 @@ CCW-help
### What's the difference between `/cli:*` and `/workflow:*` commands? ### What's the difference between `/cli:*` and `/workflow:*` commands?
**`/cli:*` commands**: **`/cli:*` commands**:
- Direct access to external AI tools - CLI tool configuration
- No workflow session required - Example: `/cli:cli-init` (initialize Gemini/Qwen configurations)
- Quick one-off tasks
- Examples: `/cli:analyze`, `/cli:chat`
**`/workflow:*` commands**: **`/workflow:*` commands**:
- Multi-phase orchestration - Multi-phase orchestration
- Session-based - Session-based
- Complex development workflows - Complex development workflows
- Examples: `/workflow:plan`, `/workflow:execute` - Examples: `/workflow:plan`, `/workflow:lite-plan`, `/workflow:lite-fix`
> **Note**: Most CLI commands have been replaced by **semantic invocation**. Simply describe your needs in natural language, and Claude will automatically use the appropriate tools.
### How do I use command flags? ### How do I use command flags?
@@ -270,9 +270,6 @@ Most commands support flags for customization:
# With CLI execution flag # With CLI execution flag
/workflow:plan --cli-execute "Feature description" /workflow:plan --cli-execute "Feature description"
# With tool selection
/cli:analyze --tool gemini "Code analysis"
# With multiple flags # With multiple flags
/workflow:ui-design:explore-auto --prompt "Login page" --style-variants 3 --layout-variants 2 /workflow:ui-design:explore-auto --prompt "Login page" --style-variants 3 --layout-variants 2
``` ```
@@ -281,17 +278,12 @@ Most commands support flags for customization:
**Yes!** Claude understands semantic invocation: **Yes!** Claude understands semantic invocation:
Instead of: Instead of using specific commands, you can say:
```bash
/cli:analyze --tool gemini "Authentication module"
```
You can say:
``` ```
"Use Gemini to analyze the authentication module architecture" "Use Gemini to analyze the authentication module architecture"
``` ```
Claude will automatically execute the appropriate command. Claude will automatically select and execute the appropriate CLI tools (Gemini/Qwen/Codex) with optimized templates.
### What does the `-e` or `--enhance` flag do? ### What does the `-e` or `--enhance` flag do?
@@ -303,8 +295,6 @@ User: "Analyze authentication module -e"
Claude will expand and enhance your request for better results. Claude will expand and enhance your request for better results.
**Note**: `--enhance` in CLI commands (e.g., `/cli:analyze --enhance`) is a different feature built into CLI tools.
--- ---
## 📦 Sessions & Tasks ## 📦 Sessions & Tasks

66
GETTING_STARTED.md
View File

@@ -178,62 +178,36 @@ After planning, validate your implementation plan for consistency and completene
Quick bug analysis and fix workflow: Quick bug analysis and fix workflow:
```bash ```bash
# Analyze the bug # Lightweight bug fix workflow with intelligent diagnosis
/cli:mode:bug-diagnosis "Incorrect success message with wrong password" /workflow:lite-fix "Incorrect success message with wrong password"
# Claude will analyze and then directly implement the fix based on the analysis # Claude will analyze severity, diagnose root cause, and implement the fix
``` ```
--- ---
## 🔧 Workflow-Free Usage: Standalone Tools ## 🔧 Lightweight Commands
Beyond the full workflow mode, CCW provides standalone CLI tools and commands suitable for quick analysis, ad-hoc queries, and routine maintenance tasks. Beyond the full workflow mode, CCW provides lightweight commands suitable for quick analysis and routine tasks.
### Direct CLI Tool Invocation ### Workflow Commands for Quick Tasks
CCW supports direct invocation of external AI tools (Gemini, Qwen, Codex) through a unified CLI interface without creating workflow sessions. Use workflow commands for integrated planning and bug fixing:
#### Code Analysis
Quickly analyze project code structure and architectural patterns:
```bash ```bash
# Code analysis with Gemini # Lightweight planning workflow
/cli:analyze --tool gemini "Analyze authentication module architecture" /workflow:lite-plan "Design a scalable microservices architecture"
# Code quality analysis with Qwen # Bug fix workflow with intelligent diagnosis
/cli:analyze --tool qwen "Review database model design for best practices" /workflow:lite-fix "Analyze potential causes of memory leak"
# Initialize CLI tool configurations
/cli:cli-init
``` ```
#### Interactive Chat ### Semantic Tool Invocation (Replaces Direct CLI Commands)
Direct interactive dialogue with AI tools: > **Important**: Direct CLI commands (`/cli:analyze`, `/cli:chat`, `/cli:execute`, etc.) have been replaced by **semantic invocation**. Simply describe your needs in natural language, and Claude will automatically select and execute the appropriate CLI tools (Gemini/Qwen/Codex) with optimized templates.
```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 Tool Invocation
Users can tell Claude to use specific tools through natural language, and Claude will understand the intent and automatically execute the appropriate commands. Users can tell Claude to use specific tools through natural language, and Claude will understand the intent and automatically execute the appropriate commands.
@@ -381,13 +355,7 @@ User: "Analyze authentication module -e"
→ AI uses prompt-enhancer skill to expand the request → AI uses prompt-enhancer skill to expand the request
``` ```
**CLI Command Enhancement** (built-in CLI feature): **Important Note**: The `-e` flag works in natural conversation to trigger the prompt-enhancer skill.
```bash
# The --enhance flag here is a CLI parameter, not a skill trigger
/cli:analyze --enhance "check for security issues"
```
**Important Note**: The `-e` flag works in natural conversation, but `--enhance` in CLI commands is a separate enhancement mechanism, not the skill system.
--- ---

66
GETTING_STARTED_CN.md
View File

@@ -188,62 +188,36 @@
快速 Bug 分析和修复工作流： 快速 Bug 分析和修复工作流：
```bash ```bash
# 分析 Bug # 轻量级 Bug 修复工作流，带智能诊断
/cli:mode:bug-diagnosis "密码错误时仍显示成功消息" /workflow:lite-fix "密码错误时仍显示成功消息"
# Claude 会分析后直接根据分析结果实现修复 # Claude 会分析严重程度，诊断根因，并实现修复
``` ```
--- ---
## 🔧 无工作流协作：独立工具使用 ## 🔧 轻量级命令
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。 除了完整的工作流模式，CCW 还提供轻量级命令，适合快速分析和日常任务。
### CLI 工具直接调用 ### 快速任务工作流命令
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。 使用工作流命令进行集成规划和 Bug 修复：
#### 代码分析
快速分析项目代码结构和架构模式：
```bash ```bash
# 使用 Gemini 进行代码分析 # 轻量级规划工作流
/cli:analyze --tool gemini "分析认证模块的架构设计" /workflow:lite-plan "设计一个可扩展的微服务架构"
# 使用 Qwen 分析代码质量 # 带智能诊断的 Bug 修复工作流
/cli:analyze --tool qwen "检查数据库模型的设计是否合理" /workflow:lite-fix "分析内存泄漏问题的可能原因"
# 初始化 CLI 工具配置
/cli:cli-init
``` ```
#### 交互式对话 ### 语义调用（替代直接 CLI 命令）
与 AI 工具进行直接交互式对话： > **重要**: 直接 CLI 命令（`/cli:analyze`、`/cli:chat`、`/cli:execute` 等）已被**语义调用**替代。只需使用自然语言描述您的需求，Claude 会自动选择并执行合适的 CLI 工具（Gemini/Qwen/Codex）和优化的模板。
```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-diagnosis --tool gemini "分析内存泄漏问题的可能原因"
```
### 工具语义调用
用户可以通过自然语言告诉 Claude 使用特定工具完成任务，Claude 会理解意图并自动执行相应的命令。 用户可以通过自然语言告诉 Claude 使用特定工具完成任务，Claude 会理解意图并自动执行相应的命令。
@@ -391,13 +365,7 @@ CCW 使用分层的 CLAUDE.md 文档系统维护项目上下文。定期更新
→ AI 使用 prompt-enhancer 技能扩展请求 → AI 使用 prompt-enhancer 技能扩展请求
``` ```
**CLI 命令增强** (CLI 内置功能): **重要说明**：`-e` 标识符用于在自然对话中触发 prompt-enhancer 技能。
```bash
# 这里的 --enhance 标识符是 CLI 参数,不是技能触发器
/cli:analyze --enhance "检查安全问题"
```
**重要说明**：`-e` 标识符仅在自然对话中有效,而 CLI 命令中的 `--enhance` 是独立的增强机制,与技能系统无关。
--- ---

45
WORKFLOW_DECISION_GUIDE.md
View File

@@ -16,7 +16,7 @@ flowchart TD
BugFix --> BugSeverity{了解问题根因?} BugFix --> BugSeverity{了解问题根因?}
BugSeverity -->|清楚| LiteFix[/ /workflow:lite-fix<br>标准Bug修复 /] BugSeverity -->|清楚| LiteFix[/ /workflow:lite-fix<br>标准Bug修复 /]
BugSeverity -->|生产事故| HotFix[/ /workflow:lite-fix --hotfix<br>热修复模式 /] BugSeverity -->|生产事故| HotFix[/ /workflow:lite-fix --hotfix<br>热修复模式 /]
BugSeverity -->|不清楚| BugDiag[/ /cli:mode:bug-diagnosis<br>先诊断根因 /] BugSeverity -->|不清楚| BugDiag[/ /workflow:lite-fix<br>自动诊断根因 /]
BugDiag --> LiteFix BugDiag --> LiteFix
LiteFix --> BugComplete[Bug修复完成] LiteFix --> BugComplete[Bug修复完成]
@@ -142,7 +142,7 @@ flowchart TD
|------|------|------| |------|------|------|
| 🐛 **标准Bug修复** | `/workflow:lite-fix "bug描述"` | 自适应严重性评估，完整诊断→影响评估→修复→验证 | | 🐛 **标准Bug修复** | `/workflow:lite-fix "bug描述"` | 自适应严重性评估，完整诊断→影响评估→修复→验证 |
| 🔥 **生产热修复** | `/workflow:lite-fix --hotfix "bug描述"` | 最小化诊断，快速修复，自动生成跟进任务 | | 🔥 **生产热修复** | `/workflow:lite-fix --hotfix "bug描述"` | 最小化诊断，快速修复，自动生成跟进任务 |
| ❓ **根因不清楚** | `/cli:mode:bug-diagnosis` → `/workflow:lite-fix` | 先深度诊断，再执行修复 | | ❓ **根因不清楚** | `/workflow:lite-fix` | 自动进行深度诊断并执行修复 |
| ✅ **功能开发** | 继续后续流程 | 不是Bug修复，按正常开发流程 | | ✅ **功能开发** | 继续后续流程 | 不是Bug修复，按正常开发流程 |
**Lite-Fix 工作流特性**: **Lite-Fix 工作流特性**:
@@ -171,16 +171,16 @@ flowchart TD
→ 最小化诊断 → 假设 Critical → 手术式修复 → 烟雾测试 → 最小化诊断 → 假设 Critical → 手术式修复 → 烟雾测试
→ 自动生成: 全面修复任务（3天内）+ 事后分析（1周内） → 自动生成: 全面修复任务（3天内）+ 事后分析（1周内）
# 根因不清楚（先诊断） # 根因不清楚（lite-fix 自动诊断）
/cli:mode:bug-diagnosis --tool gemini "购物车随机丢失商品" /workflow:lite-fix "购物车随机丢失商品"
→ 深度诊断报告 → /workflow:lite-fix "修复购物车状态同步问题" → 自动深度诊断 → 识别根因 → 实现修复
``` ```
**何时使用 lite-fix**: **何时使用 lite-fix**:
- ✅ 任何有明确症状的Bug（自动适应严重性） - ✅ 任何有明确症状的Bug（自动适应严重性）
- ✅ 本地化修复（1-5个文件） - ✅ 本地化修复（1-5个文件）
- ✅ 生产事故（使用 `--hotfix` 模式） - ✅ 生产事故（使用 `--hotfix` 模式）
- ❌ 根因完全不明 → 先用 `/cli:mode:bug-diagnosis` - ✅ 根因不清楚（自动进行深度诊断）
- ❌ 需要架构变更 → 用 `/workflow:plan --mode bugfix` - ❌ 需要架构变更 → 用 `/workflow:plan --mode bugfix`
--- ---
@@ -416,33 +416,24 @@ Phase 1: Gemini 分析 ──┐
→ Claude Code 自动生成：codex -C src/auth --full-auto exec "实现注册" → Claude Code 自动生成：codex -C src/auth --full-auto exec "实现注册"
``` ```
**方式二：直接命令调用**
```bash
# 通过 Slash 命令精准调用
/cli:chat --tool gemini "解释这个算法"
/cli:analyze --tool qwen "分析性能瓶颈"
/cli:execute --tool codex "优化查询性能"
```
--- ---
#### 🔗 CLI 结果作为上下文（Memory） #### 🔗 语义调用与结果上下文（Memory）
CLI 工具的分析结果可以被保存并作为后续操作的上下文（memory），实现智能化的工作流程： 通过自然语言描述，Claude 会自动选择并执行适当的 CLI 工具（Gemini/Qwen/Codex），分析结果作为后续操作的上下文。
**1. 结果持久化** **1. 语义调用示例**
```bash ```bash
# CLI 执行结果自动保存到会话目录 # 用自然语言描述需求，Claude 自动选择工具
/cli:chat --tool gemini "分析认证模块架构" "使用 gemini 分析认证模块架构"
→ 保存到：.workflow/active/WFS-xxx/.chat/chat-[timestamp].md → Claude 自动执行 Gemini CLI 并保存结果
/cli:analyze --tool qwen "评估性能瓶颈" "让 qwen 评估性能瓶颈"
→ 保存到：.workflow/active/WFS-xxx/.chat/analyze-[timestamp].md → Claude 自动执行 Qwen CLI 并保存结果
/cli:execute --tool codex "实现功能" "用 codex 实现这个功能"
→ 保存到：.workflow/active/WFS-xxx/.chat/execute-[timestamp].md → Claude 自动执行 Codex CLI
``` ```
**2. 结果作为规划依据** **2. 结果作为规划依据**
@@ -476,8 +467,8 @@ CLI 工具的分析结果可以被保存并作为后续操作的上下文（memo
```bash ```bash
# 引用历史会话的分析结果 # 引用历史会话的分析结果
/cli:execute --tool codex "参考 WFS-2024-001 中的架构分析，实现新的支付模块" "参考 WFS-2024-001 中的架构分析，用 codex 实现新的支付模块"
→ 系统自动加载指定会话的上下文 → Claude 自动加载指定会话的上下文
→ 基于历史分析进行实现 → 基于历史分析进行实现
``` ```

46
WORKFLOW_DECISION_GUIDE_EN.md
View File

@@ -348,33 +348,24 @@ Phase 1: Gemini analysis ──┐
→ Claude Code auto-generates: codex -C src/auth --full-auto exec "Implement registration" → Claude Code auto-generates: codex -C src/auth --full-auto exec "Implement registration"
``` ```
**Method 2: Direct Command Invocation**
```bash
# Precise invocation via Slash commands
/cli:chat --tool gemini "Explain this algorithm"
/cli:analyze --tool qwen "Analyze performance bottlenecks"
/cli:execute --tool codex "Optimize query performance"
```
--- ---
#### 🔗 CLI Results as Context (Memory) #### 🔗 Semantic Invocation & Results Context (Memory)
CLI tool analysis results can be saved and used as context (memory) for subsequent operations, enabling intelligent workflows: Through natural language, Claude automatically selects and executes appropriate CLI tools (Gemini/Qwen/Codex), with results serving as context for subsequent operations.
**1. Result Persistence** **1. Semantic Invocation Examples**
```bash ```bash
# CLI execution results automatically saved to session directory # Describe needs in natural language, Claude auto-selects tools
/cli:chat --tool gemini "Analyze authentication module architecture" "Use gemini to analyze authentication module architecture"
→ Saved to: .workflow/active/WFS-xxx/.chat/chat-[timestamp].md → Claude auto-executes Gemini CLI and saves results
/cli:analyze --tool qwen "Evaluate performance bottlenecks" "Have qwen evaluate performance bottlenecks"
→ Saved to: .workflow/active/WFS-xxx/.chat/analyze-[timestamp].md → Claude auto-executes Qwen CLI and saves results
/cli:execute --tool codex "Implement feature" "Use codex to implement this feature"
→ Saved to: .workflow/active/WFS-xxx/.chat/execute-[timestamp].md → Claude auto-executes Codex CLI
``` ```
**2. Results as Planning Basis** **2. Results as Planning Basis**
@@ -408,8 +399,8 @@ Have codex synthesize above Gemini and Qwen analyses to implement optimal soluti
```bash ```bash
# Reference historical session analysis results # Reference historical session analysis results
/cli:execute --tool codex "Refer to architecture analysis in WFS-2024-001, implement new payment module" "Refer to architecture analysis in WFS-2024-001, use codex to implement new payment module"
→ System automatically loads specified session context → Claude automatically loads specified session context
→ Implement based on historical analysis → Implement based on historical analysis
``` ```
@@ -630,16 +621,13 @@ Use gemini to review code quality
### Scenario D: Bug Fixing ### Scenario D: Bug Fixing
```bash ```bash
# 1. Diagnosis # 1. Intelligent bug fix workflow (includes diagnosis)
/cli:mode:bug-diagnosis --tool gemini "User login fails with token expired error" /workflow:lite-fix "User login fails with token expired error"
# 2. Quick fix # 2. Test fix (if needed)
/workflow:lite-plan "Fix JWT token expiration validation logic"
# 3. Test fix
/workflow:test-cycle-execute /workflow:test-cycle-execute
# 4. Complete # 3. Complete
``` ```
--- ---
@@ -654,7 +642,7 @@ Use gemini to review code quality
| ❓ Know what, don't know how | `/workflow:brainstorm:auto-parallel "Design technical solution"` | | ❓ Know what, don't know how | `/workflow:brainstorm:auto-parallel "Design technical solution"` |
| ✅ Know what and how | `/workflow:plan "Specific implementation description"` | | ✅ Know what and how | `/workflow:plan "Specific implementation description"` |
| ⚡ Simple, clear small task | `/workflow:lite-plan "Task description"` | | ⚡ Simple, clear small task | `/workflow:lite-plan "Task description"` |
| 🐛 Bug fixing | `/cli:mode:bug-diagnosis` + `/workflow:lite-plan` | | 🐛 Bug fixing | `/workflow:lite-fix "bug description"` |
### Choose by Project Phase ### Choose by Project Phase