diff --git a/.claude/commands/gemini/chat.md b/.claude/commands/gemini/chat.md
index 7371d935..c4b1df95 100644
--- a/.claude/commands/gemini/chat.md
+++ b/.claude/commands/gemini/chat.md
@@ -1,203 +1,93 @@
 ---
 name: gemini-chat
 parent: /gemini
-description: Single-execution Gemini CLI interaction command with dynamic template selection for codebase analysis
+description: Simple Gemini CLI interaction command for direct codebase analysis
 usage: /gemini:chat "inquiry"
 argument-hint: "your question or analysis request"
 examples:
   - /gemini:chat "analyze the authentication flow"
   - /gemini:chat "how can I optimize this React component performance?"
   - /gemini:chat "review security vulnerabilities in src/auth/"
-  - /gemini:chat "comprehensive code quality assessment"
-allowed-tools: Bash(gemini:*), Bash(~/.claude/scripts/chat-template-load.sh:*)
+allowed-tools: Bash(gemini:*)
 model: sonnet
 ---
 
 ### 🚀 **Command Overview: `/gemini:chat`**
 
-
--   **Type**: Gemini CLI Execution Wrapper
--   **Purpose**: To provide direct interaction with the `gemini` CLI, enhanced with intelligent, dynamic prompt template selection for codebase analysis.
--   **Core Tools**:
-    -   `Bash(gemini:*)`: Executes the external Gemini CLI tool.
-    -   `Bash(~/.claude/scripts/chat-template-load.sh:*)`: Manages all template discovery and selection logic.
+-   **Type**: Basic Gemini CLI Wrapper
+-   **Purpose**: Direct interaction with the `gemini` CLI for simple codebase analysis
+-   **Core Tool**: `Bash(gemini:*)` - Executes the external Gemini CLI tool
 
 ### 📥 **Parameters & Usage**
 
--   **`<inquiry>` (Required)**: Your primary question or analysis request.
--   **`--all-files` (Optional)**: Includes the entire codebase in the analysis context.
--   **`--compress` (Optional)**: Applies context compression for large prompts.
--   **`--save-session` (Optional)**: Saves the full interaction to current workflow session directory.
--   **File References**: Explicitly specify files or patterns within the inquiry using `@{path/to/file}`.
+-   **`<inquiry>` (Required)**: Your question or analysis request
+-   **`--all-files` (Optional)**: Includes the entire codebase in the analysis context
+-   **`--save-session` (Optional)**: Saves the interaction to current workflow session directory
+-   **File References**: Specify files or patterns using `@{path/to/file}` syntax
 
-### 🔄 **Core Execution Workflow**
+### 🔄 **Execution Workflow**
 
-⚠️ **IMPORTANT**: Template selection is **AUTOMATIC** based on input analysis and is the **FIRST STEP** in command execution.
+`Parse Input` **->** `Assemble Context` **->** `Construct Prompt` **->** `Execute Gemini CLI` **->** `(Optional) Save Session`
 
-`Parse Input & Intent` **->** `Auto-Select Template` **->** `Load Selected Template` **->** `Determine Context Needs` **->** `Assemble Context` **->** `Construct Prompt` **->** `Execute Gemini CLI` **->** `(Optional) Save Session`
+### 📚 **Context Assembly**
 
-### 🧠 **Template Selection Logic**
+Context is gathered from:
+1. **Project Guidelines**: Always includes `@{CLAUDE.md,**/*CLAUDE.md}`
+2. **User-Explicit Files**: Files specified by the user (e.g., `@{src/auth/*.js}`)
+3. **All Files Flag**: The `--all-files` flag includes the entire codebase
 
-⚠️ **CRITICAL**: Templates are selected **AUTOMATICALLY** by analyzing user input. The command execution calls script methods to discover and select the best template.
-
-**Script Methods Available:**
-- `~/.claude/scripts/chat-template-load.sh list` - Lists all available templates
-- `~/.claude/scripts/chat-template-load.sh load "template_name"` - Loads a specific template
-
-```pseudo
-FUNCTION automatic_template_selection(user_inquiry):
-  // STEP 1: Command execution calls list method to discover templates
-  available_templates = call_script_method("list")
-  
-  // STEP 2: Analyze user input to determine best template match
-  analyzed_intent = analyze_input_keywords_and_context(user_inquiry)
-  best_template = match_template_to_intent(analyzed_intent, available_templates)
-
-  // STEP 3: Command execution calls load method with selected template
-  IF best_template is FOUND:
-    template_content = call_script_method("load", best_template.name)
-    log_info("Auto-selected template: " + best_template.name)
-  ELSE:
-    // Fallback to default template if no clear match
-    template_content = call_script_method("load", "default")
-    log_warning("No clear template match, using default template")
-
-  RETURN template_content
-END FUNCTION
-```
-
-**Automatic Selection Flow:**
-1. **Command starts** → Calls `list` method to discover available templates
-2. **Input analysis** → Analyzes user inquiry for keywords, intent, and context
-3. **Template matching** → Automatically selects best template based on analysis
-4. **Template loading** → Command calls `load` method with selected template name
-5. **Continue execution** → Process the inquiry with loaded template
-
-### 📚 **Context Assembly Priority**
-
-Context is gathered based on a clear hierarchy of sources.
-
-1.  **Template Requirements**: The primary driver. The selected template defines a default set of required file patterns.
-2.  **User-Explicit Files**: Files specified by the user (e.g., `@{src/auth/*.js}`) override or add to the template's requirements.
-3.  **Command-Level Flags**: The `--all-files` flag overrides all other file specifications to scope the context to the entire project.
-
-### 📝 **Structured Prompt Format**
-
-The final prompt sent to the `gemini` CLI is assembled in three distinct parts.
+### 📝 **Prompt Format**
 
 ```
-=== SYSTEM PROMPT ===
-[Content from the selected template file is placed here]
-
 === CONTEXT ===
-@{CLAUDE.md,**/*CLAUDE.md} [Project guidelines, always included]
-@{target_files} [File context gathered based on the assembly priority]
+@{CLAUDE.md,**/*CLAUDE.md} [Project guidelines]
+@{target_files} [User-specified files or all files if --all-files is used]
 
 === USER INPUT ===
-[The original user inquiry text]
+[The user inquiry text]
 ```
 
-### ⚙️ **Gemini CLI Execution Logic**
-
-This describes how the external `gemini` binary is invoked with the constructed prompt.
+### ⚙️ **Execution Implementation**
 
 ```pseudo
-FUNCTION execute_gemini_cli(structured_prompt, flags):
-  // Retrieves the path from the user's execution environment.
-  current_directory = get_current_working_directory()
-
+FUNCTION execute_gemini_chat(user_inquiry, flags):
+  // Construct basic prompt
+  prompt = "=== CONTEXT ===\n"
+  prompt += "@{CLAUDE.md,**/*CLAUDE.md}\n"
+  
+  // Add user-specified files or all files
   IF flags contain "--all-files":
-    // For --all-files, it may be necessary to navigate to the correct directory first.
-    navigate_to_project_root(current_directory)
-    // Executes the gemini tool using the --all-files flag.
-    result = execute_tool("Bash(gemini:*)", "--all-files", "-p", structured_prompt)
+    result = execute_tool("Bash(gemini:*)", "--all-files", "-p", prompt + user_inquiry)
   ELSE:
-    // Default execution relies on @{file_patterns} resolved by the Gemini CLI.
-    // The prompt already contains the necessary @{...} references.
-    result = execute_tool("Bash(gemini:*)", "-p", structured_prompt)
-
-  IF result is 'FAILED' AND flags contain "--all-files":
-    // Implements the fallback strategy if --all-files fails.
-    log_warning("`--all-files` failed. Falling back to pattern-based context.")
-    prompt_with_fallback = add_file_patterns_to_prompt(structured_prompt)
-    result = execute_tool("Bash(gemini:*)", "-p", prompt_with_fallback)
-
+    prompt += "\n=== USER INPUT ===\n" + user_inquiry
+    result = execute_tool("Bash(gemini:*)", "-p", prompt)
+  
+  // Save session if requested
+  IF flags contain "--save-session":
+    save_chat_session(user_inquiry, result)
+  
   RETURN result
 END FUNCTION
 ```
 
 ### 💾 **Session Persistence**
 
-⚠️ **CRITICAL**: Before saving, MUST check for existing active session to avoid creating duplicate sessions.
-
--   **Trigger**: Activated by the `--save-session` flag.
--   **Action**: Saves the complete interaction, including the template used, context, and Gemini's output.
--   **Session Check**: Check for `.workflow/.active-*` marker file to identify current active session. No file creation needed.
--   **Location Strategy**: 
-    - **IF active session exists**: Save to existing `.workflow/WFS-[topic-slug]/.chat/` directory
-    - **IF no active session**: Create new session directory following WFS naming convention
-
-**File Structure**: @~/.claude/workflows/file-structure-standards.md
--   **File Format**: `chat-YYYYMMDD-HHMMSS.md` with timestamp for unique identification.
--   **Structure**: Integrates with session management system using WFS-[topic-slug] format for consistency.
--   **Coordination**: Session files coordinate with workflow-session.json and maintain document-state separation.
-
-### 🔗 **Chat Session Integration**
-
-**Session Detection Workflow:**
-```pseudo
-FUNCTION determine_save_location():
-  // STEP 1: Check for active session marker
-  active_marker = find_file(".workflow/.active-*")
-  
-  // STEP 2: Extract session name if marker exists
-  active_session_name = extract_session_name(active_marker)
-  
-  IF active_sessions.count > 0:
-    // Use existing active session directory
-    session_dir = active_sessions[0].session_path + "/.chat/"
-    ensure_directory_exists(session_dir)
-    RETURN session_dir
-  ELSE:
-    // No active session - create new one only if necessary
-    new_session_slug = generate_topic_slug(user_inquiry)
-    session_dir = ".workflow/WFS-" + new_session_slug + "/.chat/"
-    create_session_structure(session_dir)
-    RETURN session_dir
-END FUNCTION
-```
-
-**Storage Structure:**
-```
-.workflow/WFS-[topic-slug]/.chat/
-├── chat-20240307-143022.md      # Individual chat sessions
-├── chat-20240307-151445.md      # Timestamped for chronological order
-└── analysis-security.md         # Named analysis sessions
-```
+When `--save-session` flag is used:
+-   Check for existing active session (`.workflow/.active-*` markers)
+-   Save to existing session's `.chat/` directory or create new session
+-   File format: `chat-YYYYMMDD-HHMMSS.md`
+-   Include query, context, and response in saved file
 
 **Session Template:**
 ```markdown
-# Chat Session: [Timestamp] - [Topic]
+# Chat Session: [Timestamp]
 
 ## Query
 [Original user inquiry]
 
-## Template Used  
-[Auto-selected template name and rationale]
-
 ## Context
 [Files and patterns included in analysis]
 
 ## Gemini Response
 [Complete response from Gemini CLI]
-
-## Key Insights
-- [Important findings]
-- [Architectural insights] 
-- [Implementation recommendations]
-
-## Integration Links
-- [🔙 Workflow Session](../workflow-session.json)
-- [📋 Implementation Plan](../IMPL_PLAN.md)
-- [📝 Task Definitions](../.task/)
 ```
\ No newline at end of file
diff --git a/.claude/commands/gemini/chat/bug-fix.md b/.claude/commands/gemini/chat/bug-fix.md
new file mode 100644
index 00000000..d0fd2386
--- /dev/null
+++ b/.claude/commands/gemini/chat/bug-fix.md
@@ -0,0 +1,113 @@
+---
+name: bug-fix
+parent: /gemini/chat
+description: Bug analysis and fix suggestions using specialized template
+usage: /gemini:chat:bug-fix "bug description"
+argument-hint: "description of the bug or error you're experiencing"
+examples:
+  - /gemini:chat:bug-fix "authentication null pointer error in login flow"
+  - /gemini:chat:bug-fix "React component not re-rendering after state change"
+  - /gemini:chat:bug-fix "database connection timeout in production"
+allowed-tools: Bash(gemini:*)
+model: sonnet
+---
+
+### 🐛 **Command Overview: `/gemini:chat:bug-fix`**
+
+-   **Type**: Template-based Gemini CLI Wrapper
+-   **Purpose**: Specialized bug analysis and fix suggestions using expert diagnostic template
+-   **Template**: Bug fix analysis template for systematic problem diagnosis
+-   **Core Tool**: `Bash(gemini:*)` - Executes Gemini CLI with bug-fix template
+
+### 📥 **Parameters & Usage**
+
+-   **`<bug description>` (Required)**: Description of the bug, error, or unexpected behavior
+-   **`--all-files` (Optional)**: Includes entire codebase for comprehensive analysis
+-   **`--save-session` (Optional)**: Saves the bug analysis to current workflow session
+
+### 🔄 **Execution Workflow**
+
+`Parse Bug Description` **->** `Load Bug-Fix Template` **->** `Assemble Context` **->** `Execute Gemini CLI` **->** `(Optional) Save Session`
+
+### 📋 **Bug Analysis Focus**
+
+The bug-fix template provides structured analysis covering:
+- **Root Cause Analysis**: Systematic investigation of underlying issues
+- **Code Path Tracing**: Following execution flow to identify failure points
+- **Hypothesis Validation**: Testing theories about bug origins
+- **Targeted Solutions**: Specific, minimal fixes rather than broad refactoring
+- **Impact Assessment**: Understanding side effects of proposed fixes
+
+### 📚 **Context Assembly**
+
+Context includes:
+1. **Bug-Fix Template**: `@D:\Claude_dms3\.claude\prompt-templates\bug-fix.md`
+2. **Project Guidelines**: `@{CLAUDE.md,**/*CLAUDE.md}`
+3. **Relevant Files**: User-specified files or all files if `--all-files` used
+
+### 📝 **Prompt Structure**
+
+```
+=== SYSTEM PROMPT ===
+@D:\Claude_dms3\.claude\prompt-templates\bug-fix.md
+
+=== CONTEXT ===
+@{CLAUDE.md,**/*CLAUDE.md}
+@{target_files}
+
+=== USER INPUT ===
+[Bug description and any relevant details]
+```
+
+### ⚙️ **Implementation**
+
+```pseudo
+FUNCTION execute_bug_fix_analysis(bug_description, flags):
+  // Load bug-fix template
+  template = load_file("D:\Claude_dms3\.claude\prompt-templates\bug-fix.md")
+  
+  // Construct prompt with template
+  prompt = "=== SYSTEM PROMPT ===\n" + template + "\n\n"
+  prompt += "=== CONTEXT ===\n"
+  prompt += "@{CLAUDE.md,**/*CLAUDE.md}\n"
+  
+  // Execute with appropriate context
+  IF flags contain "--all-files":
+    result = execute_tool("Bash(gemini:*)", "--all-files", "-p", prompt + bug_description)
+  ELSE:
+    prompt += "\n=== USER INPUT ===\n" + bug_description
+    result = execute_tool("Bash(gemini:*)", "-p", prompt)
+  
+  // Save session if requested
+  IF flags contain "--save-session":
+    save_bug_analysis_session(bug_description, result)
+  
+  RETURN result
+END FUNCTION
+```
+
+### 💾 **Session Integration**
+
+When `--save-session` is used:
+- Saves to `.workflow/WFS-[topic]/.chat/` directory
+- File named: `bug-fix-YYYYMMDD-HHMMSS.md`
+- Includes template used, bug description, analysis, and recommendations
+
+**Session Template:**
+```markdown
+# Bug Fix Analysis: [Timestamp]
+
+## Bug Description
+[Original bug description]
+
+## Template Used
+bug-fix.md - Expert diagnostic analysis template
+
+## Analysis Results
+[Complete Gemini response with root cause analysis and fix suggestions]
+
+## Recommended Actions
+- [Immediate fixes]
+- [Prevention measures]
+- [Testing recommendations]
+```
\ No newline at end of file
diff --git a/.claude/commands/gemini/chat/plan.md b/.claude/commands/gemini/chat/plan.md
new file mode 100644
index 00000000..c20cbefd
--- /dev/null
+++ b/.claude/commands/gemini/chat/plan.md
@@ -0,0 +1,118 @@
+---
+name: plan
+parent: /gemini/chat
+description: Project planning and architecture analysis using specialized template
+usage: /gemini:chat:plan "planning topic"
+argument-hint: "planning topic or architectural challenge to analyze"
+examples:
+  - /gemini:chat:plan "design user dashboard feature architecture"
+  - /gemini:chat:plan "plan microservices migration strategy"
+  - /gemini:chat:plan "implement real-time notification system"
+allowed-tools: Bash(gemini:*)
+model: sonnet
+---
+
+### 📋 **Command Overview: `/gemini:chat:plan`**
+
+-   **Type**: Template-based Gemini CLI Wrapper
+-   **Purpose**: Comprehensive project planning and architecture analysis using expert planning template
+-   **Template**: Planning analysis template for systematic feature and system design
+-   **Core Tool**: `Bash(gemini:*)` - Executes Gemini CLI with planning template
+
+### 📥 **Parameters & Usage**
+
+-   **`<planning topic>` (Required)**: Description of the feature, system, or architectural challenge to plan
+-   **`--all-files` (Optional)**: Includes entire codebase for comprehensive planning context
+-   **`--save-session` (Optional)**: Saves the planning analysis to current workflow session
+
+### 🔄 **Execution Workflow**
+
+`Parse Planning Topic` **->** `Load Planning Template` **->** `Assemble Context` **->** `Execute Gemini CLI` **->** `(Optional) Save Session`
+
+### 📋 **Planning Analysis Focus**
+
+The planning template provides structured analysis covering:
+- **Requirements Analysis**: Understanding functional and non-functional requirements
+- **Architecture Design**: System structure, components, and interactions
+- **Implementation Strategy**: Step-by-step development approach
+- **Risk Assessment**: Identifying potential challenges and mitigation strategies
+- **Resource Planning**: Time, effort, and technology requirements
+
+### 📚 **Context Assembly**
+
+Context includes:
+1. **Planning Template**: `@D:\Claude_dms3\.claude\prompt-templates\plan.md`
+2. **Project Guidelines**: `@{CLAUDE.md,**/*CLAUDE.md}`
+3. **Relevant Files**: User-specified files or all files if `--all-files` used
+
+### 📝 **Prompt Structure**
+
+```
+=== SYSTEM PROMPT ===
+@D:\Claude_dms3\.claude\prompt-templates\plan.md
+
+=== CONTEXT ===
+@{CLAUDE.md,**/*CLAUDE.md}
+@{target_files}
+
+=== USER INPUT ===
+[Planning topic and any specific requirements or constraints]
+```
+
+### ⚙️ **Implementation**
+
+```pseudo
+FUNCTION execute_planning_analysis(planning_topic, flags):
+  // Load planning template
+  template = load_file("D:\Claude_dms3\.claude\prompt-templates\plan.md")
+  
+  // Construct prompt with template
+  prompt = "=== SYSTEM PROMPT ===\n" + template + "\n\n"
+  prompt += "=== CONTEXT ===\n"
+  prompt += "@{CLAUDE.md,**/*CLAUDE.md}\n"
+  
+  // Execute with appropriate context
+  IF flags contain "--all-files":
+    result = execute_tool("Bash(gemini:*)", "--all-files", "-p", prompt + planning_topic)
+  ELSE:
+    prompt += "\n=== USER INPUT ===\n" + planning_topic
+    result = execute_tool("Bash(gemini:*)", "-p", prompt)
+  
+  // Save session if requested
+  IF flags contain "--save-session":
+    save_planning_session(planning_topic, result)
+  
+  RETURN result
+END FUNCTION
+```
+
+### 💾 **Session Integration**
+
+When `--save-session` is used:
+- Saves to `.workflow/WFS-[topic]/.chat/` directory
+- File named: `plan-YYYYMMDD-HHMMSS.md`
+- Includes template used, planning topic, analysis, and implementation roadmap
+
+**Session Template:**
+```markdown
+# Planning Analysis: [Timestamp]
+
+## Planning Topic
+[Original planning topic description]
+
+## Template Used
+plan.md - Expert planning and architecture analysis template
+
+## Analysis Results
+[Complete Gemini response with requirements, architecture, and implementation plan]
+
+## Implementation Roadmap
+- [Phase 1: Foundation work]
+- [Phase 2: Core implementation]
+- [Phase 3: Integration and testing]
+
+## Key Decisions
+- [Architecture choices]
+- [Technology selections]
+- [Risk mitigation strategies]
+```
\ No newline at end of file
diff --git a/README.md b/README.md
index 7e11a628..3d6239b1 100644
--- a/README.md
+++ b/README.md
@@ -104,7 +104,9 @@ Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/cat
 | Command | Syntax | Description |
 |---------|--------|-------------|
 | `/enhance-prompt` | `/enhance-prompt <input>` | Enhance and structure user inputs with technical context |
-| `/gemini-chat` | `/gemini-chat <inquiry> [--all-files] [--compress]` | Interactive dialogue with Gemini CLI using smart templates |
+| `/gemini:chat` | `/gemini:chat <inquiry> [--all-files] [--save-session]` | Simple direct interaction with Gemini CLI without templates |
+| `/gemini:chat:bug-fix` | `/gemini:chat:bug-fix <bug-description> [--all-files] [--save-session]` | Bug analysis using specialized diagnostic template |
+| `/gemini:chat:plan` | `/gemini:chat:plan <planning-topic> [--all-files] [--save-session]` | Project planning using specialized architecture template |
 | `/gemini-execute` | `/gemini-execute <task-id\|description> [--yolo] [--debug]` | Intelligent executor with automatic file context inference |
 | `/gemini-mode` | `/gemini-mode <analysis-type> <target> [options]` | Template-driven codebase analysis (pattern, architecture, security) |
 | `/update-memory` | `/update-memory [related\|full]` | Intelligent CLAUDE.md documentation system with context-aware updates and strict hierarchy preservation |
diff --git a/README_CN.md b/README_CN.md
index bc910e1c..fbe1f507 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -104,7 +104,9 @@ Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/cat
 | 命令 | 语法 | 描述 |
 |---------|--------|-------------|
 | `/enhance-prompt` | `/enhance-prompt <输入>` | 增强和构造用户输入，添加技术上下文 |
-| `/gemini-chat` | `/gemini-chat <查询> [--all-files] [--compress]` | 使用智能模板与 Gemini CLI 进行交互对话 |
+| `/gemini:chat` | `/gemini:chat <查询> [--all-files] [--save-session]` | 与 Gemini CLI 的简单直接交互，不使用模板 |
+| `/gemini:chat:bug-fix` | `/gemini:chat:bug-fix <错误描述> [--all-files] [--save-session]` | 使用专门的诊断模板进行错误分析 |
+| `/gemini:chat:plan` | `/gemini:chat:plan <规划主题> [--all-files] [--save-session]` | 使用专门的架构模板进行项目规划 |
 | `/gemini-execute` | `/gemini-execute <任务ID\|描述> [--yolo] [--debug]` | 智能执行器，自动推断文件上下文 |
 | `/gemini-mode` | `/gemini-mode <分析类型> <目标> [选项]` | 模板驱动的代码库分析（模式、架构、安全） |
 | `/update-memory` | `/update-memory [full\|fast\|deep] [路径]` | 分布式记忆系统管理，维护层级化 CLAUDE.md |