diff --git a/app/agent/tools/factory.py b/app/agent/tools/factory.py
index f6fb1eae..e4455c8a 100644
--- a/app/agent/tools/factory.py
+++ b/app/agent/tools/factory.py
@@ -51,6 +51,7 @@ from app.agent.tools.impl.browse_webpage import BrowseWebpageTool
 from app.agent.tools.impl.query_installed_plugins import QueryInstalledPluginsTool
 from app.agent.tools.impl.query_plugin_capabilities import QueryPluginCapabilitiesTool
 from app.agent.tools.impl.run_plugin_command import RunPluginCommandTool
+from app.agent.tools.impl.list_all_commands import ListAllCommandsTool
 from app.core.plugin import PluginManager
 from app.log import logger
 from .base import MoviePilotTool
@@ -126,6 +127,7 @@ class MoviePilotToolFactory:
             QueryInstalledPluginsTool,
             QueryPluginCapabilitiesTool,
             RunPluginCommandTool,
+            ListAllCommandsTool,
         ]
         # 创建内置工具
         for ToolClass in tool_definitions:
diff --git a/app/agent/tools/impl/list_all_commands.py b/app/agent/tools/impl/list_all_commands.py
new file mode 100644
index 00000000..c861a74f
--- /dev/null
+++ b/app/agent/tools/impl/list_all_commands.py
@@ -0,0 +1,78 @@
+"""查询所有可用命令工具（系统命令 + 插件命令）"""
+
+import json
+from typing import Optional, Type
+
+from pydantic import BaseModel, Field
+
+from app.agent.tools.base import MoviePilotTool
+from app.command import Command
+from app.log import logger
+
+
+class ListAllCommandsInput(BaseModel):
+    """查询所有可用命令工具的输入参数模型"""
+
+    explanation: str = Field(
+        ...,
+        description="Clear explanation of why this tool is being used in the current context",
+    )
+
+
+class ListAllCommandsTool(MoviePilotTool):
+    name: str = "list_all_commands"
+    description: str = (
+        "List all available commands in the system, including system preset commands "
+        "(e.g. /cookiecloud, /sites, /subscribes, /downloading, /transfer, /restart, etc.) "
+        "and plugin-registered commands. "
+        "Use this tool to discover what commands are available before executing them with run_plugin_command. "
+        "This is especially useful when the user describes an action in natural language and you need to "
+        "find the matching command to fulfill their request."
+    )
+    args_schema: Type[BaseModel] = ListAllCommandsInput
+    require_admin: bool = True
+
+    def get_tool_message(self, **kwargs) -> Optional[str]:
+        """生成友好的提示消息"""
+        return "正在查询所有可用命令"
+
+    async def run(self, **kwargs) -> str:
+        logger.info(f"执行工具: {self.name}")
+
+        try:
+            command_obj = Command()
+            all_commands = command_obj.get_commands()
+
+            if not all_commands:
+                return "当前没有可用的命令"
+
+            commands_list = []
+            for cmd, info in all_commands.items():
+                cmd_info = {
+                    "command": cmd,
+                    "description": info.get("description", ""),
+                }
+                if info.get("category"):
+                    cmd_info["category"] = info["category"]
+                # 标识命令类型
+                if info.get("type") == "scheduler":
+                    cmd_info["type"] = "scheduler"
+                elif info.get("pid"):
+                    cmd_info["type"] = "plugin"
+                    cmd_info["plugin_id"] = info["pid"]
+                else:
+                    cmd_info["type"] = "system"
+                commands_list.append(cmd_info)
+
+            result = {
+                "total": len(commands_list),
+                "commands": commands_list,
+            }
+            return json.dumps(result, ensure_ascii=False, indent=2)
+
+        except Exception as e:
+            logger.error(f"查询可用命令失败: {e}", exc_info=True)
+            return json.dumps(
+                {"success": False, "message": f"查询可用命令时发生错误: {str(e)}"},
+                ensure_ascii=False,
+            )
diff --git a/app/agent/tools/impl/run_plugin_command.py b/app/agent/tools/impl/run_plugin_command.py
index 1d66817f..8d3f21e0 100644
--- a/app/agent/tools/impl/run_plugin_command.py
+++ b/app/agent/tools/impl/run_plugin_command.py
@@ -1,4 +1,4 @@
-"""运行插件命令工具"""
+"""运行插件/系统命令工具"""
 
 import json
 from typing import Optional, Type
@@ -6,14 +6,14 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.command import Command
 from app.core.event import eventmanager
-from app.core.plugin import PluginManager
 from app.log import logger
 from app.schemas.types import EventType, MessageChannel
 
 
 class RunPluginCommandInput(BaseModel):
-    """运行插件命令工具的输入参数模型"""
+    """运行插件/系统命令工具的输入参数模型"""
 
     explanation: str = Field(
         ...,
@@ -23,16 +23,20 @@ class RunPluginCommandInput(BaseModel):
         ...,
         description="The slash command to execute, e.g. '/cookiecloud'. "
         "Must start with '/'. Can include arguments after the command, e.g. '/command arg1 arg2'. "
-        "Use query_plugin_capabilities tool to discover available commands first.",
+        "Use query_plugin_capabilities tool to discover available plugin commands, "
+        "or list_all_commands tool to discover all available commands (including system commands).",
     )
 
 
 class RunPluginCommandTool(MoviePilotTool):
     name: str = "run_plugin_command"
     description: str = (
-        "Execute a plugin command by sending a CommandExcute event. "
-        "Plugin commands are slash-commands (starting with '/') registered by plugins. "
-        "Use the query_plugin_capabilities tool first to discover available commands and their descriptions. "
+        "Execute a system or plugin command by sending a CommandExcute event. "
+        "This tool supports ALL registered commands, including: "
+        "1) System preset commands (e.g. /cookiecloud, /sites, /subscribes, /downloading, /transfer, /restart, etc.) "
+        "2) Plugin commands registered by installed plugins. "
+        "Use the query_plugin_capabilities tool to discover plugin commands, "
+        "or the list_all_commands tool to discover all available commands. "
         "The command will be executed asynchronously. "
         "Note: This tool triggers the command execution but the actual processing happens in the background."
     )
@@ -42,7 +46,7 @@ class RunPluginCommandTool(MoviePilotTool):
     def get_tool_message(self, **kwargs) -> Optional[str]:
         """生成友好的提示消息"""
         command = kwargs.get("command", "")
-        return f"正在执行插件命令: {command}"
+        return f"正在执行命令: {command}"
 
     async def run(self, command: str, **kwargs) -> str:
         logger.info(f"执行工具: {self.name}, 参数: command={command}")
@@ -52,21 +56,17 @@ class RunPluginCommandTool(MoviePilotTool):
             if not command.startswith("/"):
                 command = f"/{command}"
 
-            # 验证命令是否存在
-            plugin_manager = PluginManager()
-            registered_commands = plugin_manager.get_plugin_commands()
+            # 从全局 Command 单例中验证命令是否存在（包含系统预设命令 + 插件命令 + 其他命令）
             cmd_name = command.split()[0]
-            matched_command = None
-            for cmd in registered_commands:
-                if cmd.get("cmd") == cmd_name:
-                    matched_command = cmd
-                    break
+            command_obj = Command()
+            matched_command = command_obj.get(cmd_name)
 
             if not matched_command:
-                # 列出可用命令帮助用户
+                # 列出所有可用命令帮助用户
+                all_commands = command_obj.get_commands()
                 available_cmds = [
-                    f"{cmd.get('cmd')} - {cmd.get('desc', '无描述')}"
-                    for cmd in registered_commands
+                    f"{cmd} - {info.get('description', '无描述')}"
+                    for cmd, info in all_commands.items()
                 ]
                 result = {
                     "success": False,
@@ -99,14 +99,16 @@ class RunPluginCommandTool(MoviePilotTool):
                 "success": True,
                 "message": f"命令 {cmd_name} 已触发执行",
                 "command": command,
-                "command_desc": matched_command.get("desc", ""),
-                "plugin_id": matched_command.get("pid", ""),
+                "command_desc": matched_command.get("description", ""),
             }
+            # 如果是插件命令，附加插件ID
+            if matched_command.get("pid"):
+                result["plugin_id"] = matched_command["pid"]
             return json.dumps(result, ensure_ascii=False, indent=2)
 
         except Exception as e:
-            logger.error(f"执行插件命令失败: {e}", exc_info=True)
+            logger.error(f"执行命令失败: {e}", exc_info=True)
             return json.dumps(
-                {"success": False, "message": f"执行插件命令时发生错误: {str(e)}"},
+                {"success": False, "message": f"执行命令时发生错误: {str(e)}"},
                 ensure_ascii=False,
             )
diff --git a/skills/command-execute/SKILL.md b/skills/command-execute/SKILL.md
new file mode 100644
index 00000000..7e93fae5
--- /dev/null
+++ b/skills/command-execute/SKILL.md
@@ -0,0 +1,73 @@
+---
+name: command-execute
+description: >-
+  Use this skill when the user's intent is to execute a system or plugin function. Applicable scenarios include:
+  1) The user sends a slash command starting with / (e.g. /cookiecloud, /sites, /subscribes, etc.);
+  2) The user describes an action in natural language that can be fulfilled by a system or plugin command
+  (e.g. "sync sites", "show subscriptions", "refresh subscriptions", "check downloads", etc.).
+  This skill helps you identify the user's intent, find the matching command, extract necessary parameters,
+  and execute the corresponding command.
+allowed-tools: list_all_commands query_plugin_capabilities run_plugin_command
+---
+
+# Command Execute
+
+Use this skill to identify user intent and invoke the corresponding system or plugin command.
+
+## When to Use
+
+- The user sends a `/xxx` slash command (execute directly)
+- The user describes an action in natural language, for example:
+  - "Sync sites" → `/cookiecloud`
+  - "Show my subscriptions" → `/subscribes`
+  - "Refresh subscriptions" → `/subscribe_refresh`
+  - "What's downloading?" → `/downloading`
+  - "Organize downloaded files" → `/transfer`
+  - "Clear cache" → `/clear_cache`
+  - "Restart the system" → `/restart`
+  - "Pause all QB tasks" → `/pause_torrents` (plugin command)
+
+## Tools
+
+- `list_all_commands` — List all available commands (system + plugin), returns command name, description, and category
+- `query_plugin_capabilities` — Query detailed plugin capabilities (commands, actions, scheduled services)
+- `run_plugin_command` — Execute a specified command (works for both system and plugin commands)
+
+## Workflow
+
+### Step 1: Identify User Intent
+
+Determine whether the user's message is requesting the execution of a command:
+
+- **Direct command**: Message starts with `/`, e.g. `/sites`, `/subscribes` → skip to Step 3
+- **Natural language**: The user describes an actionable request → continue to Step 2
+
+### Step 2: Find Matching Command
+
+Use `list_all_commands` to retrieve all available commands. Match the user's described intent against the `description` and `category` fields of each command.
+
+If the user's description involves a specific plugin's functionality, additionally use `query_plugin_capabilities` to query that plugin's detailed capabilities.
+
+**Matching strategy**:
+- Prefer exact matches on command description
+- Then narrow down by category and match
+- If no matching command is found, inform the user that no corresponding function is available
+
+### Step 3: Extract Parameters and Execute
+
+Some commands support additional arguments (space-separated after the command), for example:
+- `/redo <history_id>` — Manually re-organize a specific record
+- `/subscribe_delete <name>` — Delete a specific subscription
+
+Use `run_plugin_command` to execute the command in the format `/command_name arg1 arg2`.
+
+### Step 4: Report Result
+
+Command execution is asynchronous. After triggering, inform the user that the command has started. If the command does not exist, list available commands for reference.
+
+## Important Notes
+
+- Command execution requires admin privileges; the tool will automatically check permissions
+- Both system and plugin commands are executed via the `run_plugin_command` tool — no need to distinguish between them
+- If you are unsure which command matches the user's intent, use `list_all_commands` first to look up before deciding
+- Never guess non-existent commands; always select from the available command list