diff --git a/src/agent/skills/README.md b/src/agent/skills/README.md
index 5a8e51f0..f8c40ac7 100644
--- a/src/agent/skills/README.md
+++ b/src/agent/skills/README.md
@@ -219,13 +219,15 @@ Only skills passing all checks are marked as eligible.
 
 ## CLI Commands
 
+All commands use the unified `multica` CLI (or `pnpm multica` during development).
+
 ### List Skills
 
 ```bash
-pnpm skills:cli list           # List all skills
-pnpm skills:cli list -v        # Verbose mode
-pnpm skills:cli status         # Summary status
-pnpm skills:cli status <id>    # Specific skill status
+multica skills list           # List all skills
+multica skills list -v        # Verbose mode
+multica skills status         # Summary status
+multica skills status <id>    # Specific skill status
 ```
 
 ### Install from GitHub
@@ -247,32 +249,32 @@ anthropics/skills/
 
 Install the entire repository (all 16 skills):
 ```bash
-pnpm skills:cli add anthropics/skills
+multica skills add anthropics/skills
 # Installs to: ~/.super-multica/skills/skills/
 # All skills available: algorithmic-art, brand-guidelines, pdf, etc.
 ```
 
 Install a single skill only:
 ```bash
-pnpm skills:cli add anthropics/skills/skills/pdf
+multica skills add anthropics/skills/skills/pdf
 # Installs to: ~/.super-multica/skills/pdf/
 # Only the pdf skill is installed
 ```
 
 Install from a specific branch or tag:
 ```bash
-pnpm skills:cli add anthropics/skills@main
+multica skills add anthropics/skills@main
 ```
 
 Using full URL:
 ```bash
-pnpm skills:cli add https://github.com/anthropics/skills
-pnpm skills:cli add https://github.com/anthropics/skills/tree/main/skills/pdf
+multica skills add https://github.com/anthropics/skills
+multica skills add https://github.com/anthropics/skills/tree/main/skills/pdf
 ```
 
 Force overwrite existing:
 ```bash
-pnpm skills:cli add anthropics/skills --force
+multica skills add anthropics/skills --force
 ```
 
 **Supported formats:**
@@ -288,15 +290,15 @@ pnpm skills:cli add anthropics/skills --force
 ### Remove Skills
 
 ```bash
-pnpm skills:cli remove <name>   # Remove installed skill
-pnpm skills:cli remove          # List installed skills
+multica skills remove <name>   # Remove installed skill
+multica skills remove          # List installed skills
 ```
 
 ### Install Dependencies
 
 ```bash
-pnpm skills:cli install <id>              # Install skill dependencies
-pnpm skills:cli install <id> <install-id> # Specific install option
+multica skills install <id>              # Install skill dependencies
+multica skills install <id> <install-id> # Specific install option
 ```
 
 ---
@@ -308,8 +310,8 @@ The `status` command provides detailed diagnostics for understanding why skills
 ### Summary Status
 
 ```bash
-pnpm skills:cli status        # Show summary with grouping by issue type
-pnpm skills:cli status -v     # Verbose mode with hints
+multica skills status        # Show summary with grouping by issue type
+multica skills status -v     # Verbose mode with hints
 ```
 
 Output shows:
@@ -319,7 +321,7 @@ Output shows:
 ### Detailed Skill Status
 
 ```bash
-pnpm skills:cli status <skill-id>
+multica skills status <skill-id>
 ```
 
 Output includes:
diff --git a/src/agent/tools/README.md b/src/agent/tools/README.md
index 7a3c548f..80087453 100644
--- a/src/agent/tools/README.md
+++ b/src/agent/tools/README.md
@@ -99,18 +99,20 @@ Profiles are predefined tool sets for common use cases:
 
 ### CLI Usage
 
+All commands use the unified `multica` CLI (or `pnpm multica` during development).
+
 ```bash
 # Use a specific profile
-pnpm agent:cli --tools-profile coding "list files"
+multica run --tools-profile coding "list files"
 
 # Minimal profile with specific tools allowed
-pnpm agent:cli --tools-profile minimal --tools-allow exec "run ls"
+multica run --tools-profile minimal --tools-allow exec "run ls"
 
 # Deny specific tools
-pnpm agent:cli --tools-deny exec,process "read file.txt"
+multica run --tools-deny exec,process "read file.txt"
 
 # Use tool groups
-pnpm agent:cli --tools-allow group:fs "read config.json"
+multica run --tools-allow group:fs "read config.json"
 ```
 
 ### Programmatic Usage
@@ -146,19 +148,19 @@ Use the tools CLI to inspect and test configurations:
 
 ```bash
 # List all available tools
-pnpm tools:cli list
+multica tools list
 
 # List tools after applying a profile
-pnpm tools:cli list --profile coding
+multica tools list --profile coding
 
 # List tools with deny rules
-pnpm tools:cli list --profile coding --deny exec
+multica tools list --profile coding --deny exec
 
 # Show all tool groups
-pnpm tools:cli groups
+multica tools groups
 
 # Show all profiles
-pnpm tools:cli profiles
+multica tools profiles
 ```
 
 ## Policy System Details
@@ -261,7 +263,7 @@ export const TOOL_GROUPS: Record<string, string[]> = {
 Run the policy system tests:
 
 ```bash
-npx tsx src/agent/tools/policy.test.ts
+pnpm test src/agent/tools/policy.test.ts
 ```
 
 ## Agent Profile Integration
@@ -315,7 +317,7 @@ When both Profile config and CLI options are provided:
 # Profile has tools.profile = "coding"
 # CLI adds --tools-deny exec
 # Result: coding profile without exec tool
-pnpm agent:cli --profile my-agent --tools-deny exec "list files"
+multica run --profile my-agent --tools-deny exec "list files"
 ```
 
 ## Future Tools
diff --git a/src/agent/tools/README.zh-CN.md b/src/agent/tools/README.zh-CN.md
index dea6c2ce..5ac1a99e 100644
--- a/src/agent/tools/README.zh-CN.md
+++ b/src/agent/tools/README.zh-CN.md
@@ -99,18 +99,20 @@
 
 ### CLI 使用
 
+所有命令使用统一的 `multica` CLI（开发时使用 `pnpm multica`）。
+
 ```bash
 # 使用特定配置文件
-pnpm agent:cli --tools-profile coding "list files"
+multica run --tools-profile coding "list files"
 
 # 最小配置文件 + 允许特定工具
-pnpm agent:cli --tools-profile minimal --tools-allow exec "run ls"
+multica run --tools-profile minimal --tools-allow exec "run ls"
 
 # 禁止特定工具
-pnpm agent:cli --tools-deny exec,process "read file.txt"
+multica run --tools-deny exec,process "read file.txt"
 
 # 使用工具组
-pnpm agent:cli --tools-allow group:fs "read config.json"
+multica run --tools-allow group:fs "read config.json"
 ```
 
 ### 编程使用
@@ -146,19 +148,19 @@ const agent = new Agent({
 
 ```bash
 # 列出所有可用工具
-pnpm tools:cli list
+multica tools list
 
 # 列出应用配置文件后的工具
-pnpm tools:cli list --profile coding
+multica tools list --profile coding
 
 # 列出带有禁止规则的工具
-pnpm tools:cli list --profile coding --deny exec
+multica tools list --profile coding --deny exec
 
 # 显示所有工具组
-pnpm tools:cli groups
+multica tools groups
 
 # 显示所有配置文件
-pnpm tools:cli profiles
+multica tools profiles
 ```
 
 ## 策略系统详情
@@ -261,7 +263,7 @@ export const TOOL_GROUPS: Record<string, string[]> = {
 运行策略系统测试：
 
 ```bash
-npx tsx src/agent/tools/policy.test.ts
+pnpm test src/agent/tools/policy.test.ts
 ```
 
 ## Agent Profile 集成
@@ -315,7 +317,7 @@ npx tsx src/agent/tools/policy.test.ts
 # Profile 有 tools.profile = "coding"
 # CLI 添加 --tools-deny exec
 # 结果: coding 配置文件但没有 exec 工具
-pnpm agent:cli --profile my-agent --tools-deny exec "list files"
+multica run --profile my-agent --tools-deny exec "list files"
 ```
 
 ## 未来工具