feat(skills): 独立维护智能体生命周期操作说明 (#90)

## 中文

### 变更
- 新增 `clone-agent` 内置 Skill，覆盖私有数据复制和团队分发边界
- 将 Smart routing、reasoning、头像和确认流程迁入 action-specific Skills
- 修正 `update-agent` 与当前 ManageAgent 白名单的漂移
- 保持所有市场 Skill 按需加载，并加入 builtin 清单

### 验证
- `uv run --quiet scripts/i18n/test_validate_i18n.py`
- `uv run --quiet scripts/i18n/validate-i18n.py`
- `uv run --quiet scripts/i18n/translate.py --check`
- 公共信息边界检查通过

## English

### Changes
- Add the built-in `clone-agent` Skill for private-data copy and
team-distribution boundaries
- Move Smart routing, reasoning, avatar, and confirmation workflows into
action-specific Skills
- Align `update-agent` with the current ManageAgent configuration
whitelist
- Keep every marketplace Skill on-demand and add the new Skill to the
built-in manifest

### Verification
- `uv run --quiet scripts/i18n/test_validate_i18n.py`
- `uv run --quiet scripts/i18n/validate-i18n.py`
- `uv run --quiet scripts/i18n/translate.py --check`
- Public information boundary review passed

skills/delete-agent/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: delete-agent
 description: 安全删除指定的智能体及其关联数据。删除前会验证智能体状态，支持可选地删除所有会话历史。Use when 用户需要删除不再使用的智能体。
-version: 2.5.2
+version: 2.6.0
 type: meta
 risk_level: high
 status: enabled
@@ -12,7 +12,7 @@ tags:
   - meta
 metadata:
   author: desirecore
-  updated_at: '2026-07-19'
+  updated_at: '2026-08-25'
   i18n:
     default_locale: en-US
     source_locale: zh-CN
@@ -24,16 +24,15 @@ metadata:
       short_desc: 安全删除智能体及其关联数据，支持多重确认与可选历史清理
       description: 安全删除指定的智能体及其关联数据。删除前会验证智能体状态，支持可选地删除所有会话历史。Use when 用户需要删除不再使用的智能体。
       body: ./SKILL.zh-CN.md
-      source_hash: sha256:d5eb268aa5209e88
+      source_hash: sha256:b401869e91222236
       translated_by: human
     en-US:
       name: Delete Agent
       short_desc: Safely delete an Agent and its associated data, with multi-step confirmation and optional history cleanup
       description: Safely delete a specified Agent and its associated data. Verifies the Agent's state before deletion and optionally removes all session history. Use when the user needs to delete an Agent that is no longer in use.
       body: ./SKILL.md
-      source_hash: sha256:d5eb268aa5209e88
-      translated_by: ai:claude-fable-5
-      translated_at: '2026-07-19'
+      source_hash: sha256:b401869e91222236
+      translated_by: human
 market:
   icon: >-
     <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0
@@ -88,7 +87,7 @@ Ask whether to also delete all of the Agent's conversation history: yes → `del
 
 ### Stage 4: Execute Deletion
 
-Before the call, tell the user "the system will pop up a confirmation window; please confirm there" (delete is force-confirmed at the tool layer). Execute:
+Before the call, reconfirm the target and the `deleteRuns` choice. The tool submits deletion to the current approval chain; whether an additional dialog appears depends on the caller's approval mode. Do not promise that a dialog will appear unless an approval event is actually shown. Execute:
 
 ```
 ManageAgent(action='delete', id='legal-assistant', deleteRuns=true)
@@ -104,4 +103,4 @@ From the tool's return (cleaned paths, deleted run count, memory-cleanup details
 
 - **Always deleted**: AgentFS directory (config/persona/rules/skills/tools/memory), user preference data, in-memory state (scheduler/queue/message subscriptions/MCP connections), registry entry. **Optionally deleted** (`deleteRuns=true`): conversation history and topic index. **Team cascade** (automatic): supervisor → disband team, member → remove. **Kept**: other Agents, user config, global settings, market cache.
 - Explain tool refusals to the user with a next step: the core agent (desirecore / core / bound UUID) cannot be deleted; the caller can't delete itself; active state (online/busy/recovery) needs stopping in the UI first or waiting until idle; a non-existent ID means the Agent is already gone or the ID is wrong.
-- Always done via `ManageAgent` (`action='list' | 'get' | 'delete'`); delete is a high-risk operation and is force-confirmed at the tool layer.
+- Always done via `ManageAgent` (`action='list' | 'get' | 'delete'`). Deletion is high risk: complete this skill's explicit intent confirmation first, then follow the approval result returned by the tool.

skills/delete-agent/SKILL.zh-CN.md

@@ -33,7 +33,7 @@
 
 ### 阶段 4：执行删除
 
-调用前告知用户"系统会弹确认窗，请在弹窗中确认"（delete 由工具层强制弹确认）。执行：
+调用前再次确认目标和 `deleteRuns` 选择。工具会把删除提交到当前审批链；是否出现额外弹窗取决于调用方的审批模式，不要在没有看到审批事件时声称“一定会弹窗”。执行：
 
 ```
 ManageAgent(action='delete', id='legal-assistant', deleteRuns=true)
@@ -49,4 +49,4 @@ ManageAgent(action='delete', id='legal-assistant', deleteRuns=true)
 
 - **始终删**：AgentFS 目录（配置/人格/规则/技能/工具/记忆）、用户偏好数据、内存状态（调度器/队列/消息订阅/MCP 连接）、注册表条目。**可选删**（`deleteRuns=true`）：会话历史与话题索引。**团队级联**（自动）：组长 → 解散团队、成员 → 移除。**保留不删**：其他智能体、用户配置、全局设置、市场缓存。
 - 工具拒绝场景据此向用户解释并给下一步：核心智能体（desirecore / core / 绑定 UUID）不可删；不能删调用方自身；活跃态（online/busy/recovery）需先在 UI 停止或等其空闲；ID 不存在则智能体已删或 ID 有误。
-- 一律经 `ManageAgent`（`action='list' | 'get' | 'delete'`）完成；delete 为高风险操作，工具层强制弹确认。
+- 一律经 `ManageAgent`（`action='list' | 'get' | 'delete'`）完成；delete 为高风险操作，必须先完成本技能的明确意图确认，并遵循工具返回的审批结果。