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/create-agent/SKILL.md

@@ -2,7 +2,7 @@
 name: create-agent
 description: >-
   通过多轮对话收集需求，调用 ManageAgent 内置工具创建新的 AgentFS v2 智能体，支持自定义 persona 和 principles。Use when 用户要求创建新智能体、培养某领域助手、或快速基于模板生成可治理 Agent。
-version: 2.5.4
+version: 2.6.0
 type: meta
 risk_level: low
 status: enabled
@@ -13,7 +13,7 @@ tags:
   - meta
 metadata:
   author: desirecore
-  updated_at: '2026-07-19'
+  updated_at: '2026-08-25'
   i18n:
     default_locale: en-US
     source_locale: zh-CN
@@ -26,7 +26,7 @@ metadata:
       description: >-
         通过多轮对话收集需求，调用 ManageAgent 内置工具创建新的 AgentFS v2 智能体，支持自定义 persona 和 principles。Use when 用户要求创建新智能体、培养某领域助手、或快速基于模板生成可治理 Agent。
       body: ./SKILL.zh-CN.md
-      source_hash: sha256:52972ee5408bc49f
+      source_hash: sha256:14e8755703784086
       translated_by: human
     en-US:
       name: Create Agent
@@ -34,9 +34,8 @@ metadata:
       description: >-
         Collect requirements through multi-turn conversation and call the ManageAgent builtin tool to create a new AgentFS v2 Agent, with customizable persona and principles. Use when the user asks to create a new Agent, raise a domain assistant, or quickly produce a governable Agent from a template.
       body: ./SKILL.md
-      source_hash: sha256:52972ee5408bc49f
-      translated_by: ai:claude-fable-5
-      translated_at: '2026-07-19'
+      source_hash: sha256:14e8755703784086
+      translated_by: human
 market:
   icon: >-
     <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0
@@ -127,9 +126,51 @@ ManageAgent({
 
 - Minimal create needs only `{ "action": "create", "name": "My Assistant" }` (everything else auto-generated).
 - Basic create `{ "action": "create", "name": "Legal Advisor", "description": "contract review" }` — with just name + description, the description auto-fills persona's L0.
-- Optional `id` (kebab-case slug; `core` / `desirecore` are reserved core identifiers and cannot be used, including when the slug auto-generated from `name` collides), `config.llm` (llm delta only; sensitive fields like mcp_servers are rejected and must be adjusted via the UI after creation).
+- Optional `id` (kebab-case slug; `core` / `desirecore` are reserved core identifiers and cannot be used, including when the slug auto-generated from `name` collides), `config`, `smartRouting`, and `avatarImage`. See the contracts below. Sensitive fields such as `mcp_servers` and `tool_permissions` are rejected and must be adjusted through the UI after creation.
 - The Agent is registered and usable immediately; the returned ID works directly with ManageTeam / Delegate. If the tool errors (already exists / reserved identifier / non-whitelisted config field, etc.), explain the reason and retry after adjusting per the hint.
 
+#### Creation Parameter Guide
+
+**Smart routing**: new Agents default to the Smart flagship tier. When responsibilities require an explicit tier, pass `smartRouting`:
+
+```json
+{
+  "tier": "balanced",
+  "requiredCapabilities": ["vision", "tool_use"],
+  "reasoning": "high"
+}
+```
+
+- `tier` accepts `lightweight`, `balanced`, or `flagship`; `reasoning` accepts `auto`, `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max`.
+- Omitting `tier` defaults to `flagship`. This expresses workload and capability intent, not a concrete Provider or model.
+- Fixed model, Provider, and Smart/fixed selection are governed by the human model selector and cannot be changed through ManageAgent.
+- Natural-language requests such as "deepest/highest/max it out" normally map to `xhigh`; use `max` only when the user explicitly names it and the model supports it.
+
+**Configuration patch**: `config` supports only `llm` and declarative avatar settings. It is normally unnecessary during creation; use it only when the Agent needs a different default reasoning behavior:
+
+```json
+{
+  "llm": {
+    "reasoning": "high",
+    "maxRetryDelayMs": 30000
+  },
+  "avatar": {
+    "char": "L",
+    "color": "purple"
+  }
+}
+```
+
+`config.llm` currently exposes only `reasoning`, `thinkingBudgets`, and `maxRetryDelayMs`. Do not pass `model`, `provider`, `providerId`, or `routingMode`.
+
+**Image avatar**: use the separate `avatarImage` parameter; do not place image data in `config`:
+
+```json
+{ "source": "dc-media://<mediaId>" }
+```
+
+`source` may be a media ID from the current turn or a PNG/JPEG/WebP file inside the working directory. URLs and base64 are rejected. The service crops to 512×512 WebP and removes EXIF automatically. Avatar failure does not roll back an otherwise successful Agent creation; retry only the avatar operation according to the receipt.
+
 ### Stage 6: Receipt
 
 Present in a user-friendly way (no internal paths / technical details): confirm success and suggest next steps — start chatting, add skills, adjust persona or rules.

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

@@ -67,9 +67,51 @@ ManageAgent({
 
 - 最简创建只需 `{ "action": "create", "name": "我的助手" }`（其余全自动生成）。
 - 基础创建 `{ "action": "create", "name": "法律顾问", "description": "专注合同审查" }`——只给 name + description，description 会自动填充 persona 的 L0。
-- 可选 `id`（kebab-case slug；`core` / `desirecore` 为核心保留标识不可用，含 name 自动生成命中的情况）、`config.llm`（仅 llm 增量；mcp_servers 等敏感字段会被拒，需创建后经界面调整）。
+- 可选 `id`（kebab-case slug；`core` / `desirecore` 为核心保留标识不可用，含 name 自动生成命中的情况）、`config`、`smartRouting` 与 `avatarImage`。详细契约见下方；`mcp_servers`、`tool_permissions` 等敏感字段会被拒，需创建后经界面调整。
 - 创建后智能体立即在线可用，返回 ID 可直接用于 ManageTeam / Delegate。若工具报错（已存在 / 命中保留标识 / config 非白名单字段等），向用户说明原因并按提示调整后重试。
 
+#### 创建参数说明
+
+**智能路由**：新建 Agent 默认使用 Smart 旗舰量级。需要按职责控制量级时传 `smartRouting`：
+
+```json
+{
+  "tier": "balanced",
+  "requiredCapabilities": ["vision", "tool_use"],
+  "reasoning": "high"
+}
+```
+
+- `tier` 可选 `lightweight`、`balanced`、`flagship`；`reasoning` 可选 `auto`、`off`、`minimal`、`low`、`medium`、`high`、`xhigh`、`max`。
+- `tier` 未传时默认 `flagship`；只表达任务量级和能力需求，不绑定具体 Provider 或模型。
+- 固定模型、Provider、Smart/fixed 模式由人类模型选择器管理，不能通过 ManageAgent 修改。
+- 用户说“最深/最高/拉满”通常对应 `xhigh`；只有用户明确点名 `max` 且模型支持时才使用 `max`。
+
+**配置增量**：`config` 只支持 `llm` 与声明头像 `avatar`。创建时通常无需传；确需调整默认推理行为时可用：
+
+```json
+{
+  "llm": {
+    "reasoning": "high",
+    "maxRetryDelayMs": 30000
+  },
+  "avatar": {
+    "char": "法",
+    "color": "purple"
+  }
+}
+```
+
+`config.llm` 当前只开放 `reasoning`、`thinkingBudgets`、`maxRetryDelayMs`。不要传 `model`、`provider`、`providerId` 或 `routingMode`。
+
+**图片头像**：使用独立的 `avatarImage`，不要把图片写进 `config`：
+
+```json
+{ "source": "dc-media://<mediaId>" }
+```
+
+`source` 可以是本轮媒体 ID 或工作目录内的 PNG/JPEG/WebP 文件；不接受 URL 或 base64。服务端会自动裁成 512×512 WebP 并移除 EXIF。头像失败不会回滚已经成功创建的 Agent，需根据工具回执单独重试头像设置。
+
 ### 阶段 6：回执
 
 以用户友好方式呈现（不暴露内部路径/技术细节）：告知创建成功，并提示下一步——直接对话、添加技能、调整人格或规则。