feat: document asynchronous avatars for created agents (#204)

创建和更新智能体的中英文技能现在说明自动异步头像：默认透明真人，显式外貌/风格/背景要求优先；用户图片优先，删除或关闭可取消任务。旧客户端按实际工具
Schema 使用，图像服务条款、额度与费用明确披露。

The bilingual creation/update skills document automatic asynchronous
avatars, user customization, image precedence, cancellation,
older-client schema detection, and image-provider prerequisites and
costs.

验证 / Validation: focused i18n validation and translation freshness
passed; catalog validation has zero errors (existing repository warnings
remain).

skills/create-agent/SKILL.md

@@ -2,8 +2,9 @@
 license: "MIT"
 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: 2.6.1
+  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。可选头像生成需配置图像服务，适用供应商条款/额度及独立费用。
+version: 2.7.0
+compatibility: "DesireCore ManageAgent; optional avatar generation requires a configured image provider under its own terms and quota, with separate charges; unavailable generation retains the existing avatar."
 type: meta
 risk_level: low
 status: enabled
@@ -14,7 +15,7 @@ tags:
   - meta
 metadata:
   author: desirecore
-  updated_at: '2026-08-25'
+  updated_at: '2026-10-03'
   i18n:
     default_locale: en-US
     source_locale: zh-CN
@@ -25,17 +26,17 @@ metadata:
       name: 创建智能体
       short_desc: 通过自然语言对话收集需求，一键创建专业化数字智能体
       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。
+        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。可选头像生成需配置图像服务，适用供应商条款/额度及独立费用。
       body: ./SKILL.zh-CN.md
-      source_hash: sha256:14e8755703784086
+      source_hash: sha256:7ffb7a362c26a91e
       translated_by: human
     en-US:
       name: Create Agent
       short_desc: Collect requirements through natural-language conversation and create a specialized digital Agent in one step
       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.
+        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. Optional avatar generation requires a configured image service under provider terms/quota and separate charges.
       body: ./SKILL.md
-      source_hash: sha256:14e8755703784086
+      source_hash: sha256:7ffb7a362c26a91e
       translated_by: human
 market:
   icon: >-
@@ -172,6 +173,14 @@ ManageAgent({
 
 `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.
 
+### Automatic asynchronous avatar
+
+Check readiness through the current governed tool catalog: use `ManageCompute(action="list")` for enabled/credential status and `InspectModels(action="list", serviceType="image_gen")` for an eligible image model. Neither listing proves upstream quota or call success; follow provider terms/quota and separate charges. Do not read keys or use local HTTP. If these tools are absent, follow the configuring-compute skill's governed GUI observation. If generation is known unavailable, create with `avatarGeneration.enabled:false`, preserve the character avatar and report the limitation; this opt-out also covers unavailable service, not only user refusal. Unknown readiness is not success; inspect the background task result and do not fabricate completion.
+
+Generation requires a configured image provider and its own service terms/quota; provider charges are separate from this skill. Without a usable provider, keep the character avatar and report the failed task.
+
+Read the actual `ManageAgent` schema. On clients exposing `avatarGeneration`, creation automatically queues a transparent photorealistic portrait without waiting for generation. Do not ask for appearance preferences when the user has none, and do not call GenerateImage a second time for the same creation. Preserve explicit user requirements with `avatarGeneration.prompt`; use `transparentBackground:false` only for an explicitly requested background, or `enabled:false` when the user explicitly wants no generated image. Supplying `avatarImage.source` takes precedence. Inspect queued/running/completed/failed/interrupted state through `ManageAgent(get)`; failure retains the character avatar and does not require recreating the Agent. On an older client without the field, follow its declared schema and never send unsupported parameters.
+
 ### 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

@@ -112,6 +112,14 @@ ManageAgent({
 
 `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。
 
+### 自动异步头像
+
+通过当前受治理工具目录检查就绪状态：用 `ManageCompute(action="list")` 查看启用/凭据状态，用 `InspectModels(action="list", serviceType="image_gen")` 查看可用图像模型。列表不证明上游额度或调用成功，遵守供应商条款/额度及独立费用；不读取密钥，不用本机 HTTP 旁路。缺少这些工具时，遵循 configuring-compute 技能的受治理 GUI 观察流程。已知生成不可用时，创建传 `avatarGeneration.enabled:false`，保留字符头像并报告限制；此关闭也适用于服务不可用，不限于用户拒绝。就绪状态未知不代表成功，检查后台任务结果，不伪造完成。
+
+生成需要已配置的图像供应商及对应服务条款/额度，供应商费用独立于此技能。没有可用供应商时保留字符头像，并如实报告任务失败。
+
+先核对当前 `ManageAgent` Schema。提供 `avatarGeneration` 的新客户端会在创建成功后自动排队生成透明真人摄影头像，创建不等待生图；用户没有外貌要求时不要额外提问，不要为同一次创建再次调用 GenerateImage。用户明确的外貌/风格要求放入 `avatarGeneration.prompt`；明确要求背景才设 `transparentBackground:false`，明确不要生成才设 `enabled:false`。已有图片通过 `avatarImage.source` 设置并优先保留。用 `ManageAgent(get)` 查看 queued/running/completed/failed/interrupted 状态；失败保留字符头像，不重复创建。旧客户端没有该字段时遵从其实际声明，不发送新参数。
+
 ### 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。

skills/create-agent/catalog-metadata.v1.json

@@ -11,12 +11,12 @@
       "zh-CN": {
         "name": "创建智能体",
         "summary": "通过自然语言对话收集需求，一键创建专业化数字智能体",
-        "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。"
+        "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。可选头像生成需配置图像服务，适用供应商条款/额度及独立费用。"
       },
       "en-US": {
         "name": "Create Agent",
         "summary": "Collect requirements through natural-language conversation and create a specialized digital Agent in one step",
-        "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."
+        "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. Optional avatar generation requires a configured image service under provider terms/quota and separate charges."
       }
     },
     "category": "productivity",
@@ -28,7 +28,7 @@
   },
   "release": {
     "state": "known",
-    "version": "2.6.1",
+    "version": "2.7.0",
     "versionScheme": "semver"
   },
   "timestamps": {