feat: skill 随插件自动注册，免去 extra_skill_dirs 配置

kimi.plugin.json 声明 skills:["./skills"]，/plugins install 后 /skill kimi-eyes 经 PluginSkillSource 自动注册（源码 manifest.ts:100 + pluginSkillRoots 全链路证实）；package.json files 补 skills/；README（中英）与网页把「两步配置」简化为「一步」（只声明 image_in）。1.0.7 → 1.0.8。

README.en.md

@@ -152,22 +152,16 @@ capabilities = [ "thinking", "tool_use", "image_in" ]   # append image_in
 
 The warning above says: on a text-only provider, declaring `image_in` and using **Alt-V paste** sends an `image_url` part to the provider and triggers a 400. But the same `image_in` declaration is harmless if you go through the **`/skill` command** instead — `/skill` renders the pasted image as an `Attached image file: <path>` **plain-text path**, producing no image part. This plugin ships a skill that exploits exactly this channel.
 
-**One-time setup (two steps)**:
+**One-time setup**:
 
-1. Declare `image_in` on the text-only model (only to pass the `/skill` frontend check; `/skill` sends no image part, so **no 400**):
+Declare `image_in` on the text-only model (only to pass the `/skill` frontend check; `/skill` sends no image part, so **no 400**):
 
 ```toml
 [models."opencode-go/deepseek-v4-flash"]
 capabilities = [ "thinking", "tool_use", "image_in" ]   # append image_in
 ```
 
-2. Register the skill — add the plugin's `skills/` dir to the scan list in `~/.kimi-code/config.toml`:
+> The skill ships with the plugin — `kimi.plugin.json` declares `skills`, so after `/plugins install kimi-eyes` the `/skill kimi-eyes` command is auto-registered into the `/` completion menu. **No `extra_skill_dirs` needed.**
-
-```toml
-extra_skill_dirs = [ "D:/AIGC/Plugin/kimi-eyes/skills" ]
-```
-
-> If the plugin lives elsewhere, use its actual `kimi-eyes/skills` path. After restarting the session, `/skill kimi-eyes` appears in the `/` completion menu.
 
 **Usage**:
 

README.md

@@ -117,22 +117,16 @@ capabilities = [ "thinking", "tool_use", "image_in" ]   # 追加 image_in
 
 上面警告过：纯文本 provider 声明 `image_in` 后走 **Alt-V 粘贴**，图片会作为 `image_url` part 发给 provider 触发 400。但同样声明 `image_in`，改走 **`/skill` 命令**就不会 400——`/skill` 通道把图片渲染成 `Attached image file: <路径>` 的**纯文本路径**，不产生 image part。本插件自带一个 skill 利用这条通道。
 
-**一次性配置（两步）**：
+**一次性配置**：
 
-1. 给纯文本模型声明 `image_in`（仅为通过 `/skill` 的前端校验；`/skill` 下图片不走 part，**不会**触发 400）：
+给纯文本模型声明 `image_in`（仅为通过 `/skill` 的前端校验；`/skill` 下图片不走 part，**不会**触发 400）：
 
 ```toml
 [models."opencode-go/deepseek-v4-flash"]
 capabilities = [ "thinking", "tool_use", "image_in" ]   # 追加 image_in
 ```
 
-2. 注册 skill——在 `~/.kimi-code/config.toml` 把插件目录的 `skills/` 加入扫描：
+> skill 由插件自带——`kimi.plugin.json` 已声明 `skills`，`/plugins install kimi-eyes` 后 `/skill kimi-eyes` 自动注册到 `/` 补全菜单，**无需** `extra_skill_dirs`。
-
-```toml
-extra_skill_dirs = [ "D:/AIGC/Plugin/kimi-eyes/skills" ]
-```
-
-> 插件装在别处就换成实际的 `kimi-eyes/skills` 目录。重启会话后 `/skill kimi-eyes` 会出现在 `/` 补全菜单。
 
 **用法**：
 

docs/index.html

@@ -431,7 +431,7 @@ npx kimi-eyes setup
 @截图.png 这个图里有什么?     <span class="cmt"># → read_image</span>
 分析这张截图                 <span class="cmt"># → read_clipboard_image</span>
 
-<span class="cmt"># 纯文本模型想「粘贴」看图（需先声明 image_in + 注册 skill，详见 README）：</span>
+<span class="cmt"># 纯文本模型想「粘贴」看图（需先声明 image_in；skill 随插件自动注册，详见 README）：</span>
 /skill kimi-eyes 这张图说明什么? <span class="cmt"># 然后 Alt-V 粘贴图片，回车</span></pre>
           </div>
         </div>

kimi.plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "kimi-eyes",
-  "version": "1.0.7",
+  "version": "1.0.8",
   "description": "Give non-multimodal models vision: analyze local images and clipboard screenshots through a user-configured VLM API (OpenAI-compatible or Anthropic protocol).",
   "keywords": [
     "vision",
@@ -17,6 +17,9 @@
     "longDescription": "读取本地图片或剪贴板截图，调用用户自配的多模态 API（OpenAI 兼容或 Anthropic 协议）返回描述。多模态模型不受影响，粘贴即原生看图。"
   },
   "systemPromptPath": "./SYSTEM.md",
+  "skills": [
+    "./skills"
+  ],
   "mcpServers": {
     "kimi-eyes": {
       "command": "node",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "kimi-eyes",
-  "version": "1.0.7",
+  "version": "1.0.8",
   "description": "Give non-multimodal models in Kimi Code the ability to analyze images and screenshots via a user-configured VLM (OpenAI-compatible or Anthropic protocol).",
   "keywords": [
     "kimi",
@@ -24,6 +24,7 @@
   "files": [
     "mcp/",
     "scripts/",
+    "skills/",
     "SYSTEM.md",
     "kimi.plugin.json",
     "setup.mjs",