billowliu2
43f09c83f4
利用 kimi-code 的 /skill 文本通道（rewriteMediaPlaceholders 把图片渲染成 Attached image file 路径，不产生 image part），让纯文本主模型也能粘贴看图：用户 /skill kimi-eyes + Alt-V 粘贴，模型从路径调 read_image 拿回文字描述。新增 skills/kimi-eyes/SKILL.md；README（中英）+ 网页新增「看图方式 × image_in」对比表与 /skill 配置说明。1.0.6 → 1.0.7。
30 lines
896 B
JSON
30 lines
896 B
JSON
{
|
|
"name": "kimi-eyes",
|
|
"version": "1.0.7",
|
|
"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",
|
|
"image",
|
|
"screenshot",
|
|
"multimodal",
|
|
"vlm"
|
|
],
|
|
"author": "kimi-eyes",
|
|
"license": "MIT",
|
|
"interface": {
|
|
"displayName": "Kimi Eyes",
|
|
"shortDescription": "视觉辅助：让非多模态模型也能分析图片/截图",
|
|
"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",
|
|
"mcpServers": {
|
|
"kimi-eyes": {
|
|
"command": "node",
|
|
"args": [
|
|
"./mcp/server.mjs"
|
|
],
|
|
"cwd": "./"
|
|
}
|
|
}
|
|
}
|