10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 470 ms
modelrecord
- tool-calling
Can call tools (function calling).
- structured-outputs
Can return JSON matching a schema.
- text->text
Takes text; returns text.
- tool-calling
modelrecord18,205 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord
- text+image+video+audio->text
Takes text, image, video, audio; returns text.
- text+image+video+audio->text
modelrecord
- text+audio+image+video->text
Takes text, audio, image, video; returns text.
- text+audio+image+video->text
skillxiaomimimo/mimo-skillsrecord
- mimo-v2-5-tts
MiMo V2.5 TTS 语音合成。使用小米 MiMo V2.5 TTS 系列模型生成语音。当需要将文字转为语音、发送语音消息、朗读内容、或用户要求「说出来」「语音回复」时激活此 skill。支持预置音色、音色设计、音色克隆三种模式,支持自然语言控制、导演模式,支持语气、情绪、方言的风格标签控制,预置音色支持唱歌。
- mimo-v2-5-tts
modelrecord
- ai
Task: AI
- ai
- 7mimo-understand-image-mcpfound in code, not yet checkedno passport yet
MCP serveryipleo/mimo-understand-image-mcp
- understand_image
Analyze one or more images with Xiaomi MiMo v2.5. Use this whenever Claude Code needs to inspect screenshots, diagrams, UI mocks, photos, or local image files. Supports HTTP/HTTPS URLs, file paths, file:// URLs, and data:image base64 URLs.
- understand_image
- 8mimo-visionfound in code, not yet checkedno passport yet
- analyze_image
用 MiMo-V2.5 视觉模型分析一张本地图片(UI 截图、网页截图、报错截图、设计参考图等),返回布局、排版、间距、配色与视觉问题等分析结果,供 Coding Agent 直接使用。 主动调用时机(用户提到以下任一情况时,应主动调用本工具,无需用户明确说"调用 MCP"):用户要求"看看/分析这张图";用户给出本地截图路径;涉及 UI/网页/报错截图;涉及设计参考图;要提取图片中的文字或内容;视觉验收;判断当前实现是否接近参考图。 参数:image_path 必填;prompt 可选,指定重点分析什么。
- analyze_image
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.