clip-aware-embeddings
关于
This skill enables semantic image-text matching using CLIP and alternative models for tasks like image search, similarity matching, and zero-shot classification. It's designed for developers needing to find or categorize images based on semantic content rather than object detection. The skill explicitly avoids fine-grained classification, object counting, and spatial reasoning tasks.
快速安装
Claude Code
推荐npx skills add majiayu000/claude-skill-registry -a claude-code/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/clip-aware-embeddings在 Claude Code 中复制并粘贴此命令以安装该技能
GitHub 仓库
Frequently asked questions
What is the clip-aware-embeddings skill?
clip-aware-embeddings is a Claude Skill by majiayu000. Skills package instructions and resources that Claude loads on demand, so Claude can perform clip-aware-embeddings-related tasks without extra prompting.
How do I install clip-aware-embeddings?
Use the install commands on this page: add clip-aware-embeddings to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does clip-aware-embeddings belong to?
clip-aware-embeddings is in the AI & Machine Learning category, tagged clip, embeddings, vision, similarity and zero-shot.
Is clip-aware-embeddings free to use?
Yes. clip-aware-embeddings is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
这是一个自动优化提示词的Claude Skill，能拦截复杂任务请求并使用MCP服务器进行智能提示工程改进。它通过学习历史交互的嵌入索引来持续提升优化效果，适用于需要系统化提示优化的开发场景。开发者只需在提出复杂任务或明确要求优化提示时触发，对简单查询则会直接响应。
这是专门为Discord、Telegram和Slack平台开发聊天机器人的专家技能。它擅长处理速率限制、状态机、事件溯源和审核系统等复杂架构问题。当您需要构建生产级的聊天自动化或审核机器人时，可以激活此技能。
这是一个自动优化提示词的Claude Skill，专为复杂任务设计。它能通过MCP服务器分析历史性能并应用APE、OPRO等先进模式来持续改进提示词。当开发者请求优化提示、进行提示工程或处理复杂任务时自动激活，但不适用于简单问答或直接命令执行。
该Skill提供基于CLIP的语义图像-文本匹配能力，适用于图像搜索、零样本分类和相似度匹配等场景。它明确区分适用边界（不支持物体计数、细粒度分类等任务），并集成多种工具来获取最新替代方案和基准数据。开发者可通过"CLIP"、"embeddings"等关键词激活，并与内容识别、拼图布局等Skill配合使用。