Semantic Model Orchestrator
This skill provides an intelligent middle layer for AI agents to decide which model tier should handle a specific task. By using semantic analysis, it categorized queries into Elite, Balanced, or Basic levels.
Features
- - Semantic Intent Recognition: Uses vector embeddings to detect query complexity.
- Cost-Efficiency Orchestration: Routes queries to Elite, Balanced, or Basic models.
- ClawHub Optimized: Default tiers for Claude 3.5 Sonnet, GPT-4o-mini, and DeepSeek.
- Rolling Adjustment: Built-in logic to refine intent keywords from user history.
- Multi-Provider Support: Supports OpenAI, Anthropic, Gemini, and DeepSeek.
Model Tiers
- - Elite: INLINECODE0
- Balanced: INLINECODE1
- Basic: INLINECODE2
Usage
Add this skill to your agent's capability list. The agent will call the
get_optimal_model tool before making main LLM calls to optimize performance and budget.
Example Tool Call
CODEBLOCK0
语义模型编排器
该技能为AI代理提供了一个智能中间层，用于决定应由哪个模型层级处理特定任务。通过语义分析，它将查询分类为精英级、均衡级或基础级。
功能特性
- - 语义意图识别：使用向量嵌入检测查询复杂度。
- 成本效益编排：将查询路由至精英级、均衡级或基础级模型。
- ClawHub优化：Claude 3.5 Sonnet、GPT-4o-mini和DeepSeek的默认层级。
- 滚动调整：内置逻辑，根据用户历史记录优化意图关键词。
- 多提供商支持：支持OpenAI、Anthropic、Gemini和DeepSeek。
模型层级
- - 精英级：anthropic/claude-3-5-sonnet-latest
- 均衡级：openai/gpt-4o-mini
- 基础级：deepseek/deepseek-chat
使用方法
将此技能添加到代理的能力列表中。代理将在进行主要LLM调用前调用get
optimalmodel工具，以优化性能和预算。
示例工具调用
python
result = router.analyze
androute(为金融科技应用设计一个高可扩展的微服务架构。)
返回：{tier: ELITE, suggested_model: anthropic/claude-3-5-sonnet-latest}
