semantic-router
由 halfmoon82 提供
Productivity & Tasks简介
Auto-routing skill with configurable model pools and task type matching.
描述
该技能的功能
Routes each AI agent message to one of four model pools based on keyword detection, semantic similarity scoring, and contextual continuity. Uses a five-branch decision tree to switch models, maintain sessions, or reset conversations when topics change. Also isolates background cron jobs from user-facing sessions to prevent interruptions.
Reduces token costs and latency by matching each message to an appropriately scoped model rather than routing everything through a single expensive model.
何时使用
- Switching to a fast model for quick lookups while keeping a capable model for coding tasks
- Automatically resetting the session when the conversation topic shifts completely
- Preventing scheduled background jobs from disrupting an ongoing chat session
- Routing long-context or multi-step agent tasks to a high-context model pool
- Matching translation or writing requests to a content-optimized model
示例工作流
User asks: 'Help me write a Python web scraper'
- 1
semantic_check.py receives the message and checks it against system filters
- 2
Keyword match found: 'write' and 'scraper' classify the message as a development task
- 3
Router selects branch C and targets the Intelligence pool
- 4
Session model is patched via sessions.patch to the configured Intelligence pool model
- 5
A routing tag is prepended to the agent response instructing the LLM to output the active pool and model on the first line
Response generated by the Intelligence pool model, with a routing declaration in the first line indicating the active pool and model ID
前置要求
- API keys for at least one configured model provider (e.g., Anthropic, Google AI, OpenAI)
安装
clawhub install halfmoon82/semantic-router运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。