Token导航 LogoToken导航

Agent Skill · 研究检索

router-builder(路由器建造者)

router-builder 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

router-builder 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 61,604。

总安装 349周安装 14GitHub Stars 2下载 113核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:router-builder(路由器建造者)
来源仓库:https://github.com/mindmorass/reflex
仓库路径:skills/router-builder
安装命令:
npx skills add https://github.com/mindmorass/reflex --skill router-builder
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/mindmorass/reflex --skill router-builder

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

router-builder 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词快速定位候选结果时使用。它适用于研究检索类任务,可结合来源仓库和原始 README 进一步核验具体用法。

通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。安装前建议确认权限范围、维护状态,以及是否会触发联网或文件读写操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/router-builder

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/mindmorass/reflex --skill router-builder;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

router-builder 怎么安装?

在终端执行 npx skills add https://github.com/mindmorass/reflex --skill router-builder。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

router-builder 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

router-builder 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

router-builder 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

router-builder 用的人多吗?

公开数据是累计安装 349 次,近一周安装 14 次,下载 113 次,GitHub 2 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

router-builder 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
router-builder

路由器建造者 · 本页

3492调用外部服务MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Router Builder Skill

Build the Semantic Router for intelligent resource selection.

Overview

The router provides fast, embedding-based routing to:

  • Slash commands
  • Sub-agents
  • Skills
  • Workflows

Uses the same embedding model as RAG for consistency.

Prerequisites

pip install semantic-router sentence-transformers pyyaml

Build Steps

Step 1: Create Router Core

File: routing/router.py

#!/usr/bin/env python3
"""
Hierarchical Semantic Router

Two-tier routing:
- Tier 1: Category (command | agent | skill | workflow)
- Tier 2: Specific resource within category
"""

import os
import yaml
from pathlib import Path
from typing import Optional, Dict, List, Tuple
from dataclasses import dataclass
from enum import Enum

from semantic_router import Route
from semantic_router.layer import RouteLayer
from semantic_router.encoders import HuggingFaceEncoder

# Configuration
ROUTES_PATH = Path(os.getenv("ROUTES_PATH", "./routing/routes"))
CONFIDENCE_THRESHOLD = float(os.getenv("ROUTING_CONFIDENCE", "0.5"))

class Category(Enum):
    COMMAND = "command"
    AGENT = "agent"
    SKILL = "skill"
    WORKFLOW = "workflow"
    GENERAL = "general"

@dataclass
class RoutingResult:
    """Result of a routing decision."""
    category: Category
    resource: Optional[str]
    confidence: float
    metadata: Dict
    fallback: bool = False

class Router:
    """Hierarchical semantic router."""

    def __init__(self):
        # Use same model as RAG
        self.encoder = HuggingFaceEncoder(name="all-MiniLM-L6-v2")
        self.category_layer = self._build_category_layer()
        self.domain_layers: Dict[Category, RouteLayer] = {}
        self._build_domain_layers()

    def _load_routes(self, path: Path) -> List[Route]:
        """Load routes from YAML."""
        if not path.exists():
            return []

        with open(path) as f:
            data = yaml.safe_load(f) or {}

        return [
            Route(
                name=r["name"],
                utterances=r["utterances"],
                metadata=r.get("metadata", {})
            )
            for r in data.get("routes", [])
        ]

    def _build_category_layer(self) -> RouteLayer:
        """Build tier-1 category router."""
        routes = self._load_routes(ROUTES_PATH / "categories.yaml")

        if not routes:
            # Default routes
            routes = [
                Route(name="command", utterances=[
                    "/research", "/code-review", "/daily-standup",
                    "run the command", "execute command", "use slash command"
                ]),
                Route(name="agent", utterances=[
                    "ask the researcher", "have the coder", "use the analyst",
                    "delegate to agent", "agent should handle"
                ]),
                Route(name="skill", utterances=[
                    "use the skill", "apply skill", "leverage skill for"
                ]),
                Route(name="workflow", utterances=[
                    "run workflow", "start pipeline", "execute automation"
                ]),
            ]

        return RouteLayer(encoder=self.encoder, routes=routes)

    def _build_domain_layers(self):
        """Build tier-2 domain routers."""
        mappings = {
            Category.COMMAND: "commands.yaml",
            Category.AGENT: "agents.yaml",
            Category.SKILL: "skills.yaml",
            Category.WORKFLOW: "workflows.yaml",
        }

        for category, filename in mappings.items():
            routes = self._load_routes(ROUTES_PATH / filename)
            if routes:
                self.domain_layers[category] = RouteLayer(
                    encoder=self.encoder,
                    routes=routes
                )

    def route(self, query: str) -> RoutingResult:
        """Route a query through both tiers."""

        # Tier 1: Category
        cat_result = self.category_layer(query)

        if cat_result.name is None:
            return RoutingResult(
                category=Category.GENERAL,
                resource=None,
                confidence=0.0,
                metadata={"reason": "no_category_match"},
                fallback=True
            )

        category = Category(cat_result.name)

        # Tier 2: Specific resource
        if category in self.domain_layers:
            domain_result = self.domain_layers[category](query)

            if domain_result.name is not None:
                return RoutingResult(
                    category=category,
                    resource=domain_result.name,
                    confidence=0.8,  # TODO: extract actual score
                    metadata=getattr(domain_result, 'metadata', {}) or {}
                )

        # Category matched but no specific resource
        return RoutingResult(
            category=category,
            resource=None,
            confidence=0.5,
            metadata={"reason": "no_resource_match"},
            fallback=True
        )

    def add_route(self, category: Category, name: str, utterances: List[str], metadata: Dict = None):
        """Dynamically add a route."""
        route = Route(name=name, utterances=utterances, metadata=metadata or {})

        if category not in self.domain_layers:
            self.domain_layers[category] = RouteLayer(
                encoder=self.encoder,
                routes=[route]
            )
        else:
            # Rebuild with new route
            existing = list(self.domain_layers[category].routes)
            existing.append(route)
            self.domain_layers[category] = RouteLayer(
                encoder=self.encoder,
                routes=existing
            )

# Singleton
_router: Optional[Router] = None

def get_router() -> Router:
    global _router
    if _router is None:
        _router = Router()
    return _router

def route(query: str) -> RoutingResult:
    return get_router().route(query)

Step 2: Create Route Definitions

File: routing/routes/categories.yaml

routes:
  - name: command
    utterances:
      - "/research"
      - "/code-review"
      - "/daily-standup"
      - "/summarize"
      - "run the research command"
      - "execute code review"
      - "use slash command"
      - "run command for"

  - name: agent
    utterances:
      - "ask the researcher"
      - "have the coder implement"
      - "let the writer draft"
      - "use the analyst"
      - "delegate to agent"
      - "which agent should"
      - "agent help with"

  - name: skill
    utterances:
      - "use web research skill"
      - "apply document generation"
      - "use the skill for"
      - "leverage skill"

  - name: workflow
    utterances:
      - "run the workflow"
      - "start the pipeline"
      - "execute automation"
      - "trigger workflow"

File: routing/routes/commands.yaml

routes:
  - name: research
    utterances:
      - "research this"
      - "find information about"
      - "look up"
      - "investigate"
      - "deep dive into"
      - "gather info on"
    metadata:
      file: ".claude/commands/research.md"

  - name: code-review
    utterances:
      - "review code"
      - "check for bugs"
      - "analyze code"
      - "security review"
      - "code quality"
    metadata:
      file: ".claude/commands/code-review.md"

  - name: daily-standup
    utterances:
      - "daily standup"
      - "standup report"
      - "what did I work on"
      - "yesterday today blockers"
    metadata:
      file: ".claude/commands/daily-standup.md"

File: routing/routes/agents.yaml

routes:
  - name: researcher
    utterances:
      - "research topic"
      - "find information"
      - "look up facts"
      - "gather data"
      - "fact check"
    metadata:
      path: "agents/sub-agents/researcher"

  - name: coder
    utterances:
      - "write code"
      - "implement function"
      - "debug"
      - "fix bug"
      - "refactor"
    metadata:
      path: "agents/sub-agents/coder"

  - name: writer
    utterances:
      - "write document"
      - "draft email"
      - "compose"
      - "edit text"
    metadata:
      path: "agents/sub-agents/writer"

  - name: analyst
    utterances:
      - "analyze data"
      - "create chart"
      - "visualize"
      - "statistics"
    metadata:
      path: "agents/sub-agents/analyst"

Step 3: Create MCP Server

File: mcp/servers/router-server/server.py

#!/usr/bin/env python3
"""Router MCP Server."""

import asyncio
import json
import sys
from pathlib import Path

# Add project root to path
sys.path.insert(0, str(Path(__file__).parent.parent.parent.parent))

from mcp.server import Server
from mcp.server.stdio import stdio_server
from routing.router import Router, Category

class RouterServer:
    def __init__(self):
        self.server = Server("router-server")
        self.router = Router()
        self._setup_tools()

    def _setup_tools(self):

        @self.server.tool()
        async def route_query(query: str) -> str:
            """Route a query to the appropriate resource."""
            result = self.router.route(query)
            return json.dumps({
                "category": result.category.value,
                "resource": result.resource,
                "confidence": result.confidence,
                "metadata": result.metadata,
                "fallback": result.fallback
            })

        @self.server.tool()
        async def list_routes(category: str = None) -> str:
            """List available routes."""
            routes = {}

            # Category layer
            routes["categories"] = [r.name for r in self.router.category_layer.routes]

            # Domain layers
            for cat, layer in self.router.domain_layers.items():
                if category is None or cat.value == category:
                    routes[cat.value] = [
                        {"name": r.name, "samples": r.utterances[:3]}
                        for r in layer.routes
                    ]

            return json.dumps(routes)

    async def run(self):
        async with stdio_server() as (read_stream, write_stream):
            await self.server.run(read_stream, write_stream)

def main():
    server = RouterServer()
    asyncio.run(server.run())

if __name__ == "__main__":
    main()

Step 4: Create Test Script

File: routing/test_router.py

#!/usr/bin/env python3
"""Test the semantic router."""

import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))

from routing.router import route, Category

def test_routing():
    """Test various queries."""

    test_cases = [
        # (query, expected_category, expected_resource)
        ("research quantum computing", Category.COMMAND, "research"),
        ("/code-review", Category.COMMAND, "code-review"),
        ("ask the researcher to find", Category.AGENT, "researcher"),
        ("write code for sorting", Category.AGENT, "coder"),
        ("run the workflow", Category.WORKFLOW, None),
    ]

    print("Testing router...
")

    for query, expected_cat, expected_res in test_cases:
        result = route(query)
        status = "✅" if result.category == expected_cat else "❌"
        print(f"{status} '{query}'")
        print(f"   → {result.category.value}/{result.resource}")
        print(f"   confidence: {result.confidence}")
        print()

    print("Router test complete!")

if __name__ == "__main__":
    test_routing()

Verification

# Install dependencies
pip install semantic-router sentence-transformers pyyaml

# Run tests
cd routing
python test_router.py

Adding New Routes

  1. Edit the appropriate YAML file in routing/routes/
  2. Add 5-10 example utterances per route
  3. Include metadata for resource location
# Example: Adding a new command
routes:
  - name: my-new-command
    utterances:
      - "run my new command"
      - "execute my-new-command"
      - "new command please"
      # ... more variations
    metadata:
      file: ".claude/commands/my-new-command.md"

After Building

  1. ✅ Run tests to verify
  2. Update CLAUDE.md status
  3. Proceed to slash commands or skills/agent-builder/SKILL.md

Refinement Notes

Add notes here as we discover what works.
  • Initial implementation
  • Tuned confidence thresholds
  • Added more utterance examples
  • Tested with real queries

平台分布

Claude Code

28.82%
按下载量换算33

Codex

24.9%
按下载量换算28

Gemini CLI

18.04%
按下载量换算20

Antigravity

13.37%
按下载量换算15

windsurf

7.61%
按下载量换算9

OpenCode

3.56%
按下载量换算4

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills