Hive Task Router

LeoYeAI/openclaw-master-skillsCoding AgentsAudit failedSnapshot fd9379412665

Installs: 0

Summary

Intelligent task routing system that identifies task types (web/code/data/doc/chat) and routes to optimal models with appropriate execution mode (subagent/main session). Supports any AI model provider via environment variables.

SKILL.md

Hive Task Router

Smart task distribution system for OpenClaw — Automatically routes tasks to optimal models and execution modes based on task type recognition.

Universal Model Support — Works with any AI model provider (Bailian, OpenAI, Anthropic, etc.) via environment variable configuration.

When to Use

Automatic Trigger Rules (For AI Agents)

Use this skill automatically when the user's message contains ANY of these patterns:

Trigger Pattern	Keywords	Action
Code tasks	代码、编程、脚本、函数、nodejs、react、vue、typescript、javascript、html、css、前端、后端、api、接口、调试、bug、优化、重构	Run `router.sh` → Execute with `code` model + subagent
Web research	搜索、查找、调研、研究、github、项目、趋势、报告、分析、对比、评测、最新、2026、新闻、动态	Run `router.sh` → Execute with `web` model + subagent
Data tasks	数据、分析、统计、图表、可视化、excel、csv、json、处理、转换	Run `router.sh` → Execute with `data` model + subagent
Documentation	文档、说明、教程、指南、手册、readme、wiki、注释、文档化	Run `router.sh` → Execute with `doc` model + subagent
Batch tasks	多个、批量、同时、并行、一起	Run `router.sh` for each → Execute in parallel

Do NOT use this skill when:

Simple chat/conversation (你好、谢谢、安排、计划、汇报、总结)
Quick questions (what is, how to, explain)

Receive user message
    ↓
Contains specific trigger keywords? (code/web/data/doc/batch)
    ↓
YES → Run router.sh to analyze
    ↓
Get recommended model + execution mode
    ↓
Execute with recommended configuration
    ↓
Report result to user
    ↓
NO → Check for vague task keywords? (任务、帮忙、处理、搞定、完成)
    ↓
YES → Ask clarifying question (see "Vague Task Handling")
    ↓
User clarifies → Re-analyze with new info
    ↓
NO → Handle directly (no routing needed)

好的主人，请问是什么类型的任务？

💻 写代码/脚本？
   - 例如："写个 Python 脚本"、"开发一个 API"

🔍 搜索调研？
   - 例如："搜索最新趋势"、"调研竞品"

📊 数据处理？
   - 例如："分析 Excel 数据"、"转换 JSON 格式"

📄 写文档？
   - 例如："写 API 文档"、"编写教程"

💬 还是只是聊天？
   - 例如："今天有什么安排"、"帮我总结一下"

或者您直接告诉我具体内容，我来判断！

User: "写个脚本处理数据"
  ↓
Now contains: "脚本" (code) + "数据" (data)
  ↓
Priority: code > data
  ↓
Execute with: qwen3-coder-plus + subagent

Type	Keywords (Chinese)	Keywords (English)	Priority
web 🔍	搜索、查找、调研、研究、github、项目、趋势、报告、分析、对比、评测、最新、2026、新闻、动态	search, research, github, project, trend, report, analysis, comparison, latest, news	1 (Highest)
code 💻	代码、编程、脚本、函数、nodejs、react、vue、typescript、javascript、html、css、前端、后端、api、接口、调试、bug、优化、重构	code, programming, script, function, nodejs, react, vue, typescript, javascript, html, css, frontend, backend, api, debug, bug, optimize, refactor	2
data 📊	数据、分析、统计、图表、可视化、excel、csv、json、处理、转换	data, analysis, statistics, chart, visualization, excel, csv, json, processing, conversion	3
doc 📄	文档、说明、教程、指南、手册、readme、wiki、注释、文档化	documentation, guide, tutorial, manual, readme, wiki, comment, document	4
chat 💬	你好、谢谢、再见、今天、明天、安排、计划、汇报、总结、提醒、备忘	hello, thanks, goodbye, today, tomorrow, plan, schedule, summary, reminder, memo	5 (Default)

Task Type	Default Model	Environment Variable	Reason
code	`provider/qwen3-coder-plus`	`HIVE_MODEL_CODE`	Specialized in code generation and debugging
web	`provider/qwen3-max`	`HIVE_MODEL_WEB`	Strong search and reasoning capabilities
data	`provider/qwen3-coder-plus`	`HIVE_MODEL_DATA`	Code-based data processing
doc	`provider/qwen3.5-plus`	`HIVE_MODEL_DOC`	Good text generation, cost-effective
chat	`provider/qwen3.5-plus`	`HIVE_MODEL_CHAT`	Best for casual conversation, cost-effective

export HIVE_MODEL_CODE="bailian/qwen3-coder-plus"
export HIVE_MODEL_WEB="bailian/qwen3-max-2026-01-23"
export HIVE_MODEL_CHAT="bailian/qwen3.5-plus"
export HIVE_MODEL_DOC="bailian/qwen3.5-plus"
export HIVE_MODEL_DATA="bailian/qwen3-coder-plus"

# Auto-detect available models from OpenClaw
export HIVE_VALIDATE_MODEL=auto

Mode	Environment Variable	Behavior	Use Case
Auto (Recommended)	`export HIVE_VALIDATE_MODEL=auto`	Auto-detect + cache 24h	Best for most users
Cache	`export HIVE_VALIDATE_MODEL=cache`	Validate once, cache 24h	Manual config, stable
Always	`export HIVE_VALIDATE_MODEL=1`	Validate every execution	Debugging, changes
Never	`export HIVE_VALIDATE_MODEL=0`	Skip validation	Production, known config

# Cache directory (default: ~/.hive-task-router)
export HIVE_CACHE_DIR="$HOME/.hive-task-router"

# Cache TTL in seconds (default: 86400 = 24 hours)
export HIVE_CACHE_TTL=86400

export HIVE_MODEL_CODE="openai/gpt-4"
export HIVE_MODEL_WEB="openai/gpt-4-turbo"
export HIVE_MODEL_CHAT="openai/gpt-3.5-turbo"
export HIVE_MODEL_DOC="openai/gpt-3.5-turbo"
export HIVE_MODEL_DATA="openai/gpt-4"

export HIVE_MODEL_CODE="anthropic/claude-3-5-sonnet"
export HIVE_MODEL_WEB="anthropic/claude-3-opus"
export HIVE_MODEL_CHAT="anthropic/claude-3-haiku"
export HIVE_MODEL_DOC="anthropic/claude-3-haiku"
export HIVE_MODEL_DATA="anthropic/claude-3-5-sonnet"

# Use best model for each task type
export HIVE_MODEL_CODE="anthropic/claude-3-5-sonnet"  # Best for code
export HIVE_MODEL_WEB="openai/gpt-4-turbo"           # Best for search
export HIVE_MODEL_CHAT="bailian/qwen3.5-plus"        # Cost-effective

Task Type	Execution Mode	Reason
chat	Main Session	Quick response, no need for isolation
code/web/data/doc	Subagent	Long-running tasks, parallel execution, session isolation

User: "帮我写一个 Python 脚本处理 Excel 数据"
  ↓
Agent checks: Contains "脚本" (code) + "数据" (data)
  ↓
Priority: code > data
  ↓
Agent executes:
openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-coder-plus \
  --task "帮我写一个 Python 脚本处理 Excel 数据"

## Hive Task Router Integration

When receiving tasks:
1. Check if message contains task keywords (see SKILL.md)
2. If yes → Use hive-task-router skill
3. If no → Handle directly

# Basic usage
bash router.sh "帮我写一个 Node.js 脚本"

# Analyze research task
bash router.sh "搜索 2026 年最新的前端趋势"

# Analyze data task
bash router.sh "分析这个 JSON 数据并生成图表"

================================
蜂巢智能任务分发系统 - 路由分析
================================

任务描述：帮我写一个 Node.js 脚本
任务类型：code
推荐模型：bailian/qwen3-coder-plus
执行方式：subagent

📦 代码任务 - 使用 qwen3-coder-plus 模型
   适合：Node.js、前端代码、脚本编写

================================
推荐执行命令:
================================

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-coder-plus \
  --task "帮我写一个 Node.js 脚本"

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-coder-plus \
  --task "帮我写一个 Express API 服务"

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-max-2026-01-23 \
  --task "调研 5 个 React UI 库"

openclaw agent \
  --session-id agent:main:chat \
  --model bailian/qwen3.5-plus \
  --message "今天有什么安排"

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-coder-plus \
  --task "处理这个 CSV 文件并生成统计报告"

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3.5-plus \
  --task "为这个项目编写 README 文档"

# Spawn multiple subagents concurrently
openclaw sessions spawn --mode run --runtime subagent --model bailian/qwen3-max-2026-01-23 --task "调研项目 A" &
openclaw sessions spawn --mode run --runtime subagent --model bailian/qwen3-max-2026-01-23 --task "调研项目 B" &
openclaw sessions spawn --mode run --runtime subagent --model bailian/qwen3-max-2026-01-23 --task "调研项目 C" &

# Wait for all to complete
wait

# Then collect and summarize results

帮我写一个 Node.js 文件处理脚本，支持读取 CSV 和 JSON 格式

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-coder-plus \
  --task "帮我写一个 Node.js 文件处理脚本，支持读取 CSV 和 JSON 格式"

搜索 2026 年最新的前端趋势，包括 React、Vue、Svelte 的对比

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-max-2026-01-23 \
  --task "搜索 2026 年最新的前端趋势，包括 React、Vue、Svelte 的对比"

今天有什么安排？帮我总结一下昨天的工作

openclaw agent \
  --session-id agent:main:chat \
  --model bailian/qwen3.5-plus \
  --message "今天有什么安排？帮我总结一下昨天的工作"

分析这个销售数据 Excel 文件，生成可视化图表和统计报告

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3-coder-plus \
  --task "分析这个销售数据 Excel 文件，生成可视化图表和统计报告"

为这个 Python 项目编写完整的 API 文档和使用教程

openclaw sessions spawn \
  --mode run \
  --runtime subagent \
  --model bailian/qwen3.5-plus \
  --task "为这个 Python 项目编写完整的 API 文档和使用教程"

1. 写个脚本处理 JSON 数据
2. 搜索最新 AI 工具
3. 今天有什么安排

# Task 1 & 2 run in parallel subagents
openclaw sessions spawn --mode run --runtime subagent --model bailian/qwen3-coder-plus --task "写个脚本处理 JSON 数据" &
openclaw sessions spawn --mode run --runtime subagent --model bailian/qwen3-max-2026-01-23 --task "搜索最新 AI 工具" &

# Task 3 runs in main session (non-blocking)
openclaw agent --session-id agent:main:chat --model bailian/qwen3.5-plus --message "今天有什么安排"

# Wait for subagents
wait

clawhub install qiongcao/hive-task-router

Clone or download this skill folder

Copy to your OpenClaw skills directory:

cp -r hive-task-router ~/.openclaw/workspace/skills/

Make router script executable:

chmod +x ~/.openclaw/workspace/skills/hive-task-router/router.sh

Configure models for your provider:

export HIVE_MODEL_CODE="bailian/qwen3-coder-plus"
export HIVE_MODEL_WEB="bailian/qwen3-max-2026-01-23"
export HIVE_MODEL_CHAT="bailian/qwen3.5-plus"

# Model overrides (required)
export HIVE_MODEL_CODE="bailian/qwen3-coder-plus"
export HIVE_MODEL_WEB="bailian/qwen3-max-2026-01-23"
export HIVE_MODEL_CHAT="bailian/qwen3.5-plus"
export HIVE_MODEL_DOC="bailian/qwen3.5-plus"
export HIVE_MODEL_DATA="bailian/qwen3-coder-plus"

# Optional: custom session IDs
export HIVE_SESSION_CODE="custom:code:session"
export HIVE_SESSION_WEB="custom:web:session"
export HIVE_SESSION_CHAT="custom:chat:session"

# Optional: concurrency limit
export HIVE_MAX_CONCURRENT=10

# Check models
openclaw models list | grep bailian

# Test router script
bash router.sh "测试任务"

# Verify environment variables
echo $HIVE_MODEL_CODE
echo $HIVE_MODEL_WEB

# Make sure script is executable
chmod +x router.sh

# Run with full path
bash /path/to/router.sh "task"

# Check available models
openclaw models list

# Update environment variables with available models
export HIVE_MODEL_CODE="bailian/qwen3-coder-plus"

# Add more specific keywords to router.sh
# Edit CODE_KEYWORDS, WEB_KEYWORDS, etc.

# Verify environment variables are set
echo $HIVE_MODEL_CODE
echo $HIVE_MODEL_WEB

# Set them explicitly before running router.sh
export HIVE_MODEL_CODE="bailian/qwen3-coder-plus"
bash router.sh "task"

Metric	Traditional	Hive Router	Improvement
3 project research	~180s	~60s	3x ⚡
Model utilization	Single model	Multi-model	Flexible
Task routing	Manual	Automatic	Intelligent
Multi-provider	Manual switching	Auto config	Seamless

Provider	Status	Notes
Bailian (通义千问)	✅ Tested	Default configuration
OpenAI (GPT)	✅ Compatible	Set HIVE_MODEL_* variables
Anthropic (Claude)	✅ Compatible	Set HIVE_MODEL_* variables
Google (Gemini)	✅ Compatible	Set HIVE_MODEL_* variables
Other OpenAI-compatible	✅ Compatible	Use provider/ prefix

Hive Task Router

Summary

Hive Task Router

When to Use

Automatic Trigger Rules (For AI Agents)

Manual Trigger (For Users)

Decision Flow for AI Agents

Vague Task Handling

Quick Reference

Task Type Recognition Keywords

Model Selection Rules

Model Configuration Examples

Model Validation Modes

Execution Mode Rules

Usage

For AI Agents (Automatic Integration)

Method 1: Router Script (Recommended)

Method 2: Manual Commands

Code Tasks

Web Research Tasks

Chat Tasks (Main Session)

Data Processing Tasks

Documentation Tasks

Method 3: Parallel Execution

Examples

Example 1: Code Development Task

Example 2: Web Research Task

Example 3: Daily Chat Task

Example 4: Data Analysis Task

Example 5: Documentation Task

Example 6: Mixed Task Batch (Parallel)

Installation

Install via ClawHub

Manual Installation

Configuration

Prerequisites

Environment Variables

Verify Setup

Troubleshooting

Issue 1: Router script not found

Issue 2: Model not available

Issue 3: Task type misidentified

Issue 4: Wrong model used

Best Practices

Performance

Provider Compatibility

License

Related skills