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)
• Tasks already in progress
• User explicitly says "don't use subagent" or "just answer directly"

Manual Trigger (For Users)

Users can explicitly trigger this skill by:

• - Running router.sh "task description" directly
• Saying "use hive router" or "analyze this task"
• Asking "which model should I use for this task"

Decision Flow for AI Agents

CODEBLOCK0

Vague Task Handling

When user message is vague (e.g., "做个任务", "帮忙处理一下", "搞定这件事"):

Step 1: Acknowledge and ask
CODEBLOCK1

Step 2: User clarifies
CODEBLOCK2

Vague Keywords (trigger clarification):

• - 任务、帮忙、处理、搞定、完成、做一下、弄一下
• 这个、那个、一件事、一个东西

Specific Keywords (trigger automatic routing):

• - code: 脚本、代码、编程、函数、nodejs、react...
• web: 搜索、调研、分析、趋势、报告、对比...
• data: 数据、统计、图表、excel、csv、json...
• doc: 文档、教程、指南、readme、wiki...

Ideal scenarios:

• - Handling multiple concurrent tasks
• Technical development requiring code-specialized models
• Research tasks needing web search capabilities
• Mixed workloads with varying complexity
• Multi-provider environments (Bailian + OpenAI + Anthropic)

---

Quick Reference

Task Type Recognition Keywords

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) |

Model Selection Rules

Note: Model IDs are configurable via environment variables. Replace provider/ with your actual model provider (e.g., bailian/, openai/, anthropic/).

Task Type	Default Model	Environment Variable	Reason
code	INLINECODE14	INLINECODE15	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 |

Model Configuration Examples

Bailian (通义千问):
CODEBLOCK3

Model Validation Modes

Automatic Model Detection (Recommended):

CODEBLOCK4

First run: Detects models and caches configuration
Subsequent runs: Uses cached config (24h TTL)
Benefit: No manual configuration needed!

Manual Validation Modes:

Mode	Environment Variable	Behavior	Use Case
Auto (Recommended)	INLINECODE24	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 Configuration:
CODEBLOCK5

Validation Behavior:

• - ✅ Checks if model IDs contain provider/ placeholder
• ✅ Warns if placeholder detected
• ✅ Caches validation result (configurable TTL)
• ✅ Non-blocking (warnings only, doesn't stop execution)

OpenAI:
CODEBLOCK6

Anthropic (Claude):
CODEBLOCK7

Mixed Providers:
CODEBLOCK8

Execution Mode Rules

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 |

Priority Rule: When multiple keywords match, use the highest priority type (web > code > data > doc > chat).

---

Usage

For AI Agents (Automatic Integration)

When installed as an OpenClaw Skill, the agent will automatically use this skill when:

1. 1. User message contains task keywords (code/web/data/doc/batch)
2. Task is long-running (not a simple Q&A)
3. Multiple tasks need parallel execution

Agent Decision Example:
CODEBLOCK9

Configuration for Agents:
Add to agent's AGENTS.md or SOUL.md:

## 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

---

Method 1: Router Script (Recommended)

The router script automatically analyzes tasks and outputs recommended execution commands.

CODEBLOCK11

Output format:
CODEBLOCK12

Method 2: Manual Commands

Code Tasks

CODEBLOCK13

Web Research Tasks

CODEBLOCK14

Chat Tasks (Main Session)

CODEBLOCK15

Data Processing Tasks

CODEBLOCK16

Documentation Tasks

CODEBLOCK17

Method 3: Parallel Execution

For batch tasks, use parallel subagents:

CODEBLOCK18

---

Examples

Example 1: Code Development Task

User Input:
CODEBLOCK19

Router Analysis:

• - Matched Keywords: Node.js, 脚本，文件处理
• Task Type: code
• Recommended Model: bailian/qwen3-coder-plus
• Execution Mode: subagent

Execution Command:

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"

---

Example 2: Web Research Task

User Input:
CODEBLOCK21

Router Analysis:

• - Matched Keywords: 搜索，2026, 趋势，对比
• Task Type: web (Priority 1)
• Recommended Model: bailian/qwen3-max-2026-01-23
• Execution Mode: subagent

Execution Command:

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"

---

Example 3: Daily Chat Task

User Input:
CODEBLOCK23

Router Analysis:

• - Matched Keywords: 今天，安排，总结
• Task Type: chat
• Recommended Model: bailian/qwen3.5-plus
• Execution Mode: main_session

Execution Command:

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"

---

Example 4: Data Analysis Task

User Input:
CODEBLOCK25

Router Analysis:

• - Matched Keywords: 分析，数据，Excel, 图表，统计
• Task Type: data
• Recommended Model: bailian/qwen3-coder-plus
• Execution Mode: subagent

Execution Command:

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"

---

Example 5: Documentation Task

User Input:
CODEBLOCK27

Router Analysis:

• - Matched Keywords: 文档，教程
• Task Type: doc
• Recommended Model: bailian/qwen3.5-plus
• Execution Mode: subagent

Execution Command:

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"

---

Example 6: Mixed Task Batch (Parallel)

User Input (Multiple Tasks):
CODEBLOCK29

Router Analysis:

• - Task 1: code → qwen3-coder-plus + subagent
• Task 2: web → qwen3-max-2026-01-23 + subagent
• Task 3: chat → qwen3.5-plus + main_session

Parallel Execution:
CODEBLOCK30

Performance: 3x faster than sequential execution

---

Installation

Install via ClawHub

CODEBLOCK31

Manual Installation

1. 1. Clone or download this skill folder
2. Copy to your OpenClaw skills directory:

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

1. 3. Make router script executable:

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

1. 4. 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"
   

---

Configuration

Prerequisites

• - OpenClaw CLI installed
• Bash shell available
• Models configured (adjust for your provider):

- Code model (e.g., bailian/qwen3-coder-plus) - Web model (e.g., bailian/qwen3-max-2026-01-23) - Chat model (e.g., bailian/qwen3.5-plus)

Environment Variables

Optional environment variables for customization:

CODEBLOCK35

Verify Setup

CODEBLOCK36

---

Troubleshooting

Issue 1: Router script not found

CODEBLOCK37

Issue 2: Model not available

CODEBLOCK38

Issue 3: Task type misidentified

CODEBLOCK39

Issue 4: Wrong model used

CODEBLOCK40

---

Best Practices

1. 1. Task Distribution Principles

- ✅ Short tasks → Main session - ✅ Long tasks → Subagent - ✅ Batch tasks → Multiple parallel subagents - ✅ Fixed types → Session isolation + specialized models

1. 2. Model Selection

- Use code-specialized models for programming tasks - Use reasoning models for research tasks - Use cost-effective models for chat tasks - Mix providers for best-in-class results

1. 3. Concurrency Control

- Recommended max concurrent subagents: 5-10 - For 10+ tasks → Execute in batches - Monitor API quota usage

1. 4. Environment Management

- Set environment variables in .bashrc or .zshrc - Use different configs for different projects - Document your model choices

---

Performance

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 Compatibility

Provider	Status	Notes
Bailian (通义千问)	✅ Tested	Default configuration
OpenAI (GPT)

✅ Compatible | Set HIVEMODEL* variables | | Anthropic (Claude) | ✅ Compatible | Set HIVEMODEL* variables | | Google (Gemini) | ✅ Compatible | Set HIVEMODEL* variables | | Other OpenAI-compatible | ✅ Compatible | Use provider/ prefix |

---

License

MIT License - Feel free to use and modify.

---

Author: qiongcao
Version: 1.0.0
Last Updated: 2026-03-12
Universal Model Support: Yes