aatmaan1

Agent Orchestrator

AI 智慧體v0.1.0
作者:aatmaan1更新於 2026-05-17agent-orchestrator@clawhub_aatmaan1/agent-orchestrator
任務自動化多 Agent 協作工作流編排#Multi Agent#Orchestrate

據 AlphaMoat 統計,截至 2026-10,Agent Orchestrator 累計下載 25,339 次、獲 39 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 1,126 位,在「AI 智慧體」分類(1,632 個)中排名第 169 位。

列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。

累計下載
2.5萬
星標
39
全站下載量排名
#1,126
全站前 11% · 「AI 智慧體」前 11%
平台累計下載星標評論
ClawHub ↗1.5萬322
SkillHub ↗2.5萬39—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

文件流程包括梳理依賴、建立智慧體工作區與專屬技能檔案、用檔案交換指令和結果、按檢查點監控、驗證交付物及歸檔工作區。適合有明確成功標準且能獨立完成的子任務,執行環境需支援智慧體派發及配套指令碼。 這是流程指引,不代表命令或測試已經執行;應依目標專案調整範例並核驗結果。

資料釋出於 2026-10-27

可以用來做什麼

  • 協調可獨立完成的研究、分析或實現任務

什麼時候用

  • 複雜工作能拆成可分別驗證的交付物時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

先把專案拆成獨立子任務,列明依賴、交付物和驗收標準,再派發智慧體。

月度資料趨勢

累計下載2.5萬
1.3萬1.9萬2.6萬2026-05 · 累計下載 1.4萬2026-06 · 累計下載 1.4萬2026-07 · 累計下載 1.4萬2026-08 · 累計下載 1.5萬2026-09 · 累計下載 1.7萬2026-10 · 累計下載 2.5萬26-0526-0926-10
星標39
3437392026-05 · 星標 342026-06 · 星標 362026-07 · 星標 382026-08 · 星標 392026-09 · 星標 392026-10 · 星標 3926-0526-0926-10

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。 該技能有同名的其他版本,調整前的資料歸屬當前下載量最大的這一個。

月份累計下載環比星標
2026-102.5萬—39
2026-091.7萬—39
2026-081.5萬+2.1%39
2026-071.4萬+2.3%38
2026-061.4萬+3.4%36
2026-051.4萬—34

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

5.7 KB · ClawHub v0.1.0
---
name: agent-orchestrator
description: |
  Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion.

  MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
---

# Agent Orchestrator
展開全部(共 176 行)
Orchestrate complex tasks by decomposing them into subtasks, spawning autonomous sub-agents, and consolidating their work.

## Core Workflow

### Phase 1: Task Decomposition

Analyze the macro task and break it into independent, parallelizable subtasks:

```
1. Identify the end goal and success criteria
2. List all major components/deliverables required
3. Determine dependencies between components
4. Group independent work into parallel subtasks
5. Create a dependency graph for sequential work
```

**Decomposition Principles:**
- Each subtask should be completable in isolation
- Minimize inter-agent dependencies
- Prefer broader, autonomous tasks over narrow, interdependent ones
- Include clear success criteria for each subtask

### Phase 2: Agent Generation

For each subtask, create a sub-agent workspace:

```bash
python3 scripts/create_agent.py <agent-name> --workspace <path>
```

This creates:
```
<workspace>/<agent-name>/
├── SKILL.md          # Generated skill file for the agent
├── inbox/            # Receives input files and instructions
├── outbox/           # Delivers completed work
├── workspace/        # Agent's working area
└── status.json       # Agent state tracking
```

**Generate SKILL.md dynamically** with:
- Agent's specific role and objective
- Tools and capabilities needed
- Input/output specifications
- Success criteria
- Communication protocol

See [references/sub-agent-templates.md](references/sub-agent-templates.md) for pre-built templates.

### Phase 3: Agent Dispatch

Initialize each agent by:

1. Writing task instructions to `inbox/instructions.md`
2. Copying required input files to `inbox/`
3. Setting `status.json` to `{"state": "pending", "started": null}`
4. Spawning the agent using the Task tool:

```python
# Spawn agent with its generated skill
Task(
    description=f"{agent_name}: {brief_description}",
    prompt=f"""
    Read the skill at {agent_path}/SKILL.md and follow its instructions.
    Your workspace is {agent_path}/workspace/
    Read your task from {agent_path}/inbox/instructions.md
    Write all outputs to {agent_path}/outbox/
    Update {agent_path}/status.json when complete.
    """,
    subagent_type="general-purpose"
)
```

### Phase 4: Monitoring (Checkpoint-based)

For fully autonomous agents, minimal monitoring is needed:

```python
# Check agent completion
def check_agent_status(agent_path):
    status = read_json(f"{agent_path}/status.json")
    return status.get("state") == "completed"
```

Periodically check `status.json` for each agent. Agents update this file upon completion.

### Phase 5: Consolidation

Once all agents complete:

1. **Collect outputs** from each agent's `outbox/`
2. **Validate deliverables** against success criteria
3. **Merge/integrate** outputs as needed
4. **Resolve conflicts** if multiple agents touched shared concerns
5. **Generate summary** of all work completed

```python
# Consolidation pattern
for agent in agents:
    outputs = glob(f"{agent.path}/outbox/*")
    validate_outputs(outputs, agent.success_criteria)
    consolidated_results.extend(outputs)
```

### Phase 6: Dissolution & Summary

After consolidation:

1. **Archive agent workspaces** (optional)
2. **Clean up temporary files**
3. **Generate final summary**:
   - What was accomplished per agent
   - Any issues encountered
   - Final deliverables location
   - Time/resource metrics

```python
python3 scripts/dissolve_agents.py --workspace <path> --archive
```

## File-Based Communication Protocol

See [references/communication-protocol.md](references/communication-protocol.md) for detailed specs.

**Quick Reference:**
- `inbox/` - Read-only for agent, written by orchestrator
- `outbox/` - Write-only for agent, read by orchestrator
- `status.json` - Agent updates state: `pending` → `running` → `completed` | `failed`

## Example: Research Report Task

```
Macro Task: "Create a comprehensive market analysis report"

Decomposition:
├── Agent: data-collector
│   └── Gather market data, competitor info, trends
├── Agent: analyst
│   └── Analyze collected data, identify patterns
├── Agent: writer
│   └── Draft report sections from analysis
└── Agent: reviewer
    └── Review, edit, and finalize report

Dependency: data-collector → analyst → writer → reviewer
```

## Sub-Agent Templates

Pre-built templates for common agent types in [references/sub-agent-templates.md](references/sub-agent-templates.md):

- **Research Agent** - Web search, data gathering
- **Code Agent** - Implementation, testing
- **Analysis Agent** - Data processing, pattern finding
- **Writer Agent** - Content creation, documentation
- **Review Agent** - Quality assurance, editing
- **Integration Agent** - Merging outputs, conflict resolution

## Best Practices

1. **Start small** - Begin with 2-3 agents, scale as patterns emerge
2. **Clear boundaries** - Each agent owns specific deliverables
3. **Explicit handoffs** - Use structured files for agent communication
4. **Fail gracefully** - Agents report failures; orchestrator handles recovery
5. **Log everything** - Status files track progress for debugging

「AI 智慧體」分類下的熱門技能

aatmaan1 的其他技能

資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。