Skip to content

LeoYeAI/agent-master-skills / skills/agent-avengers

agent-avengers

Verified

올인원 멀티에이전트 오케스트레이션. 복잡한 태스크를 자동으로 분해하고, 전문 에이전트들을 즉석에서 생성/스폰하여 병렬 처리 후 결과를 통합합니다. TRIGGERS: avengers assemble, 어벤저스, agent-avengers, 멀티에이전트 자동화, 에이전트 팀 구성, 자동 에이전트

FileKindSize
ANNOUNCEMENT.mdmarkdown1.7 KB
README-kr.mdmarkdown1.0 KB
README.mdmarkdown2.7 KB
SKILL.mdskill md22.9 KB
_meta.jsonconfig283 B
examples/app-development.jsonconfig1.3 KB
examples/competitor-analysis.jsonconfig1.1 KB
package.jsonmanifest653 B
pytest.iniconfig125 B
scripts/assemble.pyscript10.0 KB
scripts/consolidate.pyscript6.4 KB
scripts/execute.pyscript6.5 KB
scripts/monitor.pyscript6.3 KB
tests/__init__.pyscript23 B
tests/test_assemble.pyscript7.8 KB
tests/test_consolidate.pyscript6.4 KB
# Agent Avengers

🦸 **All-in-One Multi-Agent Orchestration**

> [한국어 README](./README-kr.md)

## Installation

```bash
clawhub install agent-avengers
```

Or clone directly:
```bash
git clone https://github.com/oozoofrog/agent-avengers.git ~/.openclaw/workspace/skills/agent-avengers
```

## Usage

```
Avengers assemble! [complex task description]
```

## Examples

```
Avengers assemble! Analyze competitors A, B, and C, then create a comparison report
```

```
Avengers assemble! Build a full-stack todo app with React frontend and Node.js backend
```

## How It Works

1. **Decompose** — Break down the task into subtasks
2. **Compose** — Assign specialized agents to each subtask
3. **Execute** — Run in parallel or sequential order
4. **Consolidate** — Collect and merge results
5. **Report** — Deliver final output

## Agent Types

| Type | Role |
|------|------|
| 🔬 Researcher | Investigation, data collection |
| 🔍 Analyst | Analysis, pattern discovery |
| 🖊️ Writer | Documentation, content creation |
| 💻 Coder | Code implementation |
| ✅ Reviewer | Quality review |
| 🔧 Integrator | Result consolidation |

## Agent Modes

| Mode | Description |
|------|-------------|
| 🔷 Existing | Use registered agents (watson, picasso, etc.) |
| 🔶 Spawned | Create one-off sub-agents on demand |
| 🟣 Multi-Profile | Involve other OpenClaw bot instances |
| 🔷🔶🟣 Hybrid | Combine all modes (recommended) |

## Emergent Collaboration Patterns

- 🗳️ **Competitive Draft** — Multiple agents work independently, best solution wins
- 🎭 **Role Rotation** — Agents swap roles each round
- ⚔️ **Adversarial Collaboration** — Creator vs Critic iterations
- 🧬 **Evolutionary Selection** — Solutions crossbreed and evolve
- 🐝 **Swarm Intelligence** — Many micro-agents tackle small chunks
- 🔗 **Chain Relay** — Output → Input chaining
- 💭 **Consensus Protocol** — Unanimous agreement required
- 🎪 **Cross-Domain Jam** — Combine different expertise areas
- 🪞 **Meta Observer** — Agent watches and coaches the team
- ⏰ **Temporal Split** — Short/mid/long-term parallel approaches
- 🎰 **Task Auction** — Confidence-based bidding
- 🧠 **Shared Memory** — Real-time discovery sharing

## Configuration

`avengers.yaml`:
```yaml
maxAgents: 5
timeoutMinutes: 120
retryCount: 2
defaultModel: sonnet
```

## Scripts

| Script | Description |
|--------|-------------|
| `scripts/assemble.py` | Task decomposition & plan generation |
| `scripts/execute.py` | Generate execution commands |
| `scripts/monitor.py` | Progress monitoring (supports --watch) |
| `scripts/consolidate.py` | Result consolidation |

## License

MIT
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall