agentica-spawn

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agentica Spawn Skill

Use this skill after user selects an Agentica pattern.

使用本技能的前提是用户已选择一种Agentica模式。

When to Use

使用场景

After agentica-orchestrator prompts user for pattern selection
When user explicitly requests a multi-agent pattern (swarm, hierarchical, etc.)
When implementing complex tasks that benefit from parallel agent execution
For research tasks requiring multiple perspectives (use Swarm)
For implementation tasks requiring coordination (use Hierarchical)
For iterative refinement (use Generator/Critic)
For high-stakes validation (use Jury)

在agentica-orchestrator提示用户选择模式之后
当用户明确请求多智能体模式时（如swarm、hierarchical等）
处理可从并行智能体执行中获益的复杂任务时
需要多视角的研究任务（使用Swarm模式）
需要协调配合的实现任务（使用Hierarchical模式）
迭代优化任务（使用Generator/Critic模式）
高风险验证任务（使用Jury模式）

Pattern Selection to Spawn Method

模式选择对应生成方法

Swarm (Research/Explore)

Swarm（研究/探索）

python

swarm = Swarm(
    perspectives=[
        "Security expert analyzing for vulnerabilities",
        "Performance expert optimizing for speed",
        "Architecture expert reviewing design"
    ],
    aggregate_mode=AggregateMode.MERGE,
)
result = await swarm.execute(task_description)

python

swarm = Swarm(
    perspectives=[
        "Security expert analyzing for vulnerabilities",
        "Performance expert optimizing for speed",
        "Architecture expert reviewing design"
    ],
    aggregate_mode=AggregateMode.MERGE,
)
result = await swarm.execute(task_description)

Hierarchical (Build/Implement)

Hierarchical（构建/实现）

python

hierarchical = Hierarchical(
    coordinator_premise="You break tasks into subtasks",
    specialist_premises={
        "planner": "You create implementation plans",
        "implementer": "You write code",
        "reviewer": "You review code for issues"
    },
)
result = await hierarchical.execute(task_description)

python

hierarchical = Hierarchical(
    coordinator_premise="You break tasks into subtasks",
    specialist_premises={
        "planner": "You create implementation plans",
        "implementer": "You write code",
        "reviewer": "You review code for issues"
    },
)
result = await hierarchical.execute(task_description)

Generator/Critic (Iterate/Refine)

Generator/Critic（迭代/优化）

python

gc = GeneratorCritic(
    generator_premise="You generate solutions",
    critic_premise="You critique and suggest improvements",
    max_rounds=3,
)
result = await gc.run(task_description)

python

gc = GeneratorCritic(
    generator_premise="You generate solutions",
    critic_premise="You critique and suggest improvements",
    max_rounds=3,
)
result = await gc.run(task_description)

Jury (Validate/Verify)

Jury（验证/核查）

python

jury = Jury(
    num_jurors=5,
    consensus_mode=ConsensusMode.MAJORITY,
    premise="You evaluate the solution"
)
verdict = await jury.decide(bool, question)

python

jury = Jury(
    num_jurors=5,
    consensus_mode=ConsensusMode.MAJORITY,
    premise="You evaluate the solution"
)
verdict = await jury.decide(bool, question)

Environment Variables

环境变量

All spawned agents receive:

```
SWARM_ID
```
: Unique identifier for this swarm run
```
AGENT_ROLE
```
: Role within the pattern (coordinator, specialist, etc.)
```
PATTERN_TYPE
```
: Which pattern is running

所有生成的智能体都会接收以下环境变量：

```
SWARM_ID
```
: 本次swarm运行的唯一标识符
```
AGENT_ROLE
```
: 智能体在模式中的角色（如协调者、专家等）
```
PATTERN_TYPE
```
: 当前运行的模式类型