agentica-spawn

Spawn Agentica multi-agent patterns

⭐2.2kstars🔀157forks📁View on GitHub🕐Updated Jan 10, 2026⬇️1downloads

When & Why to Use This Skill

The Agentica Spawn skill enables the seamless deployment of advanced multi-agent architectures to solve complex, multi-step problems. It automates AI orchestration by implementing proven patterns such as Swarm, Hierarchical coordination, and Generator/Critic loops, allowing users to scale AI capabilities from simple tasks to sophisticated, autonomous workflows with high reliability and specialized expertise.

Use Cases

  • Comprehensive Research: Using the Swarm pattern to gather diverse perspectives from multiple specialized agents (e.g., security, performance, and architecture experts) for deep-dive analysis.
  • Complex Software Implementation: Utilizing the Hierarchical pattern to break down large-scale coding tasks into subtasks managed by a coordinator and executed by specialized planning and implementation agents.
  • Iterative Quality Improvement: Implementing a Generator/Critic loop to automatically refine code, content, or designs through multiple rounds of feedback and revision.
  • High-Stakes Decision Validation: Deploying a Jury pattern to achieve consensus and verify the accuracy of solutions through independent evaluation and majority voting.
nameagentica-spawn
descriptionSpawn Agentica multi-agent patterns
user-invocablefalse

Agentica Spawn Skill

Use this skill after user selects an Agentica pattern.

When to Use

  • 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)

Pattern Selection to Spawn Method

Swarm (Research/Explore)

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 = 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)

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

Environment Variables

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