Agentica Spawn

by parcadeid07ff4b06b62No license3.9K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 8 months ago

Spawn Agentica multi-agent patterns

Instructions onlyAI & Agents

AI-generated overview

Spawns Agentica multi-agent patterns such as Swarm, Hierarchical, Generator/Critic and Jury for a task.

What it does: This skill maps a selected Agentica multi-agent pattern to the corresponding spawn method and shows how to invoke it. It covers Swarm for research and exploration, Hierarchical for build and implementation work, Generator/Critic for iterative refinement, and Jury for validation. It also lists the environment variables passed to spawned agents, such as SWARM_ID, AGENT_ROLE and PATTERN_TYPE.
When to use it: Use it after an Agentica orchestrator prompts for pattern selection, or when the user explicitly requests a multi-agent pattern. It suits complex tasks that benefit from parallel agents, multi-perspective research, coordinated implementation, iterative refinement or high-stakes validation.
Requirements: No scripts are shipped; it is instructions only. It assumes an Agentica multi-agent runtime with the named pattern classes and an environment that supplies SWARM_ID, AGENT_ROLE and PATTERN_TYPE to spawned agents.

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)

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)

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)

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)

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)

python

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

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)

python

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

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

Source and attribution

Source:parcadei/continuous-claude-v3in.claude/skills/agentica-spawnat commitd07ff4b

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Agentica Spawn

Agentica Spawn Skill

When to Use

Pattern Selection to Spawn Method

Swarm (Research/Explore)

Hierarchical (Build/Implement)

Generator/Critic (Iterate/Refine)

Jury (Validate/Verify)

Environment Variables

Source and attribution

More from parcadei/continuous-claude-v3

Tldr Stats

Wiring

Workflow Router

Validate Agent

Tour

Tldr Overview

More in AI & Agents

Ppt Template Creator

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Find Skills