Coordinate distributed agent swarms across mesh, hierarchical, star, and ring topologies.
npx skills add https://github.com/bjpl/hablas --skill swarm-advanced-bjpl
Please help me install this Agent Skill. Skill: swarm-advanced Source: https://github.com/bjpl/hablas/tree/main/.claude/skills/swarm-advanced Command: npx skills add https://github.com/bjpl/hablas --skill swarm-advanced-bjpl
What problem does it solves? Orchestrating complex distributed workflows across multiple AI agents for tasks like research, development, or testing can be challenging without advanced patterns. This skill provides comprehensive strategies for advanced swarm orchestration, enabling efficient coordination, parallel execution, and fault tolerance for complex distributed tasks.
mesh topology swarm with specialized researchers and analysts. This allows for parallel information gathering, cross-referencing, and collaborative synthesis, significantly accelerating the research process while ensuring data quality and fault tolerance.Initialize a mesh topology swarm with 6 agents and then spawn a specialized "researcher" agent. mcp__claude-flow__swarm_init({ topology: "mesh", maxAgents: 6 }) mcp__claude-flow__agent_spawn({ type: "researcher", name: "Agent 1" })
High-intent search queries and answers about installing and using this skill.
Orchestrating distributed agent swarms coordinates multiple AI agents across mesh, hierarchical, star, or ring topologies for parallel task execution. Initialize a swarm topology, spawn specialized agents with defined capabilities, and assign parallel or sequential tasks to efficiently solve complex research, development, or testing workflows while maintaining fault tolerance and state management.
Swarm coordination supports four topology patterns: mesh enables peer-to-peer communication for collaborative workflows; hierarchical establishes supervisor-subordinate chains for structured delegation; star centralizes control through a coordinator node; and ring creates sequential communication paths. Choose based on your workflow's communication needs and coordination complexity.
Fault tolerance in agent swarms is implemented through error handling, cross-session persistence, and state snapshots stored in memory and knowledge graphs. These mechanisms preserve agent progress and coordination state, enabling swarms to recover from failures and maintain continuity in long-running research, development, or testing pipelines.
Yes, swarm orchestration supports adaptive, balanced, specialized, and parallel agent strategies tailored to task requirements. Adaptive agents adjust behavior dynamically; balanced agents handle mixed workloads; specialized agents focus on specific domains like research or analysis; and parallel agents execute independent subtasks simultaneously across your distributed workflow.
Mesh topology enables any agent to communicate with any other, supporting collaborative information gathering and cross-referencing ideal for research. Hierarchical topology establishes command chains with supervisors directing subordinates, better suited for structured delegation in development or testing workflows with clear dependencies.
No, memory and knowledge-graph management are integrated into swarm orchestration. The skill handles persistent state storage and cross-session knowledge retention alongside task coordination, so agents maintain context and learned information throughout distributed workflows without separate memory system setup.
whritOrchestrate distributed agent swarms across mesh, hierarchical, star, and ring topologies.
bendruckerProcess JSON data with jq filters for parsing, filtering, and transforming.
softmgOrchestrate distributed agent swarms across mesh, hierarchical, star, and ring topologies.
justSteveOrchestrate multi-agent swarms across mesh, hierarchical, and adaptive topologies.