Loading...
Loading...
Found 422 Skills
Multi-agent swarm orchestration where AI agents spawn, coordinate, and self-organize into collaborative teams. Use when running parallel AI agent tasks, orchestrating multi-agent workflows across Claude Code / Codex / Cursor / custom agents, isolating agent workspaces via git worktrees, tracking task dependencies across agents, or running autonomous experiments. Triggers on: clawteam, agent swarm, spawn agents, multi-agent team, agent orchestration, parallel agents, agent coordination, swarm intelligence, agent spawn, clawteam spawn, agent worktree, agentic team, ml agent experiments, autonomous agents, agent team.
Senior Multi-Agent Systems (MAS) Architect for 2026. Specialized in Model Context Protocol (MCP) orchestration, Agent-to-Agent (A2A) communication, and recursive delegation frameworks. Expert in managing complex task handoffs, shared memory state, and parallel subagent execution for high-autonomy engineering missions.
Design multi-agent harnesses for long-running autonomous coding tasks. Covers generator/evaluator loops, context reset strategy, sprint contracts, and the planner-generator-evaluator architecture from Anthropic's harness research.
Guides the agent through building LLM-powered applications with LangChain and stateful agent workflows with LangGraph. Triggered when the user asks to "create an AI agent", "build a LangChain chain", "create a LangGraph workflow", "implement tool calling", "build RAG pipeline", "create a multi-agent system", "define agent state", "add human-in-the-loop", "implement streaming", or mentions LangChain, LangGraph, chains, agents, tools, retrieval augmented generation, state graphs, or LLM orchestration.
Deterministic AI engineering workflow with multi-agent teams. Triggers: architect mode, consistency sweep, pipeline audit, team workflow
Manage project tasks with docs/task/index.md and docs/task/PREFIX-NNN.md, including claim-before-work multi-agent coordination and immediate status sync. Use when users ask to create tasks, track progress, update task status, or coordinate implementation work. Supports English and Chinese content.
Manage parallel development with Git worktrees. Covers worktree creation with port allocation, environment sync, branch isolation for multi-agent workflows, cleanup automation, and Docker Compose integration. Use when working on multiple branches simultaneously, running parallel CI validations, or isolating agent workspaces.
Design and configure AI agents for Polpo — models, tools, identity, memory, vault, and system prompts. Use when the user wants to create an agent, configure agent capabilities, set up agent memory, manage agent credentials (vault), choose models, assign tools, or architect multi-agent systems. Triggers on "polpo agent", "configure agent", "agent design", "agent tools", "agent memory", "agent vault", "system prompt", "agent identity".
Expert in making multi-agent systems resilient. Specializes in detecting loops, hallucinations, and failures, and implementing self-healing workflows. Use when designing error handling for agent systems, implementing retry strategies, or building resilient AI workflows.
Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures
Create and orchestrate multi-agent clusters to complete complex tasks. Use this skill when users need to break down complex tasks into multiple specialized agents for parallel or serial execution. Applicable scenarios: (1) Complex projects requiring multi-role collaboration (planning, research, coding, writing, design, analysis, review) (2) Need to execute multiple independent sub-tasks in parallel to improve efficiency (3) Need professional division of labor to optimize cost and quality. Keywords: multi-agent, agent cluster, task orchestration, parallel execution, agent team.
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.