Multi-Agent Systems

team-builder is an interactive agent picker for composing and dispatching parallel teams from markdown persona files. The team-builder skill helps you browse available agents, group specialists by domain, and build ad-hoc teams for Workflow Automation. Best for repos with flat or subdirectory agent libraries and clear persona structure.

santa-method is a multi-agent verification workflow for outputs that need to be right before they ship. It uses independent review to catch blind spots in content, code-adjacent deliverables, compliance-sensitive copy, and workflow automation tasks. Install the santa-method skill when you need a repeatable generate, verify, converge loop.

ralphinho-rfc-pipeline is an RFC-driven multi-agent workflow skill for splitting large features into verifiable units, validating each step, and merging with integration checks. It is ideal for ralphinho-rfc-pipeline for Multi-Agent Systems, refactors, schema changes, auth, perf, and security work.

iterative-retrieval is a workflow pattern for progressively refining context retrieval in agentic work. It helps subagents avoid too much or too little context, making it useful for iterative-retrieval usage, install decisions, and iterative-retrieval for Workflow Automation.

dmux-workflows is a guide for orchestrating parallel AI agent sessions with dmux in tmux panes. It helps split research, implementation, testing, and docs across Claude Code, Codex, OpenCode, and similar harnesses so you can manage multi-agent development with less context bottlenecking.

continuous-agent-loop helps agents run repeatable autonomous loops with quality gates, evals, recovery steps, and clear stop rules for reliable task completion.

claude-devfleet is a multi-agent orchestration skill for Claude DevFleet. It helps you plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports. Best for larger coding tasks that benefit from dependency-aware missions, not quick single-file edits.

autonomous-loops is a skill for designing autonomous Claude Code workflows, from simple sequential pipelines to multi-agent DAG orchestration with quality gates and handoffs.

autonomous-agent-harness turns Claude Code into a persistent, self-directing agent system with memory, scheduled runs, task dispatch, and computer use. It fits agent orchestration, recurring checks, and long-lived workflows when you need more than a one-time prompt.

Learn the agentic-engineering skill for eval-first execution, task decomposition, model routing, and safer workflow automation with regression checks.

agent-payment-x402 helps AI agents handle x402 payments with MCP tools, spending caps, recipient allowlists, and non-custodial wallets for paid APIs and agent orchestration.

dispatching-parallel-agents is an Agent Orchestration skill for splitting truly independent tasks across separate agents with isolated context and coordinated results.

langchain-architecture is a design guide for building LangChain 1.x and LangGraph applications. Use it to choose between chains, agents, retrieval, memory, and stateful orchestration patterns before implementation.