agent-interopManage connections, handshakes, and protocol negotiation between agents (MCP, A2A, ACP). Use when: Connect to agent [Name], Negotiate protocol, Send A2A message, Establish handshake, Join swarm.
agent-protocolDefines and validates standard communication protocols between agents (A2A). Use when: protocol, handshake, ipc, agent-messaging, a2a.
agent-workflow-patternsBuild LLM systems from composable workflow patterns (prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer) and decide workflow vs. autonomous agent. Use when: prompt chaining, routing workflow, parallelization sectioning, orchestrator workers, evaluator optimizer, wor
agentic-patternsImplements advanced AI patterns like Reflection, ReAct, Planning, and Tool Use. Use when: agentic, reflection, react pattern, planning, memory, tool use.
meta-optimizeSelf-refining engine — analyze repeated failures in other skills and rewrite their prompts/logic to improve future runs. Use when: optimize skill, refine prompt, improve agent, meta-learning, self-evolution, fix recurring error.
multi-agent-orchPlans and orchestrates multi-agent swarms, defining roles, topologies, and handoffs. Use when: orchestrate, swarm, delegation, multi-agent, agent-team.
swarm-consensusImplement voting mechanisms (majority, weighted) to resolve inter-agent conflicts. Use when: swarm consensus.