Stats
Actions
Tags
From adverant-nexus
Coordinate multiple AI agents for complex tasks via Nexus MageAgent. Use when the user needs multi-agent collaboration, competitive problem-solving, deep analysis, or information synthesis from multiple sources.
How this skill is triggered — by the user, by Claude, or both
Slash command
/adverant-nexus:agent-orchestrationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use `nexus_agents` with `action: "orchestrate"`:
Use nexus_agents with action: "orchestrate":
task (required): The task or objective to accomplishmax_agents (optional): Maximum agents to spawntimeout (optional): Timeout in millisecondsSpawns research, coding, review, and synthesis agents as needed.
Use nexus_agents with action: "collaborate":
objective (required): The collaboration objectiveagents (optional): Agent configuration array with role and focusiterations (optional): Number of collaboration iterations (1-5)Agents share context and build on each other's work iteratively.
Use nexus_agents with action: "compete":
challenge (required): The challenge for agents to solvecompetitor_count (optional): Number of competing agents (2-10)evaluation_criteria (optional): Array of criteria for rankingMultiple agents solve independently, results are ranked.
Use nexus_agents with action: "analyze":
topic (required): Topic to analyzedepth (optional): quick, standard, or deepinclude_memory (optional): Include memory context from GraphRAGUse nexus_agents with action: "synthesize":
sources (required): Array of information sourcesobjective (optional): Synthesis focusformat (optional): summary, report, analysis, or recommendationsUse nexus_agents with action: "task_status" and task_id to check on running tasks.
Use nexus_agents with action: "list" to see all active agents and their status.
npx claudepluginhub adverant/adverant-nexus-cowork-plugin --plugin adverant-nexusPatterns for multi-agent coordination, task decomposition, agent handoffs, and orchestration topology selection. Use when splitting large tasks across sub-agents or debugging agent systems.
Guides subagent dispatch decisions: when to delegate vs work inline, structuring delegation prompts, parallel fan-out sizing, and dispatching verifier agents.
Provides patterns and principles for building reliable autonomous agents: agent loops (ReAct, Plan-Execute), goal decomposition, reflection, and production guardrails. Useful when designing constrained, domain-specific agents.