multi-agent-thinker

SKILL.md

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.

Multi-agent systems address single-agent context limitations through distribution. Three dominant patterns exist: supervisor/orchestrator for centralized control, peer-to-peer/swarm for flexible handoffs, and hierarchical for layered abstraction. The critical design principle is context isolation—sub-agents exist primarily to partition context rather than to simulate organizational roles.

Effective multi-agent systems require explicit coordination protocols, consensus mechanisms that avoid sycophancy, and careful attention to failure modes including bottlenecks, divergence, and error propagation.

This skill is the "Heavy Lifting Engine" for complex problem solving. **CRITICAL TRIGGER LOGIC - READ CAREFULLY:** The IDE must evaluate the user's request description to decide whether to invoke this skill. **INVOKE THIS SKILL IF:** - The request involves **Ambiguity** (e.g., "Design a system...", "Analyze this...", "What do you think about..."). - The request requires **Reasoning** or **Planning** before coding (e.g., architecture design, trade-off analysis, root cause analysis). - The request implies **Multiple Perspectives** (e.g., "debate", "critique", "comprehensive review"). - The request explicitly asks for **Cognitive Strategies** (Socratic questioning, Devil's Advocate, Pre-mortem, Reverse Engineering). **DO NOT INVOKE IF:** - The request is a simple, deterministic action (e.g., "Fix the typo in line 10", "Read file X", "Run command Y"). - The request is a direct code generation for a well-defined function without need for architectural thought. When invoked, this skill triggers a multi-agent cognitive process to handle the complexity. Source: codingheader/myskills.

View raw