Route tasks to optimal LLM engines, models, and thinking depth.
npx skills add https://github.com/kmshihab7878/claude-code-setup --skill unified-router
Please help me install this Agent Skill. Skill: unified-router Source: https://github.com/kmshihab7878/claude-code-setup/tree/main/skills/unified-router Command: npx skills add https://github.com/kmshihab7878/claude-code-setup --skill unified-router
The unified-router removes ad-hoc and inconsistent engine/model selection by automatically choosing the optimal LLM engine, model, and thinking depth for each task across Claude Code and Qwen Code, reducing cost, risk, and coordination errors.
Ask unified-router to evaluate and dispatch the current task to the optimal engine and model with thinking enabled.
High-intent search queries and answers about installing and using this skill.
To route tasks to the best LLM engine automatically, use signal-driven routing that evaluates authority, risk tier, and cost sensitivity to select the optimal model and thinking depth for your specific task.
Model selection for multi-agent orchestration works by evaluating task requirements and MCP server needs to choose appropriate models, applying dispatch flags like --think for structured handoffs between engines like Claude and Qwen.
Yes, you can offload code generation from Claude to Qwen to save tokens using bidirectional dispatch, which supports offloading single-file tasks while escalating complex multi-file architecture plans to Claude opus.
The best way to dispatch architecture planning versus test generation is to evaluate risk tier and file coordination, routing multi-file architecture plans to Claude opus while offloading single-file test generation to Qwen with --think.
Yes, unified routing supports auto escalation between different models, allowing automatic escalation from Qwen to Claude when task complexity, authority level, or MCP server requirements demand a higher-tier engine.
anyekoutoumingOptimize Qwen model execution speed and token usage in Claude Code workflows.
jonnabioOrchestrate agent communication and coordination within multi-agent topology schemas.
MCERQUADecompose, dispatch, track, and aggregate multi-agent tasks in a mesh architecture.
fal-ai-communityCategorize fal.ai endpoints by modality and suggest task-appropriate models.
