model-selection

This skill optimizes AI model selection by reading quota states and recommending the best Claude/Codex/Gemini allocation for each task. It provides quota-aware routing and headroom displays, making it ideal for work sessions with multiple queued items or when approaching quota limits. Developers should use it before starting sessions with 3+ work items or when Claude quotas drop below 50% remaining.

This skill displays remaining API quota percentages for different AI providers in a formatted table with color-coded status indicators. It helps developers choose the most appropriate model based on availability and recommended use cases. The output includes cache freshness information and visual status thresholds for quick quota assessment.

This skill provides default AI model routing logic for different coding task complexities, independent of quota limits. It maps simple tasks to Codex, standard tasks to Claude Sonnet, and complex architectural work to Claude Opus, with fallback options specified. Developers should use this as the baseline configuration for optimizing AI agent usage in their coding workflows.

This Claude skill classifies development tasks into specific processing routes (A, B, C, Bulk, Long-context) based on keywords in the user's request. It helps optimize agent usage by routing simple tasks, standard implementations, complex architecture work, bulk operations, and large-context jobs appropriately. Developers use it to ensure their queries are handled by the most suitable agent with the correct scope and resources.