agent-usage-optimizer-complexity-tier-model-mapping
À propos
Cette compétence fournit un guide de sélection de modèle basé sur la complexité de la tâche, associant les tâches routinières à Haiku, les tâches standard à Sonnet et les tâches complexes à Opus. Elle aide les développeurs à optimiser les coûts en acheminant les tâches plus simples vers des modèles moins coûteux, tout en réservant les modèles puissants pour les travaux exigeants. Utilisez-la conjointement avec le mapping de routage lorsque la nature de la tâche est claire, afin de réduire l'écart entre l'efficacité théorique et l'efficacité observée en mise en œuvre.
Installation rapide
Claude Code
Recommandénpx skills add vamseeachanta/workspace-hub/plugin add https://github.com/vamseeachanta/workspace-hubgit clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/agent-usage-optimizer-complexity-tier-model-mappingCopiez et collez cette commande dans Claude Code pour installer cette compétence
Documentation
Complexity Tier → Model Mapping
Complexity Tier → Model Mapping
Use this alongside Route mapping when task nature is clear:
| Complexity tier | Keywords | Recommended model |
|---|---|---|
routine | format, rename, config, scaffold, update-doc, copy | Claude Haiku |
standard | implement, review, test, fix, migrate, document | Claude Sonnet |
complex | architecture, design, cross-repo, security, compound | Claude Opus |
Key insight: the gap between theoretical and observed exposure is an implementation gap —
not a capability gap. Routing routine tasks to cheaper models closes this gap for our workflow.
See WRK-5002 to automate tier detection in task_classifier.sh.
Use this skill before any multi-item work session or when quota is a concern.
Related: ai/optimization/model-selection, ai/optimization/usage-optimization
Dépôt GitHub
Compétences associées
algorithmic-art
MétaThis Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.
subagent-driven-development
DéveloppementThis skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
executing-plans
DesignUse the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.
cost-optimization
AutreThis Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.
