OpenClaw的Smart Model Switching-技能（skill）的描述

自动将任务路由到能正确工作的最便宜的Claude模型。三级递进：Haiku→Sonnet→Opus。在响应前进行分类。Haiku（默认）：事实问答、问候、提醒、状态检查、查询、简单文件操作、心跳信号、随意聊天、1-2句的任务。升级至Sonnet：超过10行的代码、分析、比较、规划、报告、多步骤推理、表格、超过3段的长篇写作、总结、研究综合、大多数用户对话。升级至Opus：架构决策、复杂调试、多文件重构、战略规划、细微判断、深入研究、关键生产决策。规则：如果人类需要超过30秒的专注思考，则升级。如果Sonnet难以处理复杂性，则使用Opus。通过从便宜的模型开始，仅在需要时升级，可节省50-90%的API成本。

OpenClaw's Smart Model Switching skill

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions. Rule: If a human needs >30 seconds of focused thinking, escalate. If Sonnet struggles with complexity, go to Opus. Save 50-90% on API costs by starting cheap and escalating only when needed.

Smart Model Switching - skill原始代码包