Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计通过

smart-model-switching智能模型切换

Agent Skill

smart-model-switching 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

186,611

周安装

7,854

GitHub Stars

21

下载量

65,345
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:smart-model-switching(智能模型切换)
来源仓库:https://github.com/millibus/smart-model-switching
安装命令:
openclaw skills install smart-model-switching
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install smart-model-switching

简介

自动将任务路由到能正常工作的最便宜的 Claude 模型。三层进展:俳句→十四行诗→作品。在回应之前先进行分类。 HAIKU(默认):事实问答、问候、提醒、状态检查、查找、简单文件操作、心跳、休闲聊天、1-2 句话任务。升级为十四行诗:代码 >10 行、分析、比较、规划、报告、多步推理、表格、长文 >3 段、总结、研究综合、大多数用户对话。升级为 OPUS:架构决策、复杂调试、多文件重构、战略规划、细致入微的判断、深入研究、关键生产决策。规则:如果一个人需要超过 30 秒的集中思考,请升级。如果 Sonnet 难以应对复杂性,请转到 Opus。从廉价开始并仅在需要时升级,可节省 50-90% 的 API 成本。

SKILL.md

name
smart-model-switching
description
>-
author
OpenClaw Community
version
1.0.0
homepage
https://clawhub.com
metadata
openclaw
emoji
💰

Smart Model Switching

Three-tier Claude routing: Haiku → Sonnet → Opus

Start with the cheapest model. Escalate only when needed. Save 50-90% on API costs.

The Golden Rule

If a human would need more than 30 seconds of focused thinking, escalate from Haiku to Sonnet. If the task involves architecture, complex tradeoffs, or deep reasoning, escalate to Opus.

Cost Reality

ModelInputOutputRelative Cost
Haiku\$0.25/M\$1.25/M1x (baseline)
Sonnet\$3.00/M\$15.00/M12x
Opus\$15.00/M\$75.00/M60x

Bottom line: Wrong model selection wastes money OR time. Haiku for simple, Sonnet for standard, Opus for complex.


💚 HAIKU — Default for Simple Tasks

Stay on Haiku for:

  • Factual Q&A — "what is X", "who is Y", "when did Z"
  • Quick lookups — definitions, unit conversions, short translations
  • Status checks — calendar, file reads, session monitoring
  • Heartbeats — periodic checks, HEARTBEAT_OK responses
  • Memory & reminders — "remember this", "remind me to..."
  • Casual conversation — greetings, small talk, acknowledgments
  • Simple file ops — read, list, basic writes
  • One-liner tasks — anything answerable in 1-2 sentences

NEVER do these on Haiku

  • ❌ Write code longer than 10 lines
  • ❌ Create comparison tables
  • ❌ Write more than 3 paragraphs
  • ❌ Do multi-step analysis
  • ❌ Write reports or proposals

💛 SONNET — Standard Work (The Workhorse)

Escalate to Sonnet for:

Code & Technical

  • Code generation — write functions, build features, scripts
  • Code review — PR reviews, quality checks
  • Debugging — standard bug investigation
  • Documentation — README, comments, user guides

Analysis & Planning

  • Analysis & evaluation — compare options, assess trade-offs
  • Planning — project plans, roadmaps, task breakdowns
  • Research synthesis — combining multiple sources
  • Multi-step reasoning — "first... then... finally"

Writing & Content

  • Long-form writing — reports, proposals, articles (>3 paragraphs)
  • Creative writing — blog posts, descriptions, copy
  • Summarization — long documents, transcripts
  • Structured output — tables, outlines, formatted docs

❤️ OPUS — Complex Reasoning Only

Escalate to Opus for:

Architecture & Design

  • System architecture decisions
  • Major codebase refactoring
  • Design pattern selection with tradeoffs
  • Database schema design

Deep Analysis

  • Complex debugging (multi-file, race conditions)
  • Security reviews
  • Performance optimization strategy
  • Root cause analysis of subtle bugs

Strategic & Creative

  • Strategic planning — business decisions, roadmaps
  • Nuanced judgment — ethics, ambiguity, competing values
  • Deep research — comprehensive multi-source analysis

🔄 Implementation

For Subagents

\\\`javascript // Routine monitoring sessions_spawn(task="Check backup status", model="haiku")

// Standard code work sessions_spawn(task="Build the REST API endpoint", model="sonnet")

// Architecture decisions sessions_spawn(task="Design the database schema for multi-tenancy", model="opus") \\\`

For Cron Jobs

\\\json { "payload": { "kind": "agentTurn", "model": "haiku" } } \\\ Always use Haiku for cron unless the task genuinely needs reasoning.


📊 Quick Decision Tree

\\\` Is it a greeting, lookup, status check, or 1-2 sentence answer? YES → HAIKU NO ↓

Is it code, analysis, planning, writing, or multi-step? YES → SONNET NO ↓

Is it architecture, deep reasoning, or critical decision? YES → OPUS NO → Default to SONNET, escalate if struggling \\\`


📋 Quick Reference Card

\\\ ┌─────────────────────────────────────────────────────────────┐ │ SMART MODEL SWITCHING │ │ Haiku → Sonnet → Opus │ ├─────────────────────────────────────────────────────────────┤ │ 💚 HAIKU (cheapest) │ │ • Greetings, status checks, quick lookups │ │ • Factual Q&A, definitions, reminders │ │ • Simple file ops, 1-2 sentence answers │ ├─────────────────────────────────────────────────────────────┤ │ 💛 SONNET (standard) │ │ • Code > 10 lines, debugging │ │ • Analysis, comparisons, planning │ │ • Reports, proposals, long writing │ ├─────────────────────────────────────────────────────────────┤ │ ❤️ OPUS (complex) │ │ • Architecture decisions │ │ • Complex debugging, multi-file refactoring │ │ • Strategic planning, deep research │ ├─────────────────────────────────────────────────────────────┤ │ 💡 RULE: If a human needs > 30 sec thinking → escalate │ │ 💰 COST: Haiku 1x → Sonnet 12x → Opus 60x │ └─────────────────────────────────────────────────────────────┘ \\\


*Built for Claude-only setups with Haiku, Sonnet, and Opus.* *Inspired by save-money skill, extended with three-tier progression.*

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

90.58%
按下载量换算59,190

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills