adaptive-routingRoutes LLM requests to a local model first (Ollama, LM Studio, llamafile), validates the response quality, and escalates to cloud only when the local result...
Install via ClawdBot CLI:
clawdbot install joelnishanth/adaptive-routingGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:11434/api/generateAudited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Medical practices can use this skill to process patient visit summaries locally first, keeping sensitive health information private. When complex medical coding questions arise, the system escalates to cloud models while maintaining HIPAA compliance through local processing of identifiable data.
Law firms can route client document analysis requests to local models first to maintain attorney-client privilege. The quality validation ensures only properly redacted or non-sensitive content gets escalated to cloud services, reducing exposure of confidential case details.
Banks and financial institutions can use local processing for transaction analysis and suspicious activity reports containing account numbers and personal data. Complex regulatory interpretation queries get escalated to cloud models while keeping sensitive customer data on-premises.
Academic institutions can process preliminary research data locally to protect unpublished findings and intellectual property. The system escalates only validated, non-sensitive analysis requests to cloud models for complex statistical interpretation or literature review tasks.
Companies can route customer support queries locally first to handle routine issues and filter sensitive information like account credentials. Complex technical problems or escalation requests get validated and routed to cloud models while maintaining customer privacy.
Offer this routing system as a service to companies wanting to reduce cloud LLM costs. Charge based on token savings achieved, with dashboard showing ROI. Include premium features like custom validation rules and advanced analytics.
Provide implementation services to regulated industries needing local-first AI processing. Offer configuration, integration with existing systems, and compliance auditing. Include ongoing support for validation rule updates and dashboard customization.
Bundle this routing skill with pre-configured local LLM servers and cloud API management. Sell as a complete solution for enterprises wanting balanced privacy and capability. Include hardware recommendations and performance monitoring services.
💬 Integration Tip
Start by configuring the complexity threshold based on your most common query types, and ensure your local models are properly tested before production deployment to minimize unnecessary escalations.
Scored Jun 19, 2026
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
Sync OpenRouter models used by OpenClaw into this installation's config. Fetches the OpenClaw app leaderboard from OpenRouter, verifies model IDs against the...