ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

smart-model-router

Route every substantive user request to the optimal LLM model. Trigger on EVERY substantive request. Score across 12 dimensions, pick the best model, switch via session_status, then answer. Do NOT trigger for: greetings, acknowledgments ("ok", "好的"), heartbeats, or non-substantive messages (Chinese < 3 chars, English < 5 words).

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bevanding/model-router-pro
Or

Smart Model Router

Every Substantive Request

  1. Score: python3 <skill_path>/scripts/router.py --task "<user message>"
  2. Parse JSON → get full_id, tier, confidence
  3. If full_id is fallback/default: do NOT switch. Tell the user to run --setup.
  4. If full_id differs from current model: session_status(model=<full_id>)
  5. Answer the user. Do not volunteer routing details, but disclose when asked.

Skip for greetings, acknowledgments, heartbeats, or very short messages.

First-Time Setup

python3 <skill_path>/scripts/router.py --setup

Recommended: Reinforce in AGENTS.md

Add the following line to your agent's AGENTS.md for reliable auto-trigger:

Always follow smart-model-router SKILL.md instructions on every substantive request.

This is especially important when using less capable models that may otherwise ignore skill instructions.

CLI

--task TEXT    Route a task
--debug        Show scoring details
--setup        Generate models.json

Metadata

Author@bevanding
Stars4473
Views0
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bevanding-model-router-pro": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

walletconnect-requester

Secure WalletConnect integration for AI agents. Connect to user wallets as a DApp (Proposer) without ever handling private keys. Request transactions and signatures - users approve everything in their wallet. Zero custody, maximum security. Use when you need to interact with user wallets securely via WalletConnect v2.

bevanding 4473

deerflow

Deep research and async task execution via DeerFlow LangGraph engine. Submit multi-step research tasks through a lightweight API-only Docker deployment (no frontend). Triggers: /deerflow, deep research, async research, deerflow.

bevanding 4473

transaction-receipt

Human-readable on-chain transaction receipt. Resolve tx status, fees, and intent: simple transfers, swaps/trades, token approvals, DeFi staking-style calls, and NFT mint/transfer. Optional Tokenview API key; falls back to public read-only sources when unset or invalid. Timeouts, rate limits, and response validation included.

bevanding 4473

eth-payment

Generate EIP-681 Ethereum payment links and QR codes for any EVM chain. Zero configuration, instant setup for receiving ETH and ERC-20 payments. Use when you need to create payment requests, invoices, donation links, or any on-chain payment request. Supports Base, Ethereum, Arbitrum, Optimism, Polygon.

bevanding 4473

antalpha-ai-setup

Install and configure the Antalpha Skills MCP server. Provides 76 Web3 tools for DEX swaps, smart money tracking, Polymarket prediction markets, Hyperliquid perpetuals, CEX trading, Bitcoin mining, and DeFi analytics.

bevanding 4473