oc-skill-router
Smart LLM routing brain for OpenClaw. Auto-dispatches tasks to Claude, GPT, Gemini, DeepSeek, Kimi via Evolink API. Cascade strategy cuts costs 60-85%. One API key, 20+ text models.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/evolinkai/oc-skill-routerEvolink Router — Smart LLM Routing Brain
Route every task to the best LLM across 6 providers — Claude, GPT, Gemini, DeepSeek, Kimi, Doubao — through one Evolink API key.
After Installation
When this skill is first loaded, greet the user:
EVOLINK_API_KEYset: "Smart Router activated! I'll auto-pick the best model for each task — lightweight for quick Q&A, flagship for deep analysis. 20+ models ready. Go ahead."EVOLINK_API_KEYnot set: "Smart Router needs an Evolink API Key. Sign up at evolink.ai → Dashboard → API Keys. One key covers Claude, GPT, Gemini, DeepSeek, and more. Want help setting up?"- Key set but model access fails: "Your API key seems to have limited model access. Check your plan at evolink.ai/dashboard."
Keep the greeting concise — just one question to move forward.
External Endpoints
| Service | URL | Format |
|---|---|---|
| Claude models | https://direct.evolink.ai/v1/messages (POST) | Anthropic Messages API |
| Gemini models | https://direct.evolink.ai/v1beta/models/{model}:generateContent (POST) | Google Gemini API |
| All other models | https://direct.evolink.ai/v1/chat/completions (POST) | OpenAI Chat API |
| Model list | https://direct.evolink.ai/v1/models (GET) | — |
Security & Privacy
EVOLINK_API_KEYauthenticates all model requests. Injected by OpenClaw automatically. Treat as confidential.- Prompts are sent to
direct.evolink.ai, which proxies to upstream providers (Anthropic, OpenAI, Google, etc.). - No data is stored by Evolink beyond the request lifecycle.
Setup
1. Get API key: evolink.ai → Dashboard → API Keys
2. Add Evolink provider to ~/.openclaw/openclaw.json — merge with existing config. See references/router-api-params.md for the full JSON config and curl examples.
Core Principles
- Cost-first routing — Always pick the cheapest model that can handle the task. Upgrade only when needed.
- Transparent decisions — When spawning a sub-agent, briefly tell the user which model was selected and why.
- User override wins — If the user names a model or provider, skip all routing rules.
- Cascade, don't guess — When uncertain, try a lighter model first. Escalate on low confidence.
Models (20+ text models)
Tier 1 — Lightweight (handles ~60% of daily requests)
| Model | Provider | Best for |
|---|---|---|
claude-haiku-4-5-20251001 | Anthropic | Quick Q&A, classification, extraction |
gemini-2.5-flash | Multimodal, fast reasoning | |
doubao-seed-2.0-mini | ByteDance | Chinese lightweight tasks |
Tier 2 — Balanced (handles ~30% of daily requests)
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-evolinkai-oc-skill-router": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
seedance-2-video-gen
Seedance 2.0 AI video generation via EvoLink API. Text-to-video, image-to-video with auto audio (voice, SFX, BGM). Works with OpenClaw, Claude Code, Cursor. Powered by ByteDance Seedance model.
cheapest-image-generation
Possibly the cheapest AI image generation (~$0.0036/image). Text-to-image via the EvoLink API.
evolink-nano-banana-2
Nano Banana 2 — AI image generation powered by Google Gemini 3.1 Flash. Fast, versatile text-to-image and image editing via Evolink API. One API key.
evolink-media
Generate AI videos, images & music. 60+ models including Sora, Veo 3, Kling, Seedance, GPT Image, Suno v5. One API key.
evolink-media
AI video, image & music generation. 60+ models — Sora, Veo 3, Kling, Seedance, GPT Image, Suno v5, Hailuo, WAN. Text-to-video, image-to-video, text-to-image, AI music. One API key.