Menu
Route a task to the best LLM based on task type and complexity
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | route |
| description | Route a task to the best LLM based on task type and complexity |
| trigger | /route |
Route any task to the optimal LLM automatically.
/route <task description>
Most prompts are classified automatically by the UserPromptSubmit hook — no /route needed. The hook uses a multi-layer classification chain:
Heuristic scoring (instant, free) — Three signal layers accumulate evidence:
Ollama local LLM (~1s, free) — When heuristics are uncertain, qwen3.5 classifies locally via the chat API with thinking disabled
Cheap API model (~$0.0001) — If Ollama is unavailable, Gemini Flash or GPT-4o-mini classifies
Weak heuristic / auto fallback — Last resort: low-confidence heuristic match or llm_route (full LLM classifier)
| Category | Tool | Signals |
|---|---|---|
| Research | llm_research | Current events, news, funding, trends, market data, rankings |
| Generate | llm_generate | Writing, drafting, brainstorming, emails, articles, translations |
| Analyze | llm_analyze | Evaluation, debugging, comparison, trade-offs, code review |
| Code | llm_code | Implementation, refactoring, building, bug fixes |
| Query | llm_query | Simple questions, definitions, explanations |
| Image | llm_image | Visual generation, design, artwork |
| Complexity | Profile | Model Tier |
|---|---|---|
| Simple | budget | Gemini Flash, GPT-4o-mini |
| Moderate | balanced | GPT-4o, Gemini 2.5 Pro |
| Complex | premium | o3, Gemini 2.5 Pro |
Every 5th routed task, the system shows estimated savings: Claude API costs avoided and rate limit capacity preserved. Run llm_usage for a detailed breakdown.
What are the top 3 AI startups that raised funding?
→ research (heuristic, score=8) → llm_research (budget) → Perplexity Sonar
Write me a blog post about productivity tips
→ generate (heuristic, score=5) → llm_generate (balanced) → Gemini 2.5 Pro
Compare React vs Vue for our new project
→ analyze (ollama, qwen3.5) → llm_analyze (balanced) → GPT-4o
Implement a rate limiter in Python using sliding window
→ code (heuristic, score=4) → llm_code (balanced) → GPT-4o
What is a monad?
→ query (ollama, qwen3.5) → llm_query (budget) → Gemini Flash
Environment variables:
LLM_ROUTER_OLLAMA_MODEL — Ollama model (default: qwen3.5:latest)LLM_ROUTER_OLLAMA_URL — Ollama server (default: http://localhost:11434)LLM_ROUTER_OLLAMA_TIMEOUT — Timeout in seconds (default: 5)LLM_ROUTER_CONFIDENCE_THRESHOLD — Heuristic score cutoff (default: 4)