LLM Router

Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding which model to call, optimizing LLM costs, or building multi-model agent systems. Activate on "which model", "model selection", "route to model", "LLM cost", "model routing", "cheap vs expensive model". NOT for prompt engineering (use prompt-engineer), model fine-tuning, or training custom models.

272 stars 46 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add curiositech/some_claude_skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add curiositech/some_claude_skills --skill llm-router
Manual install
git clone --depth 1 https://github.com/curiositech/some_claude_skills.git /tmp/some_claude_skills
mkdir -p ~/.claude/skills
cp -r /tmp/some_claude_skills/.claude/skills/llm-router ~/.claude/skills/llm-router

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# LLM Router

Selects the optimal LLM model for each task. The single biggest cost lever in multi-agent systems — intelligent routing saves 45-85% while maintaining 95%+ of top-model quality.

---

## When to Use

✅ **Use for**:
- Deciding which model to call for a specific task
- Assigning models to DAG nodes in agent workflows
- Optimizing LLM API costs across a system
- Building cascading try-cheap-first patterns

❌ **NOT for**:
- Prompt engineering (use `prompt-engineer`)
- Model fine-tuning or training
- Comparing model architectures (academic research)

---

## Routing Decision Tree

```mermaid
flowchart TD
  A{Task type?} -->|Classify / validate / format / extract| T1["Tier 1: Haiku, GPT-4o-mini (~$0.001)"]
  A -->|Write / implement / review / synthesize| T2["Tier 2: Sonnet, GPT-4o (~$0.01)"]
  A -->|Reason / architect / judge / decompose| T3["Tier 3: Opus, o1 (~$0.10)"]
  
  T1 --> Q1{Quality sufficient?}
  Q1 -->|Yes| Done1[Use cheap model]
  Q1 -->|No| T2
  
  T2 --> Q2{Quality sufficient?}
  Q2 -->|Yes| Done2[Use balanced model]
  Q2 -->|No| T3
```

---

## Tier Assignment Table

| Task Type | Tier | Models | Cost/Call | Why This Tier |
|-----------|------|--------|-----------|---------------|
| Classify input type | 1 | Haiku, GPT-4o-mini | ~$0.001 | Deterministic categorization |
| Validate schema/format | 1 | Haiku, GPT-4o-mini | ~$0.001 | Mechanical checking |
| Format output / template | 1 | Haiku, GPT-4o-mini | ~$0.001 | Structured transformation |
Read the full skill on GitHub

Details

Skill name
llm-router
Path
.claude/skills/llm-router/SKILL.md
License
MIT
Repo updated
5 November 2026

FAQ

What does the LLM Router skill do?

Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding which model to call, optimizing LLM costs, or building multi-model agent systems. Activate on "which model", "model selection", "route to model", "LLM cost", "model routing", "cheap vs expensive model". NOT for prompt engineering (use prompt-engineer), model fine-tuning, or training custom models.

How do I install the LLM Router skill?

Claude Code plugin: /plugin marketplace add curiositech/some_claude_skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is LLM Router popular?

It lives in curiositech/some_claude_skills, which has 272 GitHub stars and 46 forks.

Related skills

Email Composer

272

curiositech/some_claude_skills

Draft professional emails for various contexts including business, technical, and customer communication. Use when the user needs help writing emails or composing professional messages.

Productivity & Notes46

2000s Visualization Expert

272

curiositech/some_claude_skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

Data & Analytics46

2026 Legal Research Agent

272

curiositech/some_claude_skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic expungement research". NOT for interpreting laws (use national-expungement-expert), building UI, or legal advice.

Research & Science46

LLM Streaming Response Handler

272

curiositech/some_claude_skills

Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE", "token stream", "chat UI", "real-time AI". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.

AI, LLMs & Agents46

Interview Loop Strategist

272

curiositech/some_claude_skills

Orchestrates end-to-end interview preparation for senior ML/AI engineers targeting Anthropic and peer companies. Use for prep timeline generation, story coherence across rounds, mock scheduling, and debrief analysis. Activate on "interview prep", "interview loop", "Anthropic interview", "prep timeline". NOT for resume writing, career narratives, or individual round-type practice.

AI, LLMs & Agents46

MCP Creator

272

curiositech/some_claude_skills

Expert MCP (Model Context Protocol) server developer creating safe, performant, production-ready servers with proper security, error handling, and developer experience. Activate on 'create MCP', 'MCP server', 'build MCP', 'custom tool server', 'MCP development', 'Model Context Protocol'. NOT for using existing MCPs (just invoke them), general API development (use backend-architect), or skills/agents without external state (use skill-coach/agent-creator).

AI, LLMs & Agents46

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.