smart-routing

Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

509 stars

bya5c-ai

View on GitHub Installation ↓

Best use case

smart-routing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

Teams using smart-routing should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/smart-routing/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/ruflo/skills/smart-routing/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/smart-routing/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How smart-routing Compares

Feature / Agent	smart-routing	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Smart Routing

## Overview

Intelligent task routing using Q-Learning to select optimal execution paths. Simple tasks route to Agent Booster (WASM, <1ms, $0), medium tasks to efficient models, and complex tasks to Opus + multi-agent swarms.

## When to Use

- Optimizing cost vs. quality tradeoffs for diverse task types
- When tasks range from simple transforms to complex multi-file changes
- Reducing latency for common code transformations
- Learning from routing history to improve future decisions

## Routing Tiers

| Tier | Target | Latency | Cost |
|------|--------|---------|------|
| Agent Booster | Simple transforms (var-to-const, add-types) | <1ms | $0 |
| Medium | Standard coding tasks | ~500ms | Low |
| Complex | Multi-agent swarm coordination | 2-5s | Higher |

## Agent Booster Transforms

- `var-to-const` - Variable declaration modernization
- `add-types` - TypeScript type annotation insertion
- `add-error-handling` - Try/catch wrapper insertion
- `async-await` - Promise chain to async/await conversion
- `extract-function` - Code block extraction to named functions
- `add-jsdoc` - Documentation generation

## Agents Used

- `agents/optimizer/` - Performance and cost optimization
- `agents/architect/` - Complex task decomposition

## Tool Use

Invoke via babysitter process: `methodologies/ruflo/ruflo-task-routing`

Related Skills

Smart Contract Analysis Skill

509

from a5c-ai/babysitter

Ethereum and blockchain smart contract security analysis

vehicle-routing-solver

509

from a5c-ai/babysitter

Vehicle routing problem solver for logistics optimization with time windows, capacity constraints, and multiple depots.

langgraph-routing

509

from a5c-ai/babysitter

Conditional edge routing and state-based transitions for LangGraph workflows

process-builder

509

from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509

from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)