smart-routing

SkillProductivity

Lets your agent pick the best model and route each task automatically based on how complex it is.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the smart-routing skill

About this capability

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

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/ruflo/skills/smart-routing/SKILL.md and read by ahel’s review.

  • 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

TierTargetLatencyCost
Agent BoosterSimple transforms (var-to-const, add-types)<1ms$0
MediumStandard coding tasks~500msLow
ComplexMulti-agent swarm coordination2-5sHigher

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

Signals

GitHub stars
2k
Forks
106
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
smart-routing
Source
github.com/a5c-ai/babysitter