functional-area-resolver

What problem does it solve?

Routing files like RESOLVER.md and AGENTS.md grow too large, wasting valuable context budget and making agent routing slower or less reliable.

Core Features & Use Cases

• Functional-area dispatch compression: Converts long skill-per-row routing tables into one entry per functional area that dispatches to the right sub-skills.
• Dispatcher-aware routing: Uses a "(dispatcher for: ...)" clause so the model can drill into sub-skill options while keeping the top-level routing compact.
• Evaluation-focused safety checks: Guides verification via routing-eval structural checks and an LLM harness so routing accuracy is preserved after compression.
• Use Case: If your routing file is ~25KB and hits context limits, apply this pattern to compress it to ~13KB while maintaining correct intent-to-skill routing.

Quick Start

Ask the AI to compress your RESOLVER.md or AGENTS.md into functional-area dispatchers using the "(dispatcher for: ...)" format, then run routing-eval to verify routing accuracy before committing.