←Leaderboard/Agent Orchestration/Intent-Router
Last commit on September 28, 2026·Created on September 22, 2026

angel291592/Intent-Router

“Converges underspecified user requests into typed intent specifications before agent planning.”
Combined rank
#589
across all skills
In Agent Orchestration
#31
category rank
Stars
387
+689.8% in last 7d
Forks
42
Watchers
15
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

Intent-Router prevents agents from guessing user intent by implementing a parse, resolve, and typecheck flow. It is designed for automation builders who need to handle vague or contradictory requests in codebases, ticket queues, and research briefs.

The skill references existing decision records and policies to resolve ambiguities. It asks for user preferences one at a time with recommended defaults, halting execution rather than hallucinating when intent remains unclear.

WHO IT'S FOR
AI agent / automation builders
implementing typed intent convergence for agents
Prompt engineers
reducing LLM hallucinations during task routing
Platform / DevEx teams
standardizing AI-driven codebase modifications
Technical leads / architects
defining strict contracts for AI agent hand-offs
Repository contents

1 skill file

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Want to install it?
Clone to Claude · Manual Copy · NPX Skills AddRepository instructions