skill-selector

An AI agent determines the right skill by applying internal curiosity, self-generating key questions, and resolving them from available context like open files and conversation history to deduce intent.

Context-driven skill discovery is the process of analyzing project structure and conversation history to enumerate available skills, map needs to the right match, and present top candidates with rationale.

You route a request by running an internal curiosity workflow on the current context to analyze the input, identify the most appropriate skill, and output a deterministic ranked list of recommended skills.

You should use automated skill matching when requests are ambiguous, when multiple skills could match, or when discovery of available skills is needed to reduce ambiguity and speed up task routing.

The best way to handle ambiguous requests is using internal self-questioning and context analysis to deduce intent, enumerate matching candidates, and provide a deterministic output listing recommended skills with rationale.

Your agent recommends multiple skills because it enumerates available options during skill discovery and presents top candidates with concise rationale when multiple skills could match the context.