Use when the user asks for a large PRD-driven change. This skill orchestrates atomic execution, context budgeting, and verification so smaller models can do most of the work.
This skill is the repo's context-economy orchestrator. It is intentionally strict.
small-model: localized edit, straightforward config, simple doc updatelarge-model: cross-layer design, recovery from failing verification, unresolved conflictssubagentStart hook should block them.Close only when code, infra, AI layer, and docs all align with the acceptance criteria or when the exact blocker is external and explicit.39:["$","$L40",null,{"content":"$41","frontMatter":{"name":"orchestrator-prd-executor","description":"Use when the user asks for a large PRD-driven change. This skill orchestrates atomic execution, context budgeting, and verification so smaller models can do most of the work.","disable-model-invocation":true}}]