What problem does it solve? Creating specifications for every feature in a project roadmap one at a time is slow and error-prone, and specs written in isolation often conflict with each other. This Skill automates batch spec generation while enforcing dependency ordering and cross-spec consistency. ## Core Features & Use Cases - Dependency Wave Planning: Parses the roadmap's ## Specs (dependency order) section and groups pending features into waves so upstream specs complete before downstream ones start. - Parallel Sub-Agent Dispatch: Spawns sub-agents to run the full spec pipeline (init, requirements, design, tasks) for each feature in a wave, keeping the controller context lightweight. - Cross-Spec Consistency Review: Runs a dedicated review sub-agent that checks data models, interfaces, naming, task boundaries, and architecture seams across all generated specs, with up to three remediation rounds. - Use Case: After running discovery to produce a roadmap with six features, invoke this Skill to generate spec.json, requirements.md, design.md, and tasks.md for all of them in four dependency waves, then get a consistency report before implementation. ## Quick Start Ask the AI to run the spec batch skill to generate complete specs for every pending feature in .kiro/steering/roadmap.md.
