Orchestrates large features via RFC decomposition into verifiable work units in a multi-agent DAG, with quality gates, merge queues, complexity tiers, and recovery. Use for complex, multi-pass tasks.
From everything-claude-codenpx claudepluginhub binzetss/mobile-hvgllocalThis skill uses the workspace's default tool permissions.
Provides React and Next.js patterns for component composition, compound components, state management, data fetching, performance optimization, forms, routing, and accessible UIs.
Integrates Apple's FoundationModels for on-device LLM in iOS 26+ apps: text generation, @Generable structured output, tool calling, snapshot streaming.
Reviews Flutter/Dart code with library-agnostic checklist for widget best practices, state management patterns, Dart idioms, performance, accessibility, security, and clean architecture.
Inspired by humanplane style RFC decomposition patterns and multi-unit orchestration workflows.
Use this skill when a feature is too large for a single agent pass and must be split into independently verifiable work units.
Each work unit should include:
iddepends_onscopeacceptance_testsrisk_levelrollback_planIf a unit stalls: