performance-oracle
Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability. Use after implementing features or when performance concerns arise.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability. Use after implementing features or when performance concerns arise.
Define or update Plate editor-behavior specs with a pass-gated, evidence-scored plan. Use for behavior law, authority maps, protocol rows, parity gates, research-backed winner shifts, editor chrome contracts, and implementation-roadmap changes.
Build new Plate plugins with Slate-first architecture, sane typing, and explicit React/Plate wrapper boundaries. Use when authoring or refactoring Plate plugin packages, deciding between createSlatePlugin vs createPlatePlugin, defining plugin APIs/transforms/options, or lifting semantic base plugins into React/Plate wrappers.
Build new shadcn-style components for Plate's registry and editor surfaces. Use when authoring or refactoring registry UI/components, deciding what belongs in packages vs app-local component files, creating base/live kits and registry wiring, or applying React Compiler, Effects, accessibility, polymorphism, data-slot, data-state, and composable-component rules to Plate UI work.
Use when a Slate Yjs collaboration behavior is suspicious and Potion should be used as a live reference implementation through dev-browser, especially for offline/reconnect, selection, or history scenarios.
Compatibility entrypoint for beta promotion. Prefer release-lanes for end-to-end latest/beta lane maintenance.
Author and verify Plate registry changelog entries for user-visible registry UI, kit, example, and registry metadata changes.
Maintain Plate's latest and beta release lanes end-to-end with an autogoal plan: promote next to main, sync main directly back into next, repair release metadata conflicts, re-enter beta, and verify npm/GitHub release state.
Resolve one Slate or Slate v2 GitHub issue end to end, using task-style issue intake plus Slate Plan proof discipline, then post the verified no-PR issue comment with gh.
Mine review comments for broader diff-wide fixes instead of handling each line in isolation