frontend▌

Build a compelling promotion case by diagnosing blockers and framing advancement as solving company problems. \n \n Diagnose the situation by understanding current role, target role, manager relationship, and identifying whether blockers are visibility, advocacy, role availability, or skill gaps \n Core principle: perform at the next level before requesting the title; promotions recognize readiness, they don't develop it \n Frame promotion conversations around business impact and company needs,

Data-driven persona generation, journey mapping, and usability testing frameworks for user research and design validation. \n \n Generates research-backed personas from user data and interviews, with behavior pattern analysis, psychographic extraction, and confidence scoring \n Supports customer journey mapping, usability testing frameworks, and research synthesis to inform design decisions \n Includes design validation methods and scenario generation tied directly to persona insights \n

Exhaustive React API research from authoritative sources, not training knowledge. \n \n Spawns six parallel research agents to systematically search React's test files, source code, git history, PRs, issues, and type definitions \n Enforces skepticism mandate: treats source material as sole authority and flags discrepancies between findings and common understanding \n Generates documented research with exact file paths, line numbers, and source links for every claim, code example, and warning \n

Foundational game design theory covering MDA framework, player psychology, and balance principles. \n \n Explains the MDA framework (Mechanics → Dynamics → Aesthetics) and core engagement loops with fast feedback, clear causation, and rewarding outcomes \n Covers flow channel theory for matching challenge to player skill, Bartle's player types, and self-determination theory (autonomy, competence, relatedness) \n Details reward systems including intrinsic vs. extrinsic rewards and scheduling stra

Styling guidelines for the Mastra Playground UI, containing 5 rules across 3 categories. Rules are prioritized by impact to guide automated refactoring and code generation. These rules ensure design system consistency, prevent token drift, and maintain component library integrity.

Convert JSON specs into React component trees with type-safe props and state management. \n \n Define catalogs with Zod schemas for component props, then implement components with automatic type safety and validation \n Built-in state management via StateProvider with two-way binding ( $bindState ), conditional rendering, and external store integration (Redux, Zustand, XState) \n Event system with action dispatching, state watchers, and four built-in actions (setState, pushState, removeState, va

Framework for running design reviews using feedback hierarchy and structured critique. \n \n Prioritize feedback by value first (does it solve the problem?), then usability, then delight; defer aesthetic concerns until core value is validated \n Assign senior leaders as project sponsors to oversee quality through live demos and review 100% of shipped screens before launch \n Structure reviews around specific feedback requests; ask presenters exactly what type of input they need rather than openi

Build an HTML page that loads traces from a data source (JSON/CSV file), displays one trace at a time with Pass/Fail buttons, a free-text notes field, and Next/Previous navigation. Save labels to a local file (CSV/SQLite/JSON). Then customize to the domain using the guidelines below.

Build browser extensions for Chrome, Firefox, and cross-browser platforms using Manifest V3 architecture. \n \n Covers extension structure, Manifest V3 configuration, content scripts, background service workers, popup UIs, and storage patterns \n Includes communication patterns between popup, background worker, and content scripts; DOM injection and event handling on web pages \n Provides Chrome Storage API usage with async/await patterns, storage limits, and data persistence across devices \n H

Generate detailed Product Requirements Documents optimized for AI agent execution via ralph-tui task orchestration. \n \n Guides users through adaptive clarifying questions to understand feature scope, goals, and quality requirements \n Produces structured PRDs with user stories, functional requirements, and explicit quality gates for automated conversion to beads issues or prd.json \n Emphasizes small, independently completable user stories with verifiable acceptance criteria suitable for singl