Skill UI

This skill defines a framework-agnostic, scalable architecture pattern for React and React Native applications. It mandates feature modules, strict state separation (server vs. UI), and disciplined import rules to create predictable, maintainable, and highly scalable codebases, regardless of the chosen framework (Next.js, Remix, etc.).

This discipline establishes a portable, framework-agnostic layer for ensuring type safety at the network edge of any React or React Native application. It mandates a single, typed API client to wrap all network fetching, guaranteeing that raw wire JSON is immediately parsed into trusted, domain-specific types or standardized error objects before entering the application state. This pattern drastically reduces runtime errors and enhances code robustness.

A comprehensive discipline for managing the write path in React or React Native applications using a query/cache layer. It codifies the full optimistic update lifecycle, ensuring that UI updates feel instantaneous, rollbacks are verbatim upon failure, and the global cache remains perfectly coherent across all components and list views. This pattern is essential for complex, highly interactive user experiences.

StyleSeed Design Review analyzes UI/frontend code (React/Tailwind/HTML) against a detailed design rubric. It scores the interface (0-100) across coherence, color discipline, hierarchy, and polish. The tool pinpoints specific violations—such as mixed corner radii or non-semantic colors—and generates a prioritized, actionable list of fixes, ensuring the final product looks professional and polished, not generic or 'AI-generated.'

This skill enforces a rigorous, multi-phase coding workflow (Discuss -> Map -> Decompose -> Execute -> Verify) to ensure code is structurally grounded, complete, and free from invented APIs or assumptions. It is designed for high-stakes, complex, or multi-file engineering tasks, acting as a senior, disciplined coding partner that plans meticulously before writing code.

This skill analyzes React, Tailwind, or HTML interfaces against a comprehensive design rubric (74 rules). It scores the UI from 0-100, identifying common flaws that make interfaces look generic, unfinished, or "AI-generated"—such as mixed corner radii, poor color discipline, or missing states. It provides a prioritized list of actionable fixes to ensure a polished, professional, and user-centric experience before deployment.

WGM is a robust, agentic methodology designed to transform vague or rough requirements into working, validated software. It enforces a disciplined workflow across six stages: deep alignment (Grill), structured planning, deterministic iterative building (Loop), mandatory holdout-scenario judging, and final documentation audits. It ensures that the resulting code converges against rigorously tested acceptance criteria rather than relying on single-pass generation.

Diagnoses full-stack failure modes in agent and LLM applications, including wrapper regressions, memory contamination, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings and code-first fixes for production agent systems.

This comprehensive guide outlines a rigorous, human-in-the-loop engineering workflow for leveraging advanced AI agents to complete complex implementation tasks. It mandates defining clear completion criteria, decomposing work into manageable units, and strategically routing models (Haiku, Sonnet, Opus) based on task complexity. The workflow emphasizes continuous evaluation, regression testing, security review of invariants and edge cases, and strict cost discipline to ensure robust and reliable software development using AI assistance.

A comprehensive guide detailing idiomatic React 18/19 patterns. Covers core principles like component purity, side effect management, hooks discipline, state location decision trees, and advanced topics such as Server/Client Component boundaries (RSC), Suspense, error handling, and using React 19 form actions for building robust, performant, and accessible UIs.

This skill transforms unstructured task lists into a disciplined, protected daily schedule. It implements the Deep Work methodology by classifying tasks into deep and shallow categories, budgeting shallow work time, and creating an energy-first time-blocked plan. It enforces strict limits, such as a 4-hour deep work ceiling, ensuring focus remains the protected resource throughout the day. Includes logging and end-of-day shutdown rituals.

This skill enforces rigorous meeting discipline through a four-stage workflow: Cost Gating, Timeboxed Agenda Building, Running the Meeting, and Action Item Extraction. It calculates meeting costs, ensures every agenda topic has a desired outcome, and converts raw notes into a structured, owner-assigned, due-dated checklist, flagging any missing owners or deadlines. Ideal for transforming unproductive meetings into actionable, accountable outcomes.