engineering/skills/frontend/SKILL.md
Use for frontend engineering work such as components, routes, state management, accessibility, performance, design-system integration, and browser-facing debugging or refactors.
npx skillsauth add alvarovillalbaa/agent-suite frontendInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill owns browser-facing implementation depth. Use it together with ../agentic-development/SKILL.md: agentic-development handles repo orientation, planning, and execution model; this skill handles UI/component/framework detail.
../agentic-development/SKILL.md for repo orientation and proof planning.../backend/SKILL.md for that slice instead of inventing server logic from the client side.../backend/SKILL.md for server-side changes.Read frontend-development.md for the main delivery loop: framework boundary detection, reusable component design, refactor workflow, async UX, accessibility, responsiveness, performance priorities, analytics, and the frontend helper scripts.
Read frontend-best-practices.md for TypeScript patterns, Tailwind+CVA patterns, feature structure, barrel-export guidance, and common security guardrails for frontend code.
Read react-patterns.md for concrete React composition, hooks, state management, and anti-pattern examples.
Read react-performance-rules.md and references/react-rules/ when performance, bundle size, render churn, caching, or rendering cost matters.
Read no-use-effect.md whenever writing or reviewing React components that might drift into defensive useEffect usage.
Read nextjs-optimization-guide.md for rendering strategies, streaming, caching, dynamic imports, and Core Web Vitals work.
Read next-best-practices.md and references/next-best-practices/ when writing or reviewing Next.js code.
Read building-components.md when designing component APIs, primitives, accessibility patterns, composition systems, or library distribution.
Read component-refactoring.md when reducing component complexity or extracting hooks and structure.
Read design-system.md when auditing or extending a design system itself.
Read shadcn.md and references/shadcn/ for shadcn/ui component work, theming, registry usage, and update workflows.
Read signup-onboarding-flows.md when implementing signup forms, auth selection, verification states, onboarding checklists, empty states, guided tours, or activation instrumentation.
Read ui-constraints.md for hard MUST/NEVER/SHOULD rules around stack defaults, accessible primitives, motion budget, layout discipline, glassmorphism technique, and design guardrails.
Read design-engineering.md for animation decisions, interaction polish, gestures, and perceived performance. The Quick Decision table at the top is the fastest path to the right easing and duration.
Read transitions.md for the CSS micro-transition pattern library: nine drop-in transitions (card resize, number pop-in, notification badge, text swap, dropdown, modal, panel reveal, page slide, icon swap) with semantic CSS custom properties and a decision tree for picking the right one.
Read anti-slop.md for forbidden AI design patterns, the brand-mode vs product-mode register system, and the pre-ship anti-slop checklist. Apply before shipping any UI to avoid recognizable AI clichés.
Read ui-ux-guidelines.md for broader UX rules across accessibility, forms, navigation, charts, interaction design, audio feedback, predictive prefetching, and the named Laws of UX (Fitts', Hick's, Miller's, Jakob's, von Restorff, Zeigarnik, and 13 others).
Read web-design-guidelines.md when auditing UI code or validating a page against best practices.
Read pre-shipping-polish.md for final visual and interaction cleanup before shipping.
Read design-consultation.md when creating a design system or visual direction from scratch.
Read design-critique.md for structured feedback on mockups, screenshots, or Figma designs.
Read design-review.md for live-site visual QA and iterative polish.
Read references/epic-design/ when the task is cinematic, scroll-driven, premium, or immersive. The asset pipeline, depth system, motion system, accessibility, and performance references in that folder should be treated as a required bundle for scrollytelling work.
scripts/component_generator.py for consistent component scaffolding.scripts/bundle_analyzer.py for pre/post change JS bundle analysis.scripts/frontend_scaffolder.py for route/page/feature scaffolding.scripts/inspect-assets.py for asset inspection in design-heavy or cinematic work.scripts/validate-layers.js for validating layered cinematic builds.../agentic-development/SKILL.md.../backend/SKILL.md for any server-side dependency instead of faking it in the client.../backend/SKILL.md for API contracts, auth, persistence, queues, caching, schema design, and service logic.../agentic-development/SKILL.md when the work needs execution-mode selection, repo-wide planning, PR/review handling, or coordinated frontend/backend delivery.quality-assurance when verification strategy, flaky tests, or passive security review becomes the bottleneck.development
This skill should be used when the user asks to write, update, review, scaffold, move, remove, or continuously improve documentation for code, folders, services, repos, workflows, architectural decisions, or operational processes. Trigger for inline docs, `README.md`, `ARCHITECTURE.md`, `TESTS.md`, `SETUP.md`, `RUNBOOK.md`, `CHANGELOG.md`, `SECURITY.md`, `OVERVIEW.md`, `FAQ.md`, `DECISIONS.md`, `DEPENDENCIES.md`, `AGENTS.md`, `PLAN.md`, `SPEC.md`, `SOUL.md`, `PRINCIPLES.md`, `DESIGN.md`, `logs/`, `lessons/`, `items/`, `fixes/`, `audits/`, `raw/`, `plans/`, `specs/`, `sources/`, `lib/`, `references/`, `cookbook/`, `knowledge/`, `runbooks/`, `research/`, `official-documentation/`, `context/`, MDX docs, JSDoc/TSDoc, docstrings, ADRs, post-mortems, migration guides, documentation cleanups, and documentation-impact reviews.
tools
Cross-cloud CLI-first cloud operations for AWS, Azure, and GCP. Use when the assistant needs to identify which cloud provider or multi-cloud estate a repo uses, deploy new resources or services, wire automatic deployments, inventory and optimize infrastructure, or diagnose and repair cloud failures entirely from the terminal, with explicit approval gates for high-cost, destructive, identity-sensitive, or hard-to-reverse changes. Covers AWS Amplify full-stack projects, serverless workloads (Lambda, API Gateway, Step Functions, SAM, CDK), and the full AWS database portfolio (RDS, Aurora, Aurora DSQL, DynamoDB, ElastiCache), as well as deep Azure references for diagnostics, storage, compute, compliance, identity, Foundry, and cross-cloud migrations.
development
Use for backend engineering work such as APIs, services, data models, persistence, queues, caching, auth, background jobs, and server-side debugging or refactors.
tools
Use for AI and agent engineering work: system prompt design, tool call architecture, context engineering, memory and learning systems, multi-agent coordination, evals and regression gates, fine-tuning pipelines, RAG, vector stores (TurboPuffer/Pinecone/Azure), agent governance and safety, run steering, skill packages, prompt engineering patterns, constrained generation, ML pipelines, data engineering, and production AI infrastructure.