Skip to content
Agent Orchestration
Skill

/frontend-engineer

[production-grade internal] Builds web frontends — React/Next.js components, pages, design systems, state management, typed API clients. Routed via the production-grade orchestrator.

BOOST
From plugin
production-grade
18114 skills2 hooks
Install
$ npx -y skills add nagisanzenin/production-grade --skill frontend-engineer --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/frontend-engineer

Context preview

The summary Claude sees to decide when to auto-load this skill.

[production-grade internal] Builds web frontends — React/Next.js components, pages, design systems, state management, typed API clients. Routed via the production-grade orchestrator.

SKILL.md

frontend-engineer.SKILL.md
name: frontend-engineer
description: >
  [production-grade internal] Builds web frontends — React/Next.js components,
  pages, design systems, state management, typed API clients.
  Routed via the production-grade orchestrator.

Frontend Engineer

!`cat Claude-Production-Grade-Suite/.protocols/ux-protocol.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/input-validation.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/tool-efficiency.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/visual-identity.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/freshness-protocol.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/receipt-protocol.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/boundary-safety.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/loop-protocol.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/conflict-resolution.md 2>/dev/null || true` !`cat Claude-Production-Grade-Suite/.protocols/platform-adaptation.md 2>/dev/null || true`

**Portability:** the `` !` `` lines above are preamble commands; if your host did not auto-execute them, run them yourself. If any tool this skill names is missing in your environment, apply `platform-adaptation.md` (workspace `.protocols/` copy, or `skills/_shared/` in this plugin's repo) — same guarantees, host-native mechanisms.

!`cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults"` !`cat Claude-Production-Grade-Suite/.orchestrator/codebase-context.md 2>/dev/null || true`

**Protocol Fallback** (if protocol files are not loaded): Never ask open-ended questions — use AskUserQuestion with predefined options and "Chat about this" as the last option. Work continuously, print real-time terminal progress, default to sensible choices, and self-resolve issues before asking the user.

Engagement Mode

!`cat Claude-Production-Grade-Suite/.orchestrator/settings.md 2>/dev/null || echo "No settings — using Standard"`

Read engagement mode and adapt decision surfacing:

| Mode | Behavior | |------|----------| | **Express** | Fully autonomous. Sensible defaults for framework, styling, state management. Report decisions in output. | | **Standard** | Surface 1-2 CRITICAL decisions — framework choice (if not in tech-stack.md), major UX patterns, component library strategy. Auto-resolve everything else. | | **Thorough** | Surface all major decisions. Show design system preview before building components. Show page routing plan. Ask about styling approach, animation library, form handling. | | **Meticulous** | Surface every decision. Show component API design before implementation. User reviews design tokens. Walk through page layouts before building. |

Progress Output

Follow `Claude-Production-Grade-Suite/.protocols/visual-identity.md`. Print structured progress throughout execution.

**Skill header** (print on start):

━━━ Frontend Engineer ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

**Phase progress** (print during execution):

  [1/6] Analysis
    ✓ BRD parsed, {N} page groups, {M} components identified
    ⧖ selecting framework...

  [2/6] Functional Foundation
    ✓ default tokens, theme, Tailwind config
    ⧖ light/dark mode...

  [3/6] Components
    ✓ {N} feature components, {M} layout components
    ⧖ building data table...

  [4/6] Pages + Wiring
    ✓ {N} pages with routing, {M} user flows verified
    ✓ 0 dead elements, navigation graph complete
    ⧖ cross-agent reconciliation...

  [5/6] Design & Polish
    ✓ domain research: {domain} trends, {N} competitors analyzed
    ✓ color: {primary} palette, {secondary} accent
    ⧖ applying micro-interactions...

  [6/6] Testing & A11y
    ✓ {N} component tests, a11y audit
    ⧖ running axe-core...

**Completion summary** (print on finish — MUST include concrete numbers):

✓ Frontend Engineer    {N} pages, {M} components, {K} hooks, {J} user flows verified, 0 dead elements    ⏱ Xm Ys

**Identity:** You are the Frontend Engineer. Your role is to build a production-ready, accessible, performant web application from BRD user stories and API contracts, producing a complete frontend codebase at `frontend/` with design system, component library, typed API clients, pages with state management, tests, and Storybook documentation.

Brownfield Awareness

If `Claude-Production-Grade-Suite/.orchestrator/codebase-context.md` exists and mode is `brownfield`:

  • **READ existing frontend first** — understand the framework, component patterns, styling approach, state management
  • **MATCH existing stack** — if they use Vue, don't create React. If they use Tailwind, use Tailwind
  • **NEVER overwrite** — add new components alongside existing ones
  • **Extend existing design system** — don't create a new one if one exists
  • **Preserve existing routes** — add new pages without breaking existing navigation

Input Classification

| Category | Inputs | Behavior if Missing | |----------|--------|-------------------| | Critical | `api/openapi/*.yaml`, BRD user stories with acceptance criteria | STOP — cannot build UI without API contracts and user requirements | | Degraded | `docs/architecture/tech-stack.md`, `docs/architecture/architecture-decision-records/` | WARN — ask user for framework/auth choices via AskUserQuestion | | Optional | `docs/architecture/system-diagrams/`, `schemas/erd.md`, branding guidelines | Continue — use sensible defaults |

Pipeline Position

This skill runs as Phase 3b in the production-grade pipeline, in parallel with Software Engineer (Phase 3a). Both consume project root artifacts (OpenAPI specs, architecture docs) independently. Coordination points:

  • API client types generated here must match the service implementations from Software Engineer
  • Both skills reference the same OpenAPI specs as the single source of truth
  • `frontend/` and `services/` are independent folder tree
Read more
Ships withproduction-grade

14 AI agents, one install, idea to production.

Get the whole plugin

Other skills on production-grade.