nextjs-frontend-foundation
llms.txt2 starsChanged 9 days agoMITView on GitHub
Next.js Frontend Foundation is a Claude Code skill and plugin that scaffolds and extends production-ready Next.js 16 frontends with enforced conventions: TypeScript strict, Feature-Sliced Design, Tailwind CSS 4 and shadcn/ui, TanStack Query with a typed axios client, zod, SEO metadata with static generation and ISR, WCAG 2.2 AA, Vitest, MSW and Playwright with a 90% coverage gate, Lighthouse CI budgets (accessibility, best practices and SEO at 1.0), Husky hooks and GitHub Actions. Generated projects include an AGENTS.md whose rules are…
In this repositoryOne other file it gives its agents.
- frontend-foundationSkill
The file
Files
# Next.js Frontend Foundation > Next.js Frontend Foundation is a Claude Code skill and plugin that scaffolds and extends production-ready Next.js 16 frontends with enforced conventions: TypeScript strict, Feature-Sliced Design, Tailwind CSS 4 and shadcn/ui, TanStack Query with a typed axios client, zod, SEO metadata with static generation and ISR, WCAG 2.2 AA, Vitest, MSW and Playwright with a 90% coverage gate, Lighthouse CI budgets (accessibility, best practices and SEO at 1.0), Husky hooks and GitHub Actions. Generated projects include an AGENTS.md whose rules are each tied to a lint, type or test check. Install: `/plugin install frontend-foundation --marketplace albkhachikyan/nextjs-frontend-foundation`. Invoke: `/frontend-foundation:frontend-foundation new <name>` or `feature <description>`. The scaffold also runs without Claude Code: `bash scripts/scaffold.sh <dir> --name <kebab> --title "<Title>" --description "<line>"`. License: MIT. Author: Albert Khachikyan. ## Docs - [README](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/README.md): overview, install, usage, stack, verified results, FAQ - [SKILL.md](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/SKILL.md): modes and ground rules the skill follows - [AGENTS.md template](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/templates/project/AGENTS.md): the binding conventions of every generated project - [Versions and pins](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/versions.md): version pins, reasons, and known upstream pitfalls - [Architecture (FSD)](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/architecture-fsd.md): layers, slices, public API, naming, import order - [Data layer](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/data-layer.md): axios client, services, React Query, SSR prefetch, mutations - [SEO and rendering](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/seo-rendering.md): metadata, static generation, ISR, sitemap, JSON-LD - [Accessibility](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/accessibility.md): WCAG 2.2 AA checklist and keyboard shortcuts - [Testing](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/testing.md): unit, component, E2E and coverage patterns - [Security](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/security.md): env handling, CSP and headers, supply chain - [CI and hooks](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/ci-hooks.md): git hooks, CI jobs, Lighthouse budgets ## Optional - [UI states and errors](https://github.com/albkhachikyan/nextjs-frontend-foundation/blob/main/references/ui-states-errors.md): skeletons, pending buttons, error boundaries, toasts - [Task Splitter](https://github.com/albkhachikyan/claude-code-task-splitter): companion skill that routes subtasks to the cheapest capable model
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.