skills/stack-nextjs-fullstack/SKILL.md
Integration patterns for Next.js + Tailwind CSS + Prisma + Auth.js — the seams between frameworks
npx skillsauth add xoai/sage stack-nextjs-fullstackInstall 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.
Layer 3 — Stack Composition
Integration patterns for the most common Next.js fullstack combination: Next.js App Router + Tailwind CSS + Prisma ORM + Auth.js.
Individual framework docs tell you how each tool works in isolation. They don't tell you how they work TOGETHER. Where does the Prisma client go in a Next.js project? How does Auth.js middleware interact with App Router layouts? What happens when Tailwind's utility classes meet server components?
These integration points — the seams between frameworks — are where most bugs live. Each framework team documents their own tool. Nobody documents the gaps between tools. That's what this pack does.
| Type | Files | Coverage | |------|-------|----------| | Integration patterns | 4 | Prisma + Next.js, Auth.js + Next.js, Tailwind + Next.js, Full-stack project structure | | Anti-patterns | 3 | Prisma client instantiation, auth in wrong layer, Tailwind in server components | | Constitution | 1 | 5 stack integration principles |
This pack requires web, react, and nextjs to be
installed. It activates when the codebase-scan detects Next.js, Tailwind CSS,
and Prisma in the project dependencies.
development
Branch-per-initiative git discipline for all delivery workflows. Defines branch naming by workflow, the propose-confirm creation protocol, dirty-tree and detached-HEAD handling, the always user-gated merge protocol, worktree support for parallel sessions, and abandonment cleanup. Activates only in git repositories — silently inactive everywhere else. Use when starting /build, /fix, /architect, or /build-x at Standard+ scope, when resuming an initiative, when offering a merge at a completion checkpoint, or when the user wants a second concurrent initiative.
development
Drives task-by-task execution from an approved plan with quality gates between each task. Reads the plan, finds the next incomplete task, dispatches implementation, validates, updates progress, and continues. Use after a plan is approved and the user says "go", "start building", "execute the plan", or "implement the feature".
testing
Preserves and restores context across agent sessions using plan file checkboxes as source of truth. Use when starting a new session, resuming previous work, ending a session, or when the user says "continue from last time", "what was I doing", or "save progress".
tools
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).