Claude Code Nextjs Skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Claude Code Nextjs Skills (MCP Server) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Skills for building AI applications, especially Next.js + bun runtime.
# Start a full-stack AI app
/ai-app
# Or use individual skills as needed
/ai-sdk-6 # AI agents & streaming
/postgres-semantic-search # Vector/hybrid search| Skill | Description |
|---|---|
| ai-app | Full-stack AI app (chatbots, agents, dashboards) |
| nextjs-shadcn | Next.js 16 + shadcn/ui + bun |
| nextjs-chatbot | Production chatbot (HITL, persistence, GDPR) |
| Skill | Description |
|---|---|
| shadcn | shadcn/ui component management |
| frontend-design | Production-grade frontend interfaces |
| web-design-guidelines | UI/UX review against Web Interface Guidelines |
| chrome-devtools | Live browser inspection via Chrome DevTools MCP (DOM, console, network, performance) |
| go | Browser smoke test — verify recent UI changes work |
| Skill | Description |
|---|---|
| next-best-practices | RSC, async APIs, routing, optimization |
| react-best-practices | React/Next.js performance optimization (Vercel) |
| cache-components | Cache Components & PPR |
| nextjs-seo | SEO (metadata, sitemaps, JSON-LD) |
| Skill | Description |
|---|---|
| ai-sdk | Vercel AI SDK general guide (official) |
| ai-sdk-6 | AI SDK v6 (agents, streaming, tools) |
| ai-elements | AI Elements UI components |
| openai-agents-sdk | OpenAI Agents SDK (Python) |
| Skill | Description |
|---|---|
| postgres-semantic-search | pgvector semantic & hybrid search |
| supabase-postgres-best-practices | Postgres optimization (Supabase) |
| Skill | Description |
|---|---|
| skill-creator | Create, test, and optimize custom skills (extended) |
| handoff | Write a HANDOFF.md so a fresh agent can continue your work |
Example agents for common workflows. Copy to .claude/agents/ to use.
| Agent | Description |
|---|---|
| code-simplifier | Refines code for clarity (DRY/KISS/YAGNI) |
| nextjs-reviewer | Review reports for Next.js projects |
| e2e-tester | E2E testing via DevTools MCP, Playwright, or Claude in Chrome |
Skills under Based On drift as their upstreams change. To refresh one: fetch the upstream folder, diff it against the local copy, and copy over the changed content files — but keep the local SKILL.md frontmatter, since name/description and cross-skill references are often customized. Skip a blind npx skills update: there is no lock file and some folders are renamed from upstream.
Copy or symlink skills to:
~/.claude/skills/ (global) or .claude/skills/ (project)~/.agents/skills/ or .agents/skills/Recommended MCP servers that pair with these skills:
{
"mcpServers": {
"next-devtools": {
"command": "npx",
"args": ["-y", "next-devtools-mcp@latest"]
},
"chrome-devtools": {
"command": "npx",
"args": ["chrome-devtools-mcp@latest"]
}
}
}next-best-practices, e2e-testerchrome-devtools, go, e2e-tester. Install via CLI: claude mcp add chrome-devtools --scope user npx chrome-devtools-mcp@latest.agents-first best practices, auditing (improving-skills), skill creation (skill-creator), and discovery (skill-finder) for cross-platform agent skillsMIT (this repository)
Some skills are extended from open source originals — see Based On for details.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.