vercel-composition-patterns
React composition patterns for flexible, scalable UI component architecture
React composition patterns for flexible, scalable UI component architecture
npx skills add https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-composition-patternsReact composition patterns for flexible, scalable UI component architecture
This repo contains 7 individual skills — each has its own dedicated page.
Deploy Next.js apps to Vercel with correct config and environment setup
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.
69 prioritized React and Next.js performance rules across 8 categories
React Native best practices: performance, navigation, native modules, and platform APIs
Vercel's Web Interface Guidelines covering spacing, typography, interaction, and accessibility
Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
Hermes Agent + webui in Linux GUI Desktop
AI coding skill plugin for pencil.dev (.pen) design files via the Pencil MCP server — works with Claude Code, Cursor, Codex, and Gemini CLI
SNAP — agent skills for smart models that ship real software.
A Claude Code skill for heuristic-driven exploratory testing with structured MCOASTER reporting. Invoke /exploratory-testing with a test charter and Claude will run a focused exploratory testing session using FEW HICCUPPS, SFDIPOT, I SLICED UP FUN, and more useful heuristics, then automatically produce an ET report with prioritised bug findings.
In AI development, the key skill is no longer just writing code, but describing intent precisely enough that both humans and AI agents can act on it
A Claude Code / agent skill for building genuinely designed, editable Feishu / Lark (飞书) whiteboards — deliberate composition, real hierarchy, a gated pipeline with pre-render fit-check and independent design critique.