Most skill libraries are noise. These 10 skills changed how I ship code, content, and products — with install commands and real examples.

You will know which 10 Claude Code skills deliver real value and how to install, configure, and build your own.
TL;DR: 500+ skills exist. Most add noise. These 10 earned permanent global install after 6 months of daily use: vercel-react-best-practices, next-best-practices, shadcn-ui, seo-content-writer, seo-fundamentals, tailwind-css-patterns, web-design-guidelines, architecture-patterns, clean-code, and fixing-accessibility. Plus how to build your own in 20 minutes.
Skills are folders with a SKILL.md file that Claude loads as context rules. Not plugins. Not extensions. Context.
The vercel-react-best-practices skill contains 40+ rules about React inside Vercel — avoiding unnecessary useEffect, preferring Server Components, structuring data fetching. Claude reads those rules and applies them as constraints.
| Primitive | What It Is | When It Activates | Best For |
|---|---|---|---|
| Skill | Context rules | Auto (keyword match) or globally | Standards, domain knowledge |
| Command | Slash workflow | On demand (/command) | Repeatable tasks |
| Agent | Persona + skills + tools | Configured profile | Multi-step work |
Skills are the foundation. Commands invoke skills. Agents are built on both.
40+ rules for React in Vercel apps. Every component starts Server-first. Shifts to Client only when interaction requires it. Saves bundle weight across 170+ pages.
App Router fundamentals. Layout nesting, route groups, parallel routes, metadata API. Correct route structure on the first try.
shadcn/ui integration patterns. Extends through cn() and variant props. Keeps the design system coherent instead of fighting internal styles.
Content optimization for long-form writing. TL;DR-first structure, question-based H2s, FAQ inclusion, internal linking rules.
Core SEO — crawlability, title tags, meta descriptions, canonicals, structured data. Caught 3 missing canonicals and 2 duplicate titles before I ran a crawl.
Utility-first CSS conventions. Class grouping: layout → spacing → typography → color → state. Every component readable at a glance.
Visual design for web. Spacing systems, typographic hierarchy, color contrast, visual weight. Shifts Claude from "technically correct" to "visually intentional."
System design for production apps. Separation of concerns, data flow, service boundaries. Kept the ACOS architecture clean as it grew.
Code quality rules. Naming conventions, function length, abstraction levels. Every function name becomes a description of what it does. Code reviews are faster.
WCAG 2.2 compliance. Semantic HTML, ARIA labels, keyboard navigation, focus management, color contrast. Passed WCAG 2.2 AA on first audit for the prompt library.
# Install globally
npx skills add vercel-labs/agent-skills -y -g
npx skills add vercel-labs/next-skills -y -g
npx skills add sickn33/antigravity-awesome-skills -y -g
npx skills add ibelick/ui-skills -y -g
npx skills add giuseppe-trisciuoglio/developer-kit -y -g
# List installed
npx skills list -g
Create ~/.agents/skills/my-skill/SKILL.md:
---
name: my-brand-voice
description: Brand voice rules for content
triggers:
- blog post
- landing page
- copy
---
# Brand Voice
## Rules
- Lead with outcomes, explain mechanisms second.
- Specific numbers over vague claims.
- Short sentences for impact. Longer for explanation.
## Patterns to Avoid
- Filler phrases: "it is worth noting", "in today's world"
- Passive constructions when active is available.
Full skill-building guide: Building Custom Skills for ACOS.
The 10 skills above are the general foundation. ACOS adds 75+ domain-specific skills: agent profiles, command libraries, hook systems, and memory architecture. The difference between giving Claude a style guide and giving Claude a complete operating context. Full setup: ACOS + Claude Code + MCP guide.
Start with 5-10. More adds context overhead. I run 12 globally, load more per project.
Skills as filesystem files are Claude Code-specific. Claude.ai uses system prompts — same principles, different mechanism.
Yes. Two skills with opposing rules for the same situation create inconsistent behavior. Review for overlap before combining.
Ask Claude: "What skills are active?" It lists loaded context rules.
Global (-g): universal standards. Project-level: domain-specific rules. Use both.
Step-by-step guide to setting up ACOS, creating your first agent, and shipping real products with AI.
Start buildingDownload AI architecture templates, multi-agent blueprints, and prompt engineering patterns.
Browse templatesConnect with creators and architects shipping AI products. Weekly office hours, shared resources, direct access.
Join the circleRead on FrankX.AI — AI Architecture, Music & Creator Intelligence
Weekly field notes on AI systems, production patterns, and builder strategy.

The file Claude Code reads first every session. Structure, anti-patterns, and the exact template I use to ship 170+ pages.
Read article
Step-by-step guide to building a production-grade AI coding environment with ACOS, Claude Code, MCP servers, and custom agent workflows. From zero to shipping.
Read article
Head-to-head comparison of every major AI coding agent — architecture, pricing, strengths, and which one to choose for your workflow. Updated March 2026.
Read article