Vercel Agent Skills
Leading#4 in Skillshigh confidence
Vercel's official SKILL.md collection (~29k★): React/Next.js performance and composition best-practices plus project auditing and instant deploys.Our read
Why it ranks #4
~29.4k GitHub stars and Vercel's first-party authorship make this the most-adopted framework-specific skill collection, with unusually concrete React and Next.js engineering guidance.Here is the catch
narrowly optimized for the React, Next.js and Vercel ecosystem
framework guidance can age as platform conventions change
skills provide instructions rather than deterministic enforcement
Does this well
first-party, framework-specific recommendations
codifies detailed performance and composition practices
useful for both implementation and automated review
Pricing
Checked by hand on 2026-07-23. Prices in this category change often — if this looks wrong, it probably is.
Key features
React and Next.js performance guidancecomposition-pattern skillsproject auditingVercel deployment workflows
Sources we read
Quick facts
More in this area
The rest of the Skills column.- 1SuperpowersThe recognized leader of the Claude Code skills ecosystem (~260k★): composable SKILL.md skills chaining brainstorming, planning, subagent-driven TDD and code review.
- 2Anthropic Skills (official)Anthropic's official SKILL.md skill library (~164k★) — production-grade skills like webapp testing, MCP-server building and document editing that any agent can load.
- 3awesome-claude-skillsThe most-starred curated directory of Agent Skills (~70k★): one place to discover and install community SKILL.md skills for coding and beyond.
- 5agentskills.io (open standard + registry)The open Agent Skills spec and directory (~23k★) — discover SKILL.md skills that work across Claude Code, Codex, Gemini CLI, Cursor and more.
- 6Trail of Bits SkillsSecurity-focused SKILL.md skills from a top audit firm (~6k★) — CodeQL and Semgrep vulnerability detection wired into the agent's workflow. Niche but high-signal.
- 7DietrichGebert/ponytailRuleset that pushes coding agents down a ladder — reuse, stdlib, one-liner — before writing new code, plus over-engineering review and audit commands.