Agent skills
Skills package instructions, references, and repeatable methods for agents. They complement MCP servers: a skill can guide a workflow, while an MCP server connects an agent to tools or data.
We are starting with a small source-linked set. Each entry points to its repository and skill file and names the task it supports. Check each repository for its current license and client requirements; a listing does not imply that a skill is safe or compatible with every agent.
These are source listings, not security reviews or universal recommendations. Skill files can change, so follow the source link before installing.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
https://github.com/vercel-labs/skills · Review license at source
Source checked Nov 7, 2026
Read skill source ↗Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
https://github.com/anthropics/skills · Review license at source
Source checked Nov 7, 2026
Read skill source ↗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.
https://github.com/vercel-labs/agent-skills · Review license at source
Source checked Nov 7, 2026
Read skill source ↗