Frontend Design
Give an agent a stronger visual point of view before it builds or restyles a web interface.
Anthropic
Low setup · Claude Code
Source-verified agent skills
Find source-verified coding skills for frontend design, React and Next.js performance, browser testing, security review, MCP development, and repeatable engineering work.
8
Launch collection
3
Official publishers
100%
Source and terms visible
Each profile explains what the skill changes, when it earns its context, how to install it, and what to inspect before trusting it.
8 skills
Give an agent a stronger visual point of view before it builds or restyles a web interface.
Anthropic
Low setup · Claude Code
Audit UI code against Vercel-maintained interface guidance for accessibility, UX, content, and performance.
Vercel Labs
Low setup · Codex
Apply prioritized React and Next.js performance guidance from Vercel Engineering while writing or reviewing code.
Vercel Labs
Low setup · Codex
Guide the design and implementation of Model Context Protocol servers with useful, well-scoped tools.
Anthropic
Some setup · Claude Code
Test local web applications through real browser flows, screenshots, console output, and interaction checks.
Anthropic
Some setup · Claude Code
Trace trust boundaries and risky data flows through a codebase using GitHub’s reusable review workflow.
GitHub
Some setup · GitHub Copilot
Map an unfamiliar repository and turn scattered implementation details into a useful onboarding view.
GitHub
Low setup · GitHub Copilot
Create or improve reusable Agent Skills with clear triggers, scoped instructions, and supporting resources.
Anthropic
Low setup · Claude Code
Build a stronger agent workflow
Use a prompt to define the product outcome, then add the skill that improves how your agent designs, implements, tests, or reviews the work.
How to choose an agent skill
Every installed skill competes for attention and can influence agent behavior. Start with one workflow you repeat, verify that the trigger is specific, and keep only skills that measurably improve the result.
Choose a concrete job such as UI review, browser testing, codebase onboarding, or MCP server design.
Read the trigger description, instructions, scripts, references, dependencies, and license terms.
Confirm the expected folder, install command, tools, runtime, and permission model for your coding agent.
Compare a realistic task with and without the skill, then keep it only if the improvement is clear.
Prompt vs skill
Use a prompt for one outcome. Reach for a skill when the workflow repeats, needs bundled references or scripts, or should activate consistently across a team.
Browse build promptsA focused SKILL.md explains triggers, steps, constraints, and expected output.
Scripts, references, templates, and assets can be loaded only when needed.
The same review or build method can travel between projects and compatible agents.
Before installation
A skill can influence commands, files, network access, and decisions. Popularity is useful discovery evidence, but it is not a security boundary.
Read SKILL.md and bundled scripts, not just the repository description.
Understand which commands, files, credentials, and network destinations it can touch.
Prefer a reviewed commit or release when reproducibility matters.
Use a disposable branch or workspace before trusting it with a production repository.
Source ledger
Sources and install paths were reviewed on 4 September 2026. Always re-check the current repository before installation.
Anthropic Agent Skills
Anthropic · Apache-2.0 for listed example skills
Official publisher repository
Vercel Agent Skills
Vercel Labs · MIT
Official engineering repository
Awesome GitHub Copilot
GitHub · MIT; check bundled files
Official GitHub organization repository
Agent Skills specification
Agent Skills · Reference documentation
Open format specification
Frequently asked questions
Understand what coding skills contain, which agents can use them, how they differ from prompts, and what to review before installation.
An AI agent skill is a folder of reusable instructions centered on a SKILL.md file. It teaches a compatible coding agent when and how to perform a specific workflow and may include scripts, references, templates, or other supporting assets.
A prompt asks for one outcome in the current conversation. A skill defines a repeatable method that can be discovered or invoked when relevant. Use prompts to describe what you want to build and skills to standardize how design, testing, review, or another recurring task should be performed.
Support and installation locations vary. Claude Code, GitHub Copilot, Codex, Cursor, and other tools increasingly support the Agent Skills format or compatible skill folders. Check each profile and the current documentation for your agent before installing.
Do not assume so. A skill can influence commands, file changes, network access, and use of credentials. Read SKILL.md and every bundled script, inspect requested permissions, prefer a reviewed commit, and test in a disposable branch or workspace.
A skill primarily adds instructions and resources; it does not magically grant capabilities the agent does not have. However, those instructions may ask an existing shell, browser, or integration tool to perform actions, so the agent’s available permissions still matter.
Yes. Team-specific skills are useful for release checks, code review standards, migrations, documentation, and other repeatable procedures. Keep secrets out of the skill, document prerequisites, test realistic tasks, and store it where only the intended users or repositories can access it.
Start with one useful capability
Open a verified skill profile, inspect the original source, copy the installation command, and test it in a safe project before rolling it out to your team.