vercel-labs/agent-skills

Vercel's official collection of agent skills

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 47 minutes ago
Added to GitGenius on February 13th, 2026
Created on December 8th, 2025
Open Issues & Pull Requests: 171 (+0)
Number of forks: 2,717
Total Stargazers: 30,404 (+1)
Total Subscribers: 121 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 15.3 hours
Mean response time: 11.3 days
90th percentile: 29.2 days
Tracked items: 50

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 81% of tracked open issues have had no activity in three months, so the open count overstates what is actively being worked. Only 11% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 62
New in 7 days: 2
Closed in 7 days: 0
Avg open age: 43 days
Stale 30+ days: 58
Stale 90+ days: 50

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Detailed Description

Agent Skills is a collection of packaged instructions and scripts that extend the capabilities of AI coding agents.

The project addresses the need for agents to perform specialized audits and reviews across different domains of software development. It provides four main skills that follow the Agent Skills format: vercel-optimize audits deployed Vercel projects for cost, performance, and reliability by collecting metrics and investigating only the routes and files those metrics identify; react-best-practices offers over 40 performance optimization rules across 8 categories for React and Next.js development; web-design-guidelines audits UI code against more than 100 rules covering accessibility, performance, and user experience; and writing-guidelines reviews documentation and prose against 80+ rules from the Vercel writing handbook covering voice, structure, and typography.

Teams building AI agents that need to perform code reviews, optimization audits, or documentation checks should consider this collection. The skills are particularly suited for projects using Vercel infrastructure, React, or Next.js, or those requiring consistent documentation standards. The tool works best when agents need to apply opinionated best practices from Vercel Engineering rather than generic guidance.

The project maintains active engagement with its user base, with nearly all open issues coming from outside adopters reporting real-world use cases. Maintainers respond to new issues and pull requests within a day, indicating responsive stewardship of the collection.