vercel-labs/skills

The open agent skills tool - npx skills

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 12 minutes ago
Added to GitGenius on September 1st, 2026
Created on January 14th, 2026
Open Issues & Pull Requests: 1,189 (+0)
GitHub issues: Enabled
Number of forks: 2,623
Total Stargazers: 30,613 (+2)
Total Subscribers: 103 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 33.0 hours
Mean response time: 12.7 days
90th percentile: 44.5 days
Tracked items: 697

Most active contributors

Sign in to see contributor activity.

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. 44% of tracked open issues have had no activity in three months. Only 9% of issues opened in the past year have been closed. Three people close 67% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 835
New in 7 days: 47
Closed in 7 days: 30
Avg open age: 88 days
Stale 30+ days: 599
Stale 90+ days: 310

Recent activity

Opened in 7 days: 40
Closed in 7 days: 29
Comments in 7 days: 12
Events in 7 days: 25

Top labels

  • enhancement (169)
  • bug (156)

Detailed Description

skills is a CLI tool for discovering, installing, and using reusable prompts and code snippets across multiple AI coding agents.

The tool solves the problem of sharing and managing agent-specific skills—structured prompts and utilities—across different coding assistants. It works by providing a unified interface to install skills from various sources including GitHub repositories, direct URLs, and well-known registries. Skills can be installed globally for use across all projects or locally within a project directory. The CLI supports both interactive installation and non-interactive modes, and can launch supported agents with a generated prompt for a selected skill without requiring installation.

Developers should choose this tool if they work with multiple AI coding agents and want to reuse skills across them or share skills with their team. It suits projects where team members use different agents like Claude Code, Cursor, or Codex, since a single skill can be installed for multiple agents simultaneously. The tool handles authentication transparently, supporting GitHub HTTPS, SSH, and GitHub CLI credentials without exposing tokens to the Node.js process. For private repositories, it uses existing Git or GitHub CLI authentication automatically. Installation can target specific agents or skills, copy files instead of symlinking, and skip prompts for automation.

The project maintains active engagement with its ecosystem, regularly updating the list of supported agents. Development follows a pattern of incremental feature refinement, with careful attention to security practices around credential handling. The tool receives updates to its agent support and discovery mechanisms, indicating ongoing maintenance of compatibility with the evolving agent landscape.