openai/skills

Skills Catalog for Codex

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 44 minutes ago
Added to GitGenius on February 6th, 2026
Created on November 25th, 2025
Open Issues & Pull Requests: 290 (+0)
Number of forks: 1,709
Total Stargazers: 25,153 (+1)
Total Subscribers: 140 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 2.1 days
Mean response time: 7.9 days
90th percentile: 30.6 days
Tracked items: 39

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. 60% of tracked open issues have had no activity in three months, so the open count overstates what is actively being worked. Only 7% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 78
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 22 days
Stale 30+ days: 63
Stale 90+ days: 47

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 2
Events in 7 days: 4

Top labels

No label distribution available yet.

Most active issues this week

Detailed Description

Skills is a catalog of reusable instruction packages for Codex, an AI agent system, that enables teams and individuals to package and distribute capabilities for completing specific tasks in a repeatable way.

The tool addresses the problem of making AI agent capabilities discoverable and reusable across different contexts. Skills are folders containing instructions, scripts, and resources that Codex agents can discover and apply to perform specialized tasks. The approach organizes skills into system-installed, curated, and experimental categories, with installation handled through a skill-installer command within Codex itself.

Developers should be aware that this repository is deprecated. Current work on Codex skills and plugins has moved to the OpenAI Plugins repository, and the recommended path forward for adding custom skills to Codex is to follow the Build plugins guide in the OpenAI developer documentation. The project remains useful as a reference for understanding how skills were structured and distributed, but new development should target the plugins framework instead.

The project maintains a substantial base of adopters who report issues from real-world use rather than the core team driving the issue backlog. Maintainers typically respond to new issues and pull requests within a few days.