openai/skills

Skills Catalog for Codex

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 25 minutes ago
Added to GitGenius on February 6th, 2026
Created on November 25th, 2025
Open Issues & Pull Requests: 281 (+0)
Number of forks: 1,687
Total Stargazers: 24,822 (+0)
Total Subscribers: 137 (+0)

Issue Activity (beta)

Open issues: 70
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 22 days
Stale 30+ days: 61
Stale 90+ days: 45

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 1
Events in 7 days: 1

Top labels

No label distribution available yet.

Most active issues this week

Repository Insights (GitGenius)

Median issue/PR response: 2.1 days
Mean response time: 8.1 days
90th percentile: 30.6 days
Tracked items: 37

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. 61% 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.

Detailed Description

The openai/skills repository is a catalog of reusable skills designed for OpenAI's Codex AI system. Skills are organized folders containing instructions, scripts, and resources that enable AI agents to discover and execute specific tasks in a repeatable manner. The repository serves as a distribution hub where teams and individuals can access pre-built capabilities to extend Codex's functionality without needing to rebuild the same solutions repeatedly.

The repository organizes skills into three categories based on maturity and stability. System skills located in the .system directory are automatically installed with the latest version of Codex, ensuring core functionality is always available. Curated skills in the .curated directory represent validated, production-ready capabilities that users can install by name through Codex's built-in skill-installer tool. Experimental skills in the .experimental directory offer newer or less-tested capabilities that users can opt into by specifying the skill folder or providing a GitHub directory URL. After installing any skill, users must restart Codex to activate the new capabilities.

The repository is classified across multiple AI and automation domains including language models, skill learning, AI agents, task automation, robotics, action sequences, behavior generation, reinforcement learning, program synthesis, and web navigation. This broad classification reflects the diverse range of tasks that skills can enable agents to perform. The primary language is Python, making it accessible to developers working in that ecosystem.

However, the repository includes a deprecation notice indicating that it is no longer actively maintained. The notice directs users to the OpenAI Plugins repository for current Codex skill and plugin examples. For developers wanting to add custom skills to Codex, the deprecation notice references the Build plugins guide on the OpenAI developers website, which provides instructions for creating skill-only plugins using the current recommended approach.

Each skill in the repository includes its own LICENSE.txt file within its directory, allowing individual skills to be distributed under different licensing terms. This flexibility enables contributors to share skills under licenses appropriate to their specific use cases and requirements. The repository references the Agent Skills open standard at agentskills.io, indicating alignment with broader standardization efforts in the agent skills ecosystem.

skills
by
openaiopenai/skills

Repository Details

Fetching additional details & charts...