openai / skills

2025-11-25 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Agent Skills are standardized collections of instructions, scripts, and resources designed for AI agents to discover and execute specific tasks repeatedly. OpenAI's Codex platform utilizes these skills to package capabilities for teams and individuals. The repository catalogs these skills, which are categorized into `.system`, `.curated`, and `.experimental` folders. Skills located in the `.system` directory are automatically integrated into the latest Codex version. Users can install `.curated` or `.experimental` skills within Codex using the `$skill-installer`, either by skill name for curated skills or by specifying the skill folder or GitHub directory URL for experimental ones. A restart of Codex is required after installation to activate new skills.

Key takeaway

For AI Engineers developing or deploying agents with OpenAI Codex, understanding and utilizing Agent Skills is crucial for efficient task automation. You should leverage the `$skill-installer` to integrate pre-built or custom skills, ensuring repeatable and standardized agent behaviors. This approach streamlines development and promotes reusability across projects.

Key insights

Agent Skills standardize AI agent capabilities for repeatable task execution across various applications.

Principles

• Write once, use everywhere
• Modular agent capabilities

Method

Skills are installed in Codex via a `$skill-installer` command, referencing either a skill name or a GitHub directory URL, followed by a Codex restart.

In practice

• Install `gh-address-comments` skill
• Install `create-plan` from `.experimental`
• Restart Codex after skill installation

Topics

• Agent Skills
• OpenAI Codex
• Skill Management
• AI Agent Capabilities
• Skill Installation

Code references

• openai/skills

Best for: AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase — Agent skills enhance LLM performance by providing context and workflows through progressive disclosure.
• Two Ways to Build a Skill Server for Your AI Agent — Dynamically loading skills with rich descriptions improves AI agent tool selection and context window efficiency.
• addyosmani / agent-skills — AI coding agents can achieve production-grade software quality by following structured, verifiable engineering workflows and best practices.
• My approach to agentic skills — Effective agentic skill management involves careful design, context optimization, and a feedback loop for self-correction.
• Learn to equip AI agents with reusable skills — Agent skills provide on-demand, specialized knowledge to AI agents through standardized, reusable task-specific modules.
• You NEED to try these 12 open-source AI projects RIGHT NOW — Open-source AI projects offer specialized tools for video, coding, cybersecurity, and agent orchestration.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.