This article explains how to create and manage reusable skills in OpenAI's API. Skills are packaged bundles of files that enable repeatable workflows in hosted or local environments. It covers when to use skills, how to structure them, and the API calls necessary for uploading and utilizing them.

This article covers several recent updates to OpenAI's Codex and Responses API. Key highlights include the introduction of skills for Codex, new multi-provider support, and enhancements like Gmail and Google Calendar integration. The updates aim to improve usability and efficiency for developers.

This article explains how to create and manage reusable skills in OpenAI's API. Skills are bundles of files that allow for repeatable workflows, code execution, and asset management, making them useful for structured tasks. The guide details when to use skills, how to package them, and the process for uploading and invoking them via the API.

OpenAI has implemented a new "skills" feature in ChatGPT and Codex CLI, allowing users to access and utilize structured resources for tasks like document creation. The skills function by organizing Markdown files and additional resources in a specific folder, enabling tasks such as generating PDFs and creating plugins. This development mirrors similar features from Anthropic, indicating a growing trend in AI tool capabilities.

OpenAI announced several updates, including Open Responses, an open-source spec for building multi-provider LLM interfaces. The introduction of GPT-5.2-Codex enhances complex coding tasks, while new skills and connectors improve usability and integration with other platforms.

OpenAI has updated ChatGPT's Deep Research to allow for more interactive and guided sessions. Users can now focus research on specific websites, integrate context from apps, and modify the process mid-way, making it more suited for tasks that require precise sourcing and iterative exploration. There's also a potential new "Skills" layer on the horizon to streamline workflow customization.