Skills for organizing agent capabilities into versioned playbooks
Bundles files and a manifest (SKILL.md) to provide agents with versioned, executable playbooks.
A skill is a bundle of files plus a SKILL.md manifest containing frontmatter and instructions.
Giving agents access to specific capabilities, allowing them to consult a versioned playbook when performing tasks. The model uses skill metadata to decide whether to invoke a skill.
https://developers.openai.com/docs/skills/overview
Skills package files and a SKILL.md manifest, acting as versioned playbooks for agents. The platform exposes skill names and descriptions, enabling the model to decide when to invoke a skill based on its metadata.
Skills modularize agent capabilities, making them discoverable and executable by the model. The SKILL.md file provides detailed instructions for the model to follow when a skill is invoked.
- Shell + Skills + Compaction: Tips for long-running agents that do real work ↗OpenAI Developers Blog · OpenAI Developers Blog · Sep 3, 2026 · paraphrased
First seen on Subvolts Sep 3, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Shell + Skills + Compaction: Tips for long-running agents that do real workOpenAI · OpenAI Developers Blog · Sep 3, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- ChecklistAX Practitioner Playbook Evaluation Quality ChecklistReview your AI agent evaluation process before running it to ensure its quality and trustworthiness. · 30 min
- Skill or agent configJoplin agent for automated note filing and retrievalAutomate note organization and retrieval in Joplin using a custom agent and Python scripts. · 60 min
- HeuristicUse reasoning models for improved reliability on complex tasksEmploy reasoning models like o1, o3, and o4-mini for dramatically improved reliability on complex, multi-step work. · 5 min
- Setting tipStore AI agent traces and evaluation data with projectKeep traces, evaluation datasets, and results with your project for repeatable testing. · 5 min
- WorkflowBuild and test an AI agent using Microsoft Foundry ToolkitCreate, configure, test, and evaluate an AI agent within VS Code. · 60 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with in the sources.
- Where did this come from?
- OpenAI Developers Blog (OpenAI Developers Blog). Subvolts collected, normalized and credited it; the link above opens the original.