# Exploring the Power of Context Engineering: Unlocking Anthropic's Skills Feature

> Context Engineering with JIT injection

**Published by:** [The Agentic World](https://paragraph.com/@theagenticworld/)
**Published on:** 2025-10-16
**Categories:** ai, coding, claude, anthropic, agentic
**URL:** https://paragraph.com/@theagenticworld/unlocking-anthropics-skills-feature

## Content

Anthropic published a new feature called Skills and on the surface it sounds like a simple plugin of some sort. What it actually does is JIT context injection with increasing levels of information added as needed: It uses YAML frontmatter for token efficiency and has the following anatomy: Level 1: Metadata (always loaded) < 100 Tokens Level 2: Instructions (loaded when triggered) < 5000 Tokens Level 3: Resources and code (loaded as needed) (∞)! Read their full engineering blog post: Equipping agents for the real world with Skills Discover how Anthropic builds AI agents with practical capabilities through modular skills, enabling them to handle complex real-world tasks more effectively and reliably. https://www.anthropic.com Some people will consider this a proprietary approach but I have used heavily to allow for larger protocols but seeing Anthropic standardise is great validation of the concept. You can find an excerpt of my AGENTS.md that uses this approach here AGENTS.md JIT Loading Pattern GitHub Gist: instantly share code, notes, and snippets. http://github.com Very excited to see more of this "Context Engineering" in the coming months!

## Publication Information

- [The Agentic World](https://paragraph.com/@theagenticworld/): Publication homepage
- [All Posts](https://paragraph.com/@theagenticworld/): More posts from this publication
- [RSS Feed](https://api.paragraph.com/blogs/rss/@theagenticworld): Subscribe to updates