# Agent Skills: How is it different from command and other tools?

DevFeed: [Agent Skills: How is it different from command and other tools?](<https://devfeed.tech/articles/agent-skills-how-is-it-different-from-command-and-other-tools-25230.md>)

Original publisher: [Read original article](<https://kau.sh/blog/claude-skills/>)

Author: Kaushik Gopal

Published: 2025-10-20T11:45:11Z

Content type: opinion

Language: en

Sources: [Kaushik Gopal's Site](<https://devfeed.tech/sources/kaushik-gopal-s-site.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Markdown](<https://devfeed.tech/topics/markdown.md>), [YAML](<https://devfeed.tech/topics/yaml.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [ai](<https://devfeed.tech/tags/ai.md>), [claude](<https://devfeed.tech/tags/claude.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [yaml](<https://devfeed.tech/tags/yaml.md>)

## AI overview

This commentary examines Anthropic's Claude Skills and argues that their important innovation is progressive disclosure: Claude scans lightweight YAML metadata, builds a capability index, and loads full skill content only when relevant. It compares this approach with AGENTS.md, nested instructions, slash commands, and MCPs, emphasizing improved context and token efficiency.

## Source excerpt

Anthropic announced Claude Skills and my first reaction was: "So what?" We already have AGENTS.md, slash commands, nested instructions, or even MCPs. What's new here? But if Simon W thinks this is a big deal, then pelicans be damned; I must be missing something. So I dissected every word of Anthropic's eng. blog post to find what I missed. I don't think the innovation is what Skills does or achieves, but rather how it does it that's super interesting. This continues their push on context engineering as the next frontier. Addendum Skills has been out for sometime and Anthropic has even made it an open standard. Make sure to read the addedum at the end of this post, where I share some newer realizations I've had since first writing it. Skills and how it works # Skills are simple markdown files with YAML frontmatter. But what makes them different is the idea of progressive disclosure: Progressive disclosure is the core design principle that makes Agent Skills flexible and scalable. Like a well-organized manual that starts with a table of contents, then specific chapters, and finally a detailed appendix, skills let Claude load information only as needed: So here's how it works: Scan at startup: Claude scans available Skills and reads only their YAML descriptions (name, summary, when to use) Build lightweight index: This creates a catalog of capabilities (with minimal token cost); so think dozens of tokens per skill Load on demand: The full content of a Skill only gets injected into context when Claude's reasoning determines it's relevant to the current task This dynamic context loading mechanism is very token efficient; that's the interesting development here. In this token-starved AI economy, that's 🤑. Other solutions aren't as good in this specific way. Why the alternatives aren't as good # AGENTS.md (monolithic) ## ✓ Auto-discovered and loaded ✗ Static: all context loaded upfront (bloats context window at scale) Why not throw everything into AGENTS.md? You could add