Demo wrap-up, main vs appendix context, and Skills as packaged procedures (PDF 169–171).
Context Engineering in Claude Skills Claude Skills are Anthropic’s mechanism for giving agents reusable, persistent abilities without overloading the model’s context window. They solve a practical issue in agent design: LLMs forget everything unless all instructions, examples and edge cases are restated each time. Skills package this information into small, self-contained units that Claude loads only when they’re relevant. This allows an agent to use hundreds of specialized workflows while keeping its active context lightweight. To make this scalable, Skills use a three-layer context management system that lets it use 100s of skills without hitting context limits.
Let’s understand how it works:
● Layer 1: Main Context - Always loaded, it contains the project configuration.
● Layer 2: Skill Metadata - Comprises only the YAML frontmatter, about 2-3 lines (< 200 tokens).
● Layer 3: Active Skill Context - SKILL.md files and associated documentation are loaded as needed. Supporting files like scripts and templates aren’t pre-loaded but accessed directly when in use, consuming zero tokens. This architecture supports hundreds of skills without breaching context limits. Now let’s zoom into the main ideas behind Skills, because understanding what they are clarifies why this 3-layer system matters.
Skills as SOPs for Agents Think of a Skill as a packaged procedure - a complete, reusable workflow that teaches the agent how to perform a task with consistency. Instead of re-explaining steps, examples, constraints, and edge cases every time, you define the workflow once and reuse it forever. It’s the AI equivalent of an operating manual: structured, repeatable, and self-contained. Anatomy of a Skill A skill is simply a folder, but what it contains is carefully designed:
● A skill.md file with two layers of context:
○ YAML Front Matter: a tiny descriptor Claude uses to decide when the skill is relevant.
○ Skill Body: the detailed instructions, workflows, examples, and guidance used during execution.
● Optional supporting files such as scripts, templates or reference docs.
These aren’t loaded into context, they’re fetched only when the agent needs them. This separation lets Claude stay lightweight until a specific skill is activated. How Skills Fit Into the Agent Architecture Skills don’t replace Projects, Subagents or MCP - they complement them:
● Projects organize your workspace.
● MCP connects Claude to tools and external services.
● Subagents handle delegated reasoning.
● Skills package the reusable expertise that all of them can rely on.
Each solves a different layer of the agent problem, and skills serve as the procedural knowledge base.
Building Your Own Skills The creation process is straightforward: 1. Identify a workflow you repeat constantly. 2. Create a skill folder and add a skill.md file. 3. Write the YAML front matter + full markdown instructions. 4. Add any scripts, examples, or supporting resources. 5. Zip the folder and upload it in Claude’s capabilities. Claude Desktop even includes a “Skill Creator” skill that helps generate the structure for you.