Skip to main content
A skill.md is plain Markdown with two parts: a small metadata header and a structured body. The header makes the skill discoverable and installable; the body is what your agent reads.

​
Metadata header

The header is YAML frontmatter describing the skill at a glance: 
---
title: "Stripe API"
description: "Payments, Checkout, and webhooks for the Stripe REST API."
source: "https://docs.stripe.com"
mode: "api"
tags: ["payments", "rest", "webhooks"]
---
FieldPurpose
titleHuman-readable name shown in the app and editor
descriptionOne-line summary used in search and listings
sourceThe URL the skill was generated from
modeThe generation mode used
tagsTopics for discovery and filtering

​
Structured body

Below the header is the content your agent consumes — organized into the sections that matter for the source type. The exact headings depend on the mode, but the goal is constant: everything the agent needs, nothing it doesn’t.
A short orientation: what the source is, who it’s for, and the core mental model.
The vocabulary and ideas an agent must hold to reason about the source correctly.
The concrete details — endpoints, components, tokens, or APIs — depending on mode.
Representative snippets that show real usage, not just signatures.
Edge cases, limits, and footguns worth flagging before the agent hits them.

​
Designed for agents

Token-aware

Distilled rather than dumped, so it fits a context window with room to spare.

Self-contained

One file your agent can read start to finish without fetching anything else.