# Agent Skills

> Agent Skills are reusable procedures packaged as folders with a SKILL.md file — loaded by an AI agent on demand when a task matches, now an open standard.

**Agent Skills are reusable procedures packaged as a folder containing a SKILL.md file — YAML frontmatter that tells the agent when the skill applies, plus a Markdown body of instructions it follows once loaded.**

The design solves the standing tension between capability and [context](/glossary/context-window): an agent that carries every procedure in its [system prompt](/glossary/system-prompt) pays for all of them on every request. Skills invert that with progressive disclosure — at session start only each skill's name and description load; the full body loads when a task matches; bundled scripts and references load only when the instructions reach for them. The description doubles as the routing signal, which is why writing it well is [most of the craft](/guides/skills/claude-code-skills-best-practices).

Skills began as a Claude Code feature and became a portable format: the same SKILL.md runs on claude.ai, on the Claude API via `/v1/skills` and code execution, and — since Anthropic published Agent Skills as an open standard in December 2025 — in dozens of third-party tools. The [full guide](/guides/skills/what-are-claude-skills) covers the concept; the [SKILL.md reference](/guides/skills/skill-md-reference) documents every field.

---

_Source: https://agentscamp.com/glossary/agent-skills — Term on AgentsCamp._