{
  "id": "agent-skills",
  "code": "PTL-0148",
  "term": "Agent Skills",
  "aliases": [
    "skills",
    "SKILL.md",
    "progressive disclosure"
  ],
  "category": "agents",
  "definition": "Agent skills are packaged folders of instructions, scripts, and reference files, each anchored by a SKILL.md file with a name and description, that an agent loads only when a task calls for them.",
  "description": "Only each skill's short description sits in the agent's context at startup. The full instructions are read when relevant, and supporting files are opened only if needed, a pattern called progressive disclosure. This lets an agent carry many specialized procedures without filling its context window, and lets organizations package their own workflows for reuse.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "context-engineering",
    "ai-agent",
    "model-context-protocol",
    "system-prompt"
  ],
  "introduced": 2025,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Equipping agents for the real world with Agent Skills",
      "authors": "Anthropic",
      "year": 2025,
      "url": "https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills"
    }
  ],
  "url": "https://protologue.com/t/agent-skills/",
  "citation": "Protologue. (2026). Agent Skills. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0148). https://protologue.com/t/agent-skills/"
}