# Agent Skills

> 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.

- Identifier: PTL-0148
- Category: Agents & Orchestration
- Canonical URL: https://protologue.com/t/agent-skills/
- Also known as: skills, SKILL.md, progressive disclosure
- Introduced: 2025

## 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.

## Related terms

- [Context Engineering](https://protologue.com/t/context-engineering/)
- [AI Agent](https://protologue.com/t/ai-agent/)
- [Model Context Protocol](https://protologue.com/t/model-context-protocol/)
- [System Prompt](https://protologue.com/t/system-prompt/)

## Comparisons

- [Agent Skills vs Model Context Protocol](https://protologue.com/compare/agent-skills-vs-model-context-protocol/)

## Sources

- Anthropic (2025). Equipping agents for the real world with Agent Skills. https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills

## Cite this entry

Protologue. (2026). Agent Skills. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0148). https://protologue.com/t/agent-skills/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)