Agent Skills
In one line
Agent Skills are bundled capability packages that let an agent do a specific job well — Anthropic's Skills feature is the canonical example.
Going deeper
A Skill is a bundle — prompts, tools, reference docs, execution procedures — packaged as one capability. 'Build a slide deck', 'analyse a financial statement', 'write copy in our brand voice' — when the entire context for one job is bundled together, the agent no longer needs to be re-briefed every time. Anthropic launched Skills inside Claude on October 16, 2025 and opened it as a cross-platform standard on December 18, 2025; Cursor, Goose and VS Code adopted shortly after, and the term stuck.
The interesting angle for marketers is seeing Skills as reusable marketing assets. Bottle the brand voice, the copy-writing procedure and the campaign analysis routine into Skills, and anyone on the team can run the agent at the same quality bar. In practice it is closer to 'SOPs for the AI era' than to a developer-only feature.
Skills overlap with MCP and tool use, which makes them easy to confuse. The cleanest read is that MCP is the standard for calling tools, while a Skill is a packaged context, tool set and document bundle aimed at one job. They are usually complementary, not competing.
Sources
Related terms
MCP
MCP (Model Context Protocol) is the open standard introduced by Anthropic for connecting LLMs to external tools and data sources in a consistent way.
AI AgentTool Use
Tool use is an LLM calling external APIs, calculators or search systems directly to ground its answers — the foundational behaviour of every agent.
LLMClaude
Claude is Anthropic's LLM family, known for safety alignment, long-context handling and strong tool use — widely adopted in enterprise and developer settings.
AI AgentAI Agent
An AI agent is an LLM-driven system that takes a goal, plans the steps, calls the tools it needs and runs the task end-to-end with limited human input.
LLMPrompt Engineering
Prompt engineering is the practice of crafting inputs that steer an LLM toward better outputs — a way to dramatically change result quality without retraining the model.
How does your brand show up in AI answers?
Villion measures how your brand appears across ChatGPT, Perplexity and AI Overviews, then automates the work that lifts citation rate and share of voice.
Get a free audit