Skill (Claude / GPT)

A Skill is a packaged capability — instructions + tools + files — that an AI assistant can selectively load to handle a specific task type, distinct from a Custom GPT in distribution and surface.

Anthropic introduced Skills for Claude in 2024 as a reusable unit of capability — a system prompt + scripts + reference files — that Claude loads when relevant to the conversation. OpenAI's Custom GPTs serve a similar purpose but distribute publicly via the GPT Store. By 2026 both are widely used for internal team workflows and shareable productized assistants. Skills are particularly strong for engineering teams that want versioned, code-reviewed assistant behaviour rather than chat-room prompt sharing.

When to use skill (claude / gpt)

• Internal team workflows that need reusable assistant behaviour.
• Productizing a recurring task as a packaged capability.

Common mistakes

• Skill that's too broad — loses focus and quality.
• Skipping eval on the skill — quality drifts with model updates.

FAQ

Related terms

• System message — A system message is the highest-priority instruction message in a chat-style API call — used to set role, constraints, and behaviour for the entire conversation.
• AI agent — An AI agent is a system where a language model autonomously plans and executes a sequence of tool calls to accomplish a goal.
• MCP (Model Context Protocol) — MCP is an open protocol from Anthropic that standardises how language models connect to external tools, data sources, and prompts — the USB-C of LLM integrations.
• Tool use (LLM) — Tool use is the umbrella term for any LLM mechanism that lets the model invoke external functions, APIs, or services — function calling, code interpreter, MCP servers, browser actions.

Last updated: 2026-06-01. Raw markdown: https://promtable.com/glossary/skill.md.