Skip to main content
Basics

What Are Claude Agent Skills?

Skills are reusable folders of instructions (a SKILL.md file) that teach an AI agent how to do a task well, loaded only when needed. How they work and why.

Updated August 21, 2026 · 6 min read

Anyone who has used Claude for some time will have retyped the same instructions: format a spreadsheet, follow a code-review checklist, or build a deck to a house style. Agent Skills exist so that those instructions need not be restated. This guide explains what a skill is, how the SKILL.md format works, and how skills differ from prompts, plugins, and MCP.

A skill is a folder with a SKILL.md file

A skill is a directory containing a single SKILL.md file. That file has two parts:

  • YAML frontmatter — a short block at the top with a name and, most importantly, a description. The description is the trigger: it tells the model when to reach for this skill.
  • Markdown instructions — everything below the frontmatter: the actual how-to knowledge, written as if you were briefing a capable new teammate.

A minimal skill looks like this:

---
name: excel-reports
description: Create formatted .xlsx spreadsheets with working formulas,
  pivot tables and charts. Use when the user asks for an Excel file,
  a spreadsheet, or a financial model.
---

# Creating Excel reports

When building a spreadsheet:
1. Put raw data on a "Data" sheet and analysis on a "Summary" sheet.
2. Use real formulas (SUMIF, XLOOKUP) so numbers stay live.
3. Format headers bold, freeze the top row, add a title.
...

The description is the whole game

The single biggest factor in whether a skill helps you is its description. Claude reads only the name and description of every installed skill up front — the full instructions are loaded on demand. So the description has to clearly name the situation the skill is for, not just the topic. “Helps with documents” is useless; “Fills, extracts and summarizes PDF forms; use when the user uploads a PDF or asks to extract a table” is what makes the skill fire at the right moment.

Progressive disclosure: why skills stay cheap

Skills are designed around progressive disclosure. Only the name and description sit in context at all times (a few tokens each). When your request matches, Claude pulls in the full SKILL.md body. If that body points to extra files — a reference.md, a script, a template — those are read only if needed. The result: you can have dozens of skills installed without paying a token cost for the ones you are not using right now.

Skills vs prompts vs plugins vs MCP

These four things are easy to confuse. Here is the short version:

ConceptWhat it isBest for
PromptA one-off instruction you type in chatA single task, right now
SkillReusable know-how (a SKILL.md folder) loaded on demandDoing a task the same good way every time
PluginA distributable bundle that can package skills, commands and settingsSharing and installing a set of capabilities
MCPA protocol that gives the model access to external tools and dataConnecting to APIs, databases and services

They are complementary, not competing. A common pattern: MCP gives Claude access to your database, and a skill teaches it the right way to query that database. Want to build one of your own? See how to create a Claude skill, or if a skill is misbehaving, jump to why skills stop working.

Official vs community skills

Official skills come from Anthropic’s own repository — the built-in document skills (PDF, Excel, Word, PowerPoint), plus tools like the Skill Creator and MCP Builder. Community skills are written by developers and teams solving their own problems. Both can be excellent; the difference is provenance and testing. OpxSkills rates every skill with an OpxScore (documentation, practicality, evidence, and source trust) and marks whether that score is reviewed or provisional, so you can tell them apart at a glance.

Who should use skills?

Anyone who does a task with Claude more than once. Writers package their house style; engineers encode their review checklist and testing workflow; analysts save their reporting format. Good first skills are the built-in document ones and the Skill Creator, which scaffolds new skills for you. Browse by what you do in the Coding, Writing, and Analysis categories, or see every skill that works with Claude.

Frequently asked questions

What is a Claude Agent Skill?

A skill is a folder containing a SKILL.md file — YAML frontmatter (a name and a description) plus Markdown instructions — that teaches an AI agent how to perform a specific task. Claude loads the instructions only when the task comes up, so skills add capability without bloating the context window.

What is the difference between a skill and a prompt?

A prompt is a one-off instruction you type. A skill is a reusable, versioned package of instructions (plus optional scripts and reference files) that the model pulls in automatically whenever its description matches what you are doing. Think of a prompt as a note and a skill as a saved recipe.

Are skills only for Claude?

Skills started with Claude (Claude Code, Claude Desktop, and the API), but the SKILL.md format is being adopted more broadly — Codex CLI, Gemini CLI, Copilot, Cursor and others are converging on the same file-based, progressive-disclosure pattern. OpxSkills tracks which models each skill is compatible with.

Do I need to write code to use a skill?

No. Installing a skill is just placing a folder in the right directory (or installing a plugin that bundles it). Many skills contain no code at all — only instructions. Some bundle helper scripts, but you do not have to touch them.

Skills to begin with

Analysis & Researchintermediate

Skill Creator

Scaffold a new AI agent skill from a plain-language job description: folder, SKILL.md frontmatter, trigger description, and a first draft of...

76OpxScoreProvisional

Model fit

ClaudeChatGPTGemini+5
197.7K65
View
Coding & Developmentintermediate

Mcp Builder

Design and implement Model Context Protocol servers so an agent can call external tools with typed schemas instead of stuffing API docs into...

67OpxScoreProvisional

Model fit

Model fit pending
197.7K66
View
Writing & Contentintermediate

Pdf

Read, fill, extract, and generate PDF documents from an agent session — forms, reports, and print-ready files rather than markdown-only outp...

75OpxScoreProvisional

Model fit

Model fit pending
197.7K59
View
Coding & Developmentintermediate

Xlsx

Build and analyze Excel (.xlsx) workbooks — formulas, multiple sheets, and tabular exports — from an agent instead of CSV paste.

67OpxScoreProvisional

Model fit

Model fit pending
197.7K51
View
Creativity & Designintermediate

Pptx

Generate and edit PowerPoint (.pptx) decks with real slides, not markdown pretending to be a presentation.

75OpxScoreProvisional

Model fit

Model fit pending
197.7K49
View
Writing & Contentintermediate

Docx

Create and edit Microsoft Word (.docx) files with headings, tables, and tracked-change-friendly structure from an agent workflow.

75OpxScoreProvisional

Model fit

Model fit pending
197.7K60
View

Browse all skills in the directory →

More guides

Weekly digest

Receive published digests of new listings and catalogue updates. Confirm your email to join.

Double opt-in required. You may unsubscribe at any time.