Agent skills guide

What Are AI Agent Skills?

Learn how agent skills package reusable instructions, references, guardrails, and tests for Claude Code, Codex, and Cursor—and when to use one.

Published July 22, 2026 · Updated July 22, 2026

An AI agent skill is a reusable package of instructions and supporting material that teaches a coding agent when and how to perform a particular workflow. Instead of pasting the same long prompt into every conversation, you give the agent a durable procedure it can discover when relevant.

A skill is more than a saved prompt

A prompt usually handles one request in one conversation. A well-formed skill describes the requests that should trigger it, the inputs it needs, the ordered workflow, expected outputs, safety boundaries, and what to do when a prerequisite is missing. References and examples can live beside the main instructions without occupying every conversation by default.

The common anatomy

Skills, rules, tools, and agents solve different problems

MechanismBest useKey distinction
SkillReusable workflow or specialized knowledgeLoaded when the task calls for it
Project rulesAlways-relevant repository conventionsPresent across ordinary project work
Tool or MCP serverAccessing an external capability or systemProvides an action, not the complete procedure
SubagentDelegated work with separate contextA worker, not a reusable instruction package

Claude Code's official feature overview makes a similar distinction: skills provide reusable knowledge and workflows, while MCP connects tools and subagents run isolated work. See the official comparison.

How XSkills targets different coding agents

XSkills compiles separate native packages for Claude Code, Codex, and Cursor. The shared workflow and evidence remain consistent, while the install root and harness-specific metadata follow the selected destination. A Claude Code package installs under ~/.claude/skills; Codex uses ~/.agents/skills; Cursor uses ~/.cursor/skills.

Cross-harness output is not produced by blindly copying a folder. XSkills validates that a package does not contain metadata intended for another agent and records the target in its manifest before delivery.

When a skill is worth keeping

Create a skill when the workflow is repeated, benefits from consistent sequencing, or contains constraints the agent should not rediscover every time. Keep a one-off answer as a prompt when it is unlikely to recur. Avoid turning vague inspiration into a skill: durable instructions amplify both good assumptions and bad ones.

The safest workflow preserves the source, tests the activation boundary, and requires a person to approve the exact version that will be installed. That is the model used by XSkills.

Next, read how XSkills turns X bookmarks into Claude Code skillsor inspect the review and installation safeguards.