S Claude Has Skills Tools

Claude Code

Claude Code Skills: Installation and Invocation

Where Claude Code skills live, how project and personal skills differ, and how to keep skill usage scoped.

Updated 2026-07-06 8 min T4 source-backed

Primary source takeaway: Claude Code documents project, personal, and plugin skill locations separately, so scope is part of the design.

Three scopes

Use project skills when the workflow belongs to a repository. They should live under .claude/skills so the team can review changes, version them, and keep task behavior close to the code or documentation it affects.

Use personal skills for private workflows you want across projects. These belong in your user-level Claude configuration, not in a shared repository. Use plugin-distributed skills when the skill comes from an installed Claude Code plugin or marketplace source.

When to create a project skill

Create a project skill when the repository has a repeated local practice: release checks, architecture review, design QA, data migration rehearsal, support-log triage, or documentation conversion. The skill should encode the project-specific rules that generic Claude Code guidance cannot know.

Do not use a project skill as a dumping ground for every team preference. Stable repository facts may belong in project instructions; specialized procedures with supporting files belong in skills.

Invocation and triggering

Users can mention a skill by name, but the stronger design is to make the description clear enough that the agent can select it when the task matches. The description should say when to use the skill, not just what the skill is called.

If a skill fails to trigger, revise the description before adding paragraphs of instructions. Trigger matching depends on the skill being described in the same language users naturally use for the task.

Version control and review

Treat project skills like code-adjacent configuration. Review diffs, avoid hidden network behavior, keep scripts executable and small, and document dependencies. A skill that changes deploy behavior deserves the same scrutiny as a shell script in the repo.

For more general Claude Code engineering practice, use a dedicated Claude Code guide rather than overloading this site. This page is intentionally about skill packaging and scope.

FAQ

Is this site affiliated with Anthropic?

No. Claude Has Skills is an independent editorial guide. It links to Anthropic and Agent Skills primary sources so readers can verify product details directly.

Does a skill replace normal prompting?

No. A skill packages repeatable instructions and resources so the agent can load them when a task matches. The user still asks for a task, and the agent still decides what to read and run.

Should I commit project skills?

Usually yes, if they define shared repository workflows. Committing them makes review and team alignment possible.

Can a Claude Code plugin provide skills?

Yes. Claude Code can receive skills from installed plugin sources, which should still be reviewed like any other dependency.

Primary Sources

Claude Code Skills docs

Anthropic Docs

Canonical source for Claude Code skill locations, types, and runtime behavior.