Claude Code custom slash commands and skills (SKILL.md)

• Personal: ~/.claude/skills/SKILL-NAME/SKILL.md loads in all your projects on this machine.
• Project: .claude/skills/SKILL-NAME/SKILL.md loads in sessions in this repository. Commit it so your team gets it too.
• Plugin: PLUGIN/skills/SKILL-NAME/SKILL.md is invoked as /plugin-name:skill-name.
• Legacy commands: .claude/commands/deploy.md and .claude/skills/deploy/SKILL.md both create /deploy. A file at .claude/commands/frontend/component.md becomes /frontend:component.
• If a skill and a .claude/commands/ file share a name, the skill wins. With the same name at more than one level, enterprise beats personal, and personal beats project.

Command files accept the same frontmatter as skills except name and paths. For new work, use skills, since they also support a folder of supporting files.

Frontmatter is YAML between --- markers at the top of SKILL.md. Every field is optional, but description is recommended so Claude knows when to use the skill. Unknown fields are ignored.

• name: the command name shown in the / menu. Defaults to the directory name.
• description: what the skill does and when to use it. If omitted, Claude uses the first non-empty line of the content.
• when_to_use: extra trigger context appended to the description.
• argument-hint and arguments: an autocomplete hint, and named positional arguments.
• disable-model-invocation: true means only you can invoke the skill.
• user-invocable: false means only Claude can invoke it.
• allowed-tools and disallowed-tools: tools pre-approved for, or removed from, the turn that invokes the skill.
• Also available: model, effort, context: fork, agent, hooks, paths and more; see the official reference table.

---
name: deploy
description: Deploy the application to production
disable-model-invocation: true
---

Deploy $ARGUMENTS to production:

1. Run the test suite
2. Build the application
3. Push to the deployment target
4. Verify the deployment succeeded

Whatever you type after the skill name replaces $ARGUMENTS. Use $ARGUMENTS[N] or the shorthand $N (counting from 0) for single positional arguments. Wrap a multi-word value in quotes to pass it as one argument. If no placeholder receives your input, Claude Code appends it to the end of the skill content.

---
name: migrate-component
description: Migrate a component from one language to another
argument-hint: [component] [from] [to]
---

Migrate the $0 component from $1 to $2.
Preserve all existing behavior and tests.

/migrate-component SearchBar JavaScript TypeScript

By default both you and Claude can invoke any skill. Start your message with /skill-name to run it directly. Skill descriptions stay in context so Claude can load the full skill when your request matches; the full content only loads when the skill is invoked.

• disable-model-invocation: true keeps the description out of context, so Claude can't invoke it on its own. Use this for actions with side effects, like deploys or commits.
• user-invocable: false hides the skill from the / menu but still lets Claude load it as background knowledge.
• paths limits automatic loading to when Claude works with files matching the glob patterns.
• If a skill never triggers, add the words people would naturally say to its description, or call it directly with /skill-name.