
This does the tedious work of writing interface microcopy: button labels, error messages, empty states, confirmation dialogs, all the little text that makes or breaks user experience. It follows solid UX writing principles (clear, concise, human) and gives you structured output with a main recommendation plus alternatives in a comparison table. The guidance is practical, like structuring error messages as "what happened + why + how to fix" or making CTAs start with verbs. If you have design tools or a knowledge base connected, it can pull brand voice guidelines and check actual layout constraints. Honestly, this is most useful when you're stuck on how to phrase something or need to quickly generate options that don't sound robotic.
$ npx -y skills add anthropics/knowledge-work-plugins --skill ux-copy --agent claude-codeInstalls into .claude/skills of the current project.
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Write or review UX copy for any interface context.
/ux-copy $ARGUMENTS
Structure: What happened + Why + How to fix
Structure: What this is + Why it's empty + How to start
Adapt tone to context:
## UX Copy: [Context]
### Recommended Copy
**[Element]**: [Copy]
### Alternatives
| Option | Copy | Tone | Best For |
|--------|------|------|----------|
| A | [Copy] | [Tone] | [When to use] |
| B | [Copy] | [Tone] | [When to use] |
| C | [Copy] | [Tone] | [When to use] |
### Rationale
[Why this copy works — user context, clarity, action-orientation]
### Localization Notes
[Anything translators should know — idioms to avoid, character expansion, cultural context]
If ~~knowledge base is connected:
If ~~design tool is connected:
Sponsors