Agent skill
ux-copy
Write or review UX copy — microcopy, error messages, empty states, CTAs. Trigger with "write copy for", "what should this button say?", "review this error message", or when naming a CTA, wording a confirmation dialog, filling an empty state, or writing onboarding text.
Install this agent skill to your Project
npx add-skill https://github.com/anthropics/knowledge-work-plugins/tree/main/design/skills/ux-copy
SKILL.md
/ux-copy
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.
Usage
/ux-copy $ARGUMENTS
What I Need From You
- Context: What screen, flow, or feature?
- User state: What is the user trying to do? How are they feeling?
- Tone: Formal, friendly, playful, reassuring?
- Constraints: Character limits, platform guidelines?
Principles
- Clear: Say exactly what you mean. No jargon, no ambiguity.
- Concise: Use the fewest words that convey the full meaning.
- Consistent: Same terms for the same things everywhere.
- Useful: Every word should help the user accomplish their goal.
- Human: Write like a helpful person, not a robot.
Copy Patterns
CTAs
- Start with a verb: "Start free trial", "Save changes", "Download report"
- Be specific: "Create account" not "Submit"
- Match the outcome to the label
Error Messages
Structure: What happened + Why + How to fix
- "Payment declined. Your card was declined by your bank. Try a different card or contact your bank."
Empty States
Structure: What this is + Why it's empty + How to start
- "No projects yet. Create your first project to start collaborating with your team."
Confirmation Dialogs
- Make the action clear: "Delete 3 files?" not "Are you sure?"
- Describe consequences: "This can't be undone"
- Label buttons with the action: "Delete files" / "Keep files" not "OK" / "Cancel"
Tooltips
- Concise, helpful, never obvious
Loading States
- Set expectations, reduce anxiety
Onboarding
- Progressive disclosure, one concept at a time
Voice and Tone
Adapt tone to context:
- Success: Celebratory but not over the top
- Error: Empathetic and helpful
- Warning: Clear and actionable
- Neutral: Informative and concise
Output
## 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 Connectors Available
If ~~knowledge base is connected:
- Pull your brand voice guidelines and content style guide
- Check for existing copy patterns and terminology standards
If ~~design tool is connected:
- View the screen context in Figma to understand the full user flow
- Check character limits and layout constraints from the design
Tips
- Be specific about context — "Error message when payment fails" is better than "error message."
- Share your brand voice — "We're professional but warm" helps me match your tone.
- Consider the user's emotional state — Error messages need empathy. Success messages can celebrate.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
anthropics/knowledge-work-plugins
view-pdf
Interactive PDF viewer. Use when the user wants to open, show, or view a PDF and collaborate on it visually — annotate, highlight, stamp, fill form fields, place signature/initials, or review markup together. Not for summarization or text extraction (use native Read instead).
anthropics/knowledge-work-plugins
signature-request
Prepare and route a document for e-signature — run a pre-signature checklist, configure signing order, and send for execution. Use when a contract is finalized and ready to sign, when verifying entity names, exhibits, and signature blocks before sending, or when setting up an envelope with sequential or parallel signers.
anthropics/knowledge-work-plugins
brief
Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.
anthropics/knowledge-work-plugins
legal-risk-assessment
Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.
anthropics/knowledge-work-plugins
triage-nda
Rapidly triage an incoming NDA and classify it as GREEN (standard approval), YELLOW (counsel review), or RED (full legal review). Use when a new NDA arrives from sales or business development, when screening for embedded non-solicits, non-competes, or missing carveouts, or when deciding whether an NDA can be signed under standard delegation.
anthropics/knowledge-work-plugins
compliance-check
Run a compliance check on a proposed action, product feature, or business initiative, surfacing applicable regulations, required approvals, and risk areas. Use when launching a feature that touches personal data, when marketing or product proposes something with regulatory implications, or when you need to know which approvals and jurisdictional requirements apply before proceeding.
Didn't find tool you were looking for?