ux-copy

A guide for writing and reviewing the short words people see in software interfaces, such as button labels, error messages, empty screens, confirmations, and onboarding text.

In plain words
What is it for?
Use it to write or review button text, error messages, empty states, confirmation dialogs, calls to action, and onboarding copy.
Why use it?
It helps make interface messages clear, concise, consistent, and useful when the right wording is difficult to choose.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/anthropics/knowledge-work-plugins/ux-copy
Any agent
npx skills add anthropics/knowledge-work-plugins --skill ux-copy
Clone the repo
git clone --depth 1 https://github.com/anthropics/knowledge-work-plugins

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.00830
Opus 5 $0.00031 $0.00415
Sonnet 5 $0.00012 $0.00166
Haiku 4.5 $0.00006 $0.00083

Measured 3d ago against content hash d46a00a62ec6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-copy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • ux-copy — 100% identical, 0 lines differ
  • ux-copy-th — 91% identical, 10 lines differ
design/skills/ux-copy/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/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

  1. Clear: Say exactly what you mean. No jargon, no ambiguity.
  2. Concise: Use the fewest words that convey the full meaning.
  3. Consistent: Same terms for the same things everywhere.
  4. Useful: Every word should help the user accomplish their goal.
  5. 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]

Read the full file on GitHub · 108 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 108 lines · 62 tokens per session scan A d46a00a62ec6

Subscribe to this mod's changes

ux-copy is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 830 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens