Ux Microcopy logo

Ux Microcopy

Organization
Uxcel-Lab
ux-microcopy

Write or improve UX microcopy — button labels, error and empty states, tooltips, form labels, notifications, and confirmations — so it's clear, concise, action-oriented, and on-voice. Trigger when asked to write microcopy, improve a button label or error message, write copy for a flow, or make interface copy clearer or friendlier.

Overview

PublisherUxcel-Lab
Repositoryproduct-skills
Skill nameux-microcopy
Stars
35
Forks
8
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Uxcel-Lab on GitHub. Read the source before you install it.

Installation

Install the Ux Microcopy AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Uxcel-Lab/product-skills/tree/main/ux/foundations/microcopy
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Uxcel-Lab/product-skills.git /tmp/product-skills
mkdir -p .claude/skills
cp -r /tmp/product-skills/ux/foundations/microcopy .claude/skills/ux-microcopy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ux Microcopy in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ux Microcopy on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ux Microcopy is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

UX Microcopy Skill

How this skill behaves (read first)

This is a generative skill. Claude's default UX copy tends to be verbose, clever, or generic ("Oops! Something went wrong", "Submit", "Are you sure?"). Good microcopy is the opposite: plain, specific, and quietly helpful. The expressive part — tone — is context-dependent, so this skill gates:

  1. Establish voice, audience, and the moment — tone that's right for a celebratory success state is wrong for a payment error.
  2. Apply the always-true core — clarity, concision, action-orientation, consistency, and inclusive/accessible language hold for all copy.
  3. Choose tone deliberately — pick the register for the brand and the specific moment; don't default to jokey or to robotic.

Then hand off to the audits: the companion ux-microcopy-audit, plus accessibility (copy that screen readers and all users can follow) and dark-patterns (copy must persuade honestly, never manipulate).


Step 0 — Establish context before writing

  • Brand voice — the product's consistent personality (playful vs. formal, warm vs. neutral).
  • Audience & vocabulary — use the words users use ("rides", not "commutes"); tech-savviness and reading level.
  • The moment — celebratory, routine, sensitive (payment/security), or error/recovery? This sets the tone.
  • Locale — language(s) and platform conventions ("click" desktop vs. "tap" mobile); localization beyond literal translation.

State assumptions if proceeding without answers.


The always-apply core (true for any microcopy)

  • Plain, simple language. Write for the widest range of users; no jargon or high-register vocabulary unless the audience expects it. Read it aloud to test.
  • Concise. Say it in as few words as keep the meaning; ~16% read word-by-word, the rest scan. Cut filler.
  • Action-based and specific. Labels are verbs (+ nouns) describing the outcome — "Get Pro", "Delete file", "Unmute now" — never generic "Yes/No/OK/Submit". A great CTA also conveys the benefit.
  • Tell users what's happening and what's next. Reduce uncertainty: where they are, what an action does, how long it takes.
  • Consistent terminology. One term per concept across the whole product ("scheduling" everywhere, not "booking" elsewhere); consistent with platform conventions.
  • Human numbers & dates. "Tomorrow" not "April 1"; "8:45 AM" not "a quarter to nine"; concrete numbers/social proof over vague "many".
  • Inclusive & accessible. Gender-neutral pronouns (they/them); descriptive link text ("Read more about pricing", not "More"); microcopy as live text, not baked into images; persistent labels (not placeholder-only); acknowledge completed actions.
  • Honest, never manipulative. No confirmshaming, fake urgency, or guilt (→ dark-patterns).

Tone — the gated decision (pick per brand + moment)

Choose the register intentionally; the same message reads differently in each. Don't default to one.

ToneUse forCaution
Playful / wittyLow-stakes moments, light errors, easter eggsKnow your audience; never at the cost of clarity
Enthusiastic / praisingEncouragement during effort; celebrating an achievementDon't over-cheer routine actions
Warm / friendlyWelcomes, everyday guidance (first names, contractions, "you")Can feel flippant in serious moments
ConfidentSensitive moments — payments, security, dataAvoid hedging ("maybe", "try to")
Respectful / formalProfessional, regulated, or sensitive contextsCan read as dry — still be clear
Honest / directPermission/data requestsActive voice; don't mask intent
ConciseDense UI, labels, mobileDon't strip needed context

Rule: match tone to the moment. A payment error wants confident + clear, not a joke.


Microcopy patterns (quick reference)

  • Buttons: verb + outcome; descriptive over generic ("Unmute now" > "Yes").
  • Errors/alerts: explicit (what happened) + constructive (how to fix) + plain language; place next to the problem; polite, no blame/ALL-CAPS.
  • Labels: specific verbs+nouns, not "OK/Start/Finish".
  • Placeholders: hints/examples only — never the sole label (they vanish on input).
  • Tooltips: add genuine value; never state the obvious.
  • Notifications/push: ask "how does this help the user?"; useful, not intrusive.
  • Empty/success states: empty = teach the first action; success = confirm + positive moment.

Validate the result (orchestration)

Hand-offs name each lens by its installable skill name. Invoke one only if that skill is installed; if it isn't, this skill's own core already carries these rules — proceed without it rather than blocking.

After writing or revising copy, hand the result to the audit lenses rather than declaring it done. These are candidate lenses — posture is set by docs/orchestration-policy.md, or route the whole thing through ux-design-review. Here, microcopy and dark-patterns are Tier A (auto-run); accessibility is Tier B (offered) — under an existing design system accessibility narrows to usage. If the user invoked this skill for one specific thing, respect that scope.

  • ux-microcopy-audit (Tier A) — the companion audit: clarity, action-orientation, consistency, tone fit across the flow.
  • ux-accessibility-audit (Tier B — offer; narrow under a design system) — plain language, descriptive links, live text, persistent labels, screen-reader acknowledgments.
  • ux-dark-patterns-audit (Tier A) — copy persuades honestly: no confirmshaming, manufactured urgency, or guilt.

If an audit flags it, resolve toward the core: plainer, more specific, on-the-right-tone.


Common do/don't patterns

❌ Don't✅ Do
"Oops! Something went wrong.""We couldn't save your changes. Check your connection and try again."
"Submit" / "OK" / "Yes"Verb + outcome: "Create account", "Delete file"
Jargon / high-register wordsPlain language users actually use
Same tone everywhereMatch tone to brand and the moment
Joke on a payment/security errorConfident, clear, reassuring copy
"April 1" / "a quarter to nine""Tomorrow" / "8:45 AM"
"Register" here, "Join free" thereOne consistent term per concept
"Click More" link / generic labelsDescriptive: "Read more about pricing"
Text baked into an imageLive, selectable text
Confirmshaming the opt-outNeutral, honest dismissals (→ dark-patterns)

Source lessons (Uxcel)

Frequently asked questions

What does the Ux Microcopy AI skill do?

Write or improve UX microcopy — button labels, error and empty states, tooltips, form labels, notifications, and confirmations — so it's clear, concise, action-oriented, and on-voice. Trigger when asked to write microcopy, improve a button label or error message, write copy for a flow, or make interface copy clearer or friendlier.

Why use Ux Microcopy on TypingMind?

Because you install it once and use it with any model. Ux Microcopy is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ux Microcopy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Uxcel-Lab/product-skills/tree/main/ux/foundations/microcopy. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ux Microcopy?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ux Microcopy?

As many as you like. As long as a model supports skills, you can use Ux Microcopy with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ux Microcopy AI skill free?

Yes. It is published on GitHub by Uxcel-Lab under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇