ux-writing
Create user-centered, accessible interface copy (microcopy) for digital products including buttons, labels, error messages, notifications, forms, onboarding, empty states, success messages, and help text. Use when writing or editing any text that appears in apps, websites, or software interfaces, designing conversational flows, establishing voice and tone guidelines, auditing product content for consistency and usability, reviewing UI strings, or improving existing interface copy. Applies UX writing best practices based on four quality standards — purposeful, concise, conversational, and clear. Includes accessibility guidelines, research-backed benchmarks (sentence length, comprehension rates, reading levels), expanded error patterns, tone adaptation frameworks, and comprehensive reference materials.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/content-designer-ux-writing-skill)HTML
<a href="/listings/content-designer-ux-writing-skill"><img src="/api/listings/content-designer-ux-writing-skill/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
What You Need
This skill works with **Claude Desktop**, **Claude Code**, **Codex** (CLI and IDE extensions), and **Cursor**. Install it with the [skills CLI](https://skills.sh/docs/cli) — no manual download or file copying required.
**Note:** This skill works with Codex CLI/IDE, not ChatGPT. ChatGPT cannot install or use skills.
Install with the Skills CLI
Run this command in your terminal:
npx skills add content-designer/ux-writing-skill
The CLI downloads the skill and configures it automatically for your agent. Restart your agent or IDE after installation.
**Verify it's working** by asking your agent:
Write an error message for when a payment fails
Your agent will apply UX writing best practices and produce a clear, empathetic error message.
For Teams: Project Installation
Want your whole team to use this skill automatically? Run the CLI from your project root:
npx skills add content-designer/ux-writing-skill
Then commit the installed skill files to your repository. Teammates get the skill when they pull the code.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 417 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- ---
- name: ux-writing
- description: Create user-centered, accessible interface copy (microcopy) for digital products including buttons, labels, error messages, notifications, forms, onboarding, empty states, success messages, and help text. Use when writing or editing any text that appears in apps, websites, or software interfaces, designing conversational flows, establishing voice and tone guidelines, auditing product content for consistency and usability, reviewing UI strings, or improving existing interface copy. Applies UX writing best practices based on four quality standards — purposeful, concise, conversational, and clear. Includes accessibility guidelines, research-backed benchmarks (sentence length, comprehension rates, reading levels), expanded error patterns, tone adaptation frameworks, and comprehensive reference materials.
- ---
- # UX Writing
- Write clear, concise, user-centered interface copy (UX text/microcopy) for digital products and experiences. This skill provides frameworks, patterns, and best practices for creating text that helps users accomplish their goals.
- **Compatible with:** Claude, Codex, Cursor, and other agents that support the agent skills specification.
- **Note:** This skill works with Codex CLI/IDE, not ChatGPT. ChatGPT cannot install or use skills.
- ## When to Use This Skill
- Use this skill when:
- - Writing interface copy (buttons, labels, titles, messages, forms)
- - Editing existing UX text for clarity and effectiveness
- - Creating error messages, notifications, or success messages
- - Designing conversational flows or onboarding experiences
- - Establishing voice and tone for a product
- - Auditing product content for consistency and usability
- ## Core UX Writing Principles
- ### The Four Quality Standards
- Every piece of UX text should be:
- 1. **Purposeful** — Helps users or the business achieve goals
- 2. **Concise** — Uses the fewest words possible without losing meaning
- 3. **Conversational** — Sounds natural and human, not robotic
- 4. **Clear** — Unambiguous, accurate, and easy to understand
- ### Key Best Practices
- **Conciseness**
- - Use 40-60 characters per line maximum
- - Every word must have a job
- - Break dense text into scannable chunks
- - Front-load important information
- **Clarity**
- - Use plain language (7th grade reading level for general, 10th for professional)
- - Avoid jargon, idioms, and technical terms
- - Use consistent terminology throughout
- - Choose meaningful, specific verbs
- **Conversational Tone**
- - Write how you speak
- - Use active voice 85% of the time
- - Include prepositions and articles
- - Avoid robotic phrasing
- **User-Centered**
- - Focus on user benefits, not features
- - Anticipate and answer user questions
- - Use second-person ("you") language
- - Match user's language and mental models
- ## UX Text Patterns
- Apply these common patterns for interface elements.
- ### Titles
- - **Purpose**: Orient users to where they are
- - **Format**: Noun phrases, sentence case
- - **Types**: Brand titles, content titles, category titles, task titles
- - **Examples**: "Account settings", "Your library", "Create new post"
- ### Buttons and Links
- - **Purpose**: Enable users to take action
- - **Format**: Active imperative verbs, sentence case
- - **Pattern**: `[Verb] [object]`
- - **Examples**: "Save changes", "Delete account", "View details"
- - **Avoid**: Generic labels like "OK", "Submit", "Click here"
- ### Error Messages
- - **Purpose**: Explain problem and provide solution
- - **Format**: Empathetic, clear, actionable
- - **Pattern**: `[What failed]. [Why/context]. [What to do].`
- **Error Message Types**
- **Validation Errors (Inline)**
- - Show as user completes field or on blur
- - Brief, specific guidance to correct input
- - Pattern: `[Field] [specific requirement]`
- - Examples:
- - "Email must include @"
- - "Password must be at least 8 characters"
- - "Choose a date in the future"
- - Timing: Real-time or on field exit
- - Location: Below or beside the field
- **System Errors (Modal/Banner)**
- - Show when backend operations fail
- - Explain what happened and why
- - Pattern: `[Action failed]. [Likely cause]. [Recovery step].`
- - Examples:
- - "Payment failed. Your card was declined. Try a different payment method."
- - "Couldn't save changes. Connection lost. Reconnect and try again."
- - "Upload failed. File is too large. Choose a file under 10MB."
- - Timing: Immediately after failure
- - Location: Modal dialog or prominent banner
- **Blocking Errors (Full-screen)**
- - Prevent continued use until resolved
- - Clear explanation of blocker and resolution
- - Pattern: `[What's blocked]. [Why]. [Specific action needed].`
- - Examples:
- - "Update required. This version is no longer supported. Update now to continue."
- - "Subscription expired. Your account is paused. Renew subscription to restore access."
- - "Verification needed. Confirm your email to access features. Check your inbox."
- - Timing: On app launch or feature access
- - Location: Full screen or large modal
- **Permission Errors**
- - Explain benefit before requesting permission
- - Pattern: `[User benefit]. [Permission needed].`
- - Examples:
- - "Get notified when orders ship. Enable notifications."
- - "Find nearby stores. Allow location access."
- - "Back up your photos. Grant storage permission."
- - Timing: When feature is first used
- - Location: In context of the feature
- **What to Avoid**
- - Technical codes without explanation ("Error 403")
- - Blame language ("invalid input", "illegal character")
- - Robotic tone ("An error has occurred")
- - Dead ends (error with no recovery path)
- - Vague causes ("Something went wrong")
- ### Success Messages
- - **Purpose**: Confirm action completion
- - **Format**: Past tense, specific, encouraging
- - **Pattern**: `[Action] [result/benefit]`
- - **Examples**: "Changes saved", "Email sent", "Profile updated"
- ### Empty States
- - **Purpose**: Guide users when content is absent
- - **Types**: First-use, user-cleared, error/no results
- - **Format**: Explanation + CTA to populate
- - **Example**: "No messages yet. Start a conversation to connect with your team."
- ### Form Fields
- - **Labels**: Clear noun phrases describing input ("Email address", "Phone number")
- - **Instructions**: Verb-first, explain why information is needed
- - **Placeholder**: Use sparingly, only for standard inputs like "name@example.com"
- - **Helper text**: Static, on-demand, or automatic based on importance
- ### Notifications
- - **Purpose**: Deliver timely, valuable information
- - **Types**: Action-required (intrusive), Passive (less intrusive)
- - **Format**: Verb-first title + contextual description
- - **Example**: "Update required. Install the latest version to continue."
- ## Voice and Tone
- ### Voice (Consistent Brand Personality)
- Voice is the consistent personality of the product. Establish voice using:
- - **Concepts**: 3-5 key brand principles/values
- - **Voice characteristics**: Descriptive adjectives for each concept
- - **Do/Don't examples**: Concrete examples showing voice in action
- See references/voice-chart-template.md for creating a voice chart.
- ### Tone (Adaptive to Context)
- Tone is how voice adapts to specific situations. While voice remains constant, tone shifts based on user context and emotional state.
- **Tone Variables**
- - **Purpose**: Why user is seeing this text (information, action, confirmation)
- - **Context**: What user is trying to do (learning, completing task, recovering from error)
- - **Emotional state**: How user likely feels (frustrated, excited, confused, cautious)
- - **Stakes**: Impact of the action (low: changing theme, high: deleting account)
- **Tone Adaptation by User Emotional State**
- **Frustrated** (errors, failures, blockers)
- - Empathetic and solution-focused
- - Acknowledge the problem without blame
- - Provide clear recovery path
- - Example: "Payment failed. Your card was declined. Try a different payment method."
- **Confused** (first use, complex features)
- - Patient and explanatory
- - Break down steps clearly
- - Provide context and guidance
- - Example: "Connect your bank to see spending insights. We'll guide you through it."
- **Confident** (routine tasks, return visits)
- - Efficient and direct
- - Minimal explanation
- - Quick confirmation
- - Example: "Saved"
- **Cautious** (high-stakes actions, data loss)
- - Serious and transparent
- - Clear consequences
- - Respectful of user's decision
- - Example: "Delete account? You'll lose all data and this can't be undone."
- **Successful** (completions, achievements)
- - Positive and encouraging
- - Proportional to achievement
- - Brief celebration
- - Example: "Profile updated. Your changes are live."
- **Tone Adaptation by Content Type**
- **Error messages**: Empathetic, reassuring, solution-focused
- - Never blame user
- - Explain what happened
- - Provide clear next step
- **Success messages**: Positive, specific, encouraging
- - Confirm what happened
- - Proportional to action importance
- - Brief and clear
- **Instructions**: Clear, direct, helpful
- - Front-load key action
- - Explain why when needed
- - Use simple steps
- **Onboarding**: Inviting, encouraging, concise
- - Welcome without overwhelming
- - Focus on value
- - Celebrate early wins
- **Confirmations**: Serious, transparent, respectful
- - Clear about consequences
- - No manipulation
- - Easy to back out
- **Empty states**: Hopeful, actionable, guiding
- - Explain why it's empty
- - Provide clear next action
- - Keep encouraging tone
- ## Editing Process
- Edit UX text in four phases:
- ### Phase 1: Purposeful
- - Does text help user achieve their goal?
- - Does text serve business objectives?
- - Is value to user clear?
- - Are concerns anticipated and addressed?
- ### Phase 2: Concise
- - Remove unnecessary words
- - Combine redundant information
- - Ensure every word earns its space
- - Front-load important concepts
- ### Phase 3: Conversational
- - Read aloud—would you say this?
- - Use active voice (unless passive is clearer)
- - Include natural connecting words
- - Avoid corporate jargon
- ### Phase 4: Clear
- - Use specific, accurate verbs
- - Maintain consistent terminology
- - Test readability (Hemingway Editor, Flesch-Kincaid)
- - Ensure unambiguous meaning
- ## Workflow
- 1. **Understand context**
- - User goals and needs
- - Business objectives
- - Technical constraints
- - Emotional state of user
- 2. **Draft content**
- - Start with conversation (what would you say?)
- - Apply appropriate pattern
- - Consider voice and tone
- - Front-load important information
- 3. **Edit iteratively**
- - Phase 1: Purposeful
- - Phase 2: Concise
- - Phase 3: Conversational
- - Phase 4: Clear
- 4. **Test and measure**
- - Review with team
- - Test with users when possible
- - Measure task completion, comprehension
- - Iterate based on feedback
- ## Accessibility in UX Writing
- Writing accessible content ensures all users, including those using assistive technology, can understand and interact with your product.
- ### Core Accessibility Principles
- **Screen Reader Optimization**
- - Label all interactive elements explicitly ("Submit form" not just "Submit")
- - Write descriptive link text ("Read pricing details" not "Click here")
- - Structure error messages to work with screen readers (error + field label read together)
- - Use ARIA labels when visual context isn't sufficient
- **Cognitive Accessibility**
- - Target 8-14 words per sentence (8 words = 100% comprehension, 14 words = 90%)
- - Break complex information into scannable chunks
- - Use clear headings and logical hierarchy
- - Provide consistent, predictable patterns
- **Multi-Modal Communication**
- - Don't rely on color alone to convey meaning
- - Pair visual indicators with text ("Error: Email required" with red icon)
- - Provide text alternatives for icons and images
- - Ensure sufficient color contrast (WCAG AA minimum: 4.5:1)
- **Plain Language for All**
- - Target 7th-8th grade reading level for general audience
- - Define technical terms when first used
- - Avoid idioms, metaphors, and cultural references
- - Use common, everyday words
- ### Accessible Pattern Examples
- **Buttons**
- - ❌ Poor: "Submit" (context missing for screen readers)
- - ✅ Good: "Submit application"
- **Links**
- - ❌ Poor: "Click here for more information"
- - ✅ Good: "Read our privacy policy"
- **Error Messages**
- - ❌ Poor: Red text showing "Invalid"
- - ✅ Good: "Error: Email must include @" (with error icon)
- **Form Labels**
- - ❌ Poor: Placeholder-only fields
- - ✅ Good: Visible label + optional placeholder
- ## UX Text Benchmarks
- Use these research-backed metrics to create effective UX text.
- ### Sentence Length Targets
- **By Content Type**
- - **Buttons/CTAs**: 2-4 words ideal, 6 word maximum
- - **Titles**: 3-6 words, 40 characters maximum
- - **Error messages**: 12-18 words (including solution)
- - **Instructions**: 20 words maximum, 14 ideal
- - **Body copy**: 15-20 words per sentence average
- - **Notifications**: 10-15 words for title + body
- **Comprehension Rates**
- - 8 words or fewer: 100% user comprehension
- - 14 words or fewer: 90% user comprehension
- - 25 words: Maximum before significant comprehension drop
- ### Character and Line Length
- **Optimal Ranges**
- - **Line length**: 40-60 characters for maximum readability
- - **Button labels**: 15-25 characters
- - **Page titles**: 30-50 characters
- - **Notification titles**: 35-45 characters
- ### Reading Level Guidelines
- **By Audience**
- - **General public**: 7th-8th grade (Flesch-Kincaid)
- - **Professional tools**: 9th-10th grade
- - **Technical products**: 10th-11th grade
- - **Specialized fields**: 11th-12th grade (only when necessary)
- **Testing Tools**
- - Hemingway Editor: Highlights complex sentences
- - Readable.com: Provides multiple readability scores
- - Microsoft Word: Built-in Flesch-Kincaid scoring
- ## Common Mistakes to Avoid
- - Using passive voice excessively
- - Generic button labels ("Submit", "OK")
- - Blaming users in error messages
- - Overly clever humor in serious contexts
- - Inconsistent terminology
- - Hidden instructions or explanations
- - System-oriented language vs. user language
- - Too many words (not concise enough)
- - Robotic, corporate tone
- - Relying on color alone for meaning
- - Writing inaccessible link text ("Click here")
- ## Quick Reference
- **Sentence case**: "Save your changes" (not "Save Your Changes")
- **Active imperative for buttons**: "Delete account" (not "Account deletion")
- **User-focused**: "Save time with shortcuts" (not "We offer shortcuts")
- **Specific verbs**: "Delete" (not "Remove" when permanently deleting)
- **Front-loaded**: "Password must be 8 characters" (not "Must be 8 characters for your password")
- ## Resources
- This skill includes:
- - **references/accessibility-guidelines.md**: Comprehensive guide to writing accessible UX text for all users
- - **references/voice-chart-template.md**: Template for creating a product voice chart
- - **references/content-usability-checklist.md**: Comprehensive checklist for evaluating UX text quality
- - **references/patterns-detailed.md**: Extended examples of UX text patterns in different voices
- - **examples/real-world-improvements.md**: Before/after transformations with detailed analysis and scoring
- - **templates/error-message-template.md**: Fillable template for writing effective error messages
- - **templates/empty-state-template.md**: Guide for creating helpful empty states
- - **templates/onboarding-flow-template.md**: Framework for designing clear onboarding experiences
- - **docs/figma-integration.md**: Guide for using this skill with Figma MCP (Claude Code, Codex, and Cursor)
README.md · README · 247 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # Agent Skill for UX Writing
- > Scale content quality through AI-powered design system enforcement
- **🌐 [View website](https://content-designer.github.io/ux-writing-skill/)**
- **📄 [Read docs](https://content-designer-ux-writing-skill-26.mintlify.app/introduction)**
- An [agent skill](https://agentskills.io/) that enables Claude, Codex, and Cursor to write and edit user-centered interface copy (UX text/microcopy) for digital products. This skill transforms AI assistants into specialized UX writing tools that apply consistent standards, patterns, and voice across your product.
- ## The Problem
- Design systems solve visual consistency, but content quality still depends on individual writers. Every error message, button label, and empty state requires manual review to ensure it's clear, concise, conversational, and purposeful. This doesn't scale.
- ## The Solution
- This agent skill packages UX writing expertise into a system your agent can apply automatically. Instead of asking "make this better," you can rely on consistent, evidence-based improvements across your entire product interface.
- ## What Makes This Different
- **Systems thinking, not style guides**: This isn't a list of writing tips. It's a framework for evaluating and improving UX text based on four measurable quality standards.
- **Progressive disclosure**: Reference materials are loaded only when needed, keeping Claude's context efficient while providing deep expertise on demand.
- **Proven patterns**: Built from real-world UX writing best practices, with examples across different product voices and contexts.
- **Immediately actionable**: Every pattern includes concrete before/after examples and scoring against quality standards.
- ## What You Get
- ### Core Framework
- - **Four quality standards**: Purposeful, Concise, Conversational, Clear
- - **Common UX patterns**: Buttons, errors, empty states, forms, notifications, onboarding
- - **Editing process**: Systematic approach to improving any interface text
- - **Voice and tone guidance**: Adapt content to brand personality and context
- - **Accessibility guidelines**: Write for screen readers, cognitive accessibility, and WCAG compliance
- - **Research-backed benchmarks**: Sentence length targets, comprehension rates, reading levels
- ### Reference Materials
- - **Accessibility guidelines**: Comprehensive guide for writing inclusive, accessible UX text
- - **Voice chart template**: Establish consistent brand personality
- - **Content usability checklist**: Evaluate text quality with scoring framework
- - **Detailed pattern examples**: See how different voices apply the same patterns
- ### Practical Tools
- - **Real-world improvements**: Before/after transformations with analysis
- - **Fillable templates**: Error messages, empty states, onboarding flows
- - **Expanded error patterns**: Validation, system, blocking, and permission errors with examples
- - **Tone adaptation framework**: Map emotional states to appropriate tone
- - **Quick reference**: Common patterns and anti-patterns
- ## Use Cases
- **For content designers**: Apply consistent UX writing standards across your product without memorizing every rule.
- **For product teams**: Enable non-writers to create interface copy that follows your design system.
- **For design system teams**: Enforce content guidelines at scale without becoming a bottleneck.
- **For early-stage products**: Build content quality in from the start with proven patterns.
- ## Installation
- ### What You Need
- This skill works with **Claude Desktop**, **Claude Code**, **Codex** (CLI and IDE extensions), and **Cursor**. Install it with the [skills CLI](https://skills.sh/docs/cli) — no manual download or file copying required.
- **Note:** This skill works with Codex CLI/IDE, not ChatGPT. ChatGPT cannot install or use skills.
- ### Install with the Skills CLI
- Run this command in your terminal:
- ```bash
- npx skills add content-designer/ux-writing-skill
- ```
- The CLI downloads the skill and configures it automatically for your agent. Restart your agent or IDE after installation.
- **Verify it's working** by asking your agent:
- ```
- Write an error message for when a payment fails
- ```
- Your agent will apply UX writing best practices and produce a clear, empathetic error message.
- ### For Teams: Project Installation
- Want your whole team to use this skill automatically? Run the CLI from your project root:
- ```bash
- npx skills add content-designer/ux-writing-skill
- ```
- Then commit the installed skill files to your repository. Teammates get the skill when they pull the code.
- ## Figma Integration
- **Review and improve UX copy directly from your Figma designs!**
- Connect this skill to Figma through your agent to analyze mockups, audit copy, and suggest improvements based on UX writing best practices. Perfect for:
- - Content designers reviewing flows before launch
- - Product teams iterating on copy in designs
- - Design QA and accessibility audits
- - Cross-platform consistency checks
- **📖 Setup guide for all agents:** [docs/figma-integration.md](docs/figma-integration.md)
- ## Usage Examples
- ### Basic Usage
- ```
- Write an error message for when a payment fails
- ```
- Your agent applies the skill automatically and generates clear, actionable error messages following best practices.
- ### Editing Existing Copy
- ```
- Review this button label: "Submit your information for processing"
- ```
- Your agent evaluates against the four quality standards and suggests improvements.
- ### Creating Consistent Patterns
- ```
- Create empty state copy for a task list, keeping voice consistent with:
- - Purposeful, Concise, Conversational, Clear
- - Professional but friendly tone
- ```
- Your agent applies the appropriate patterns and maintains voice consistency.
- ### Evaluating Quality
- ```
- Score this error message:
- "An error occurred. Please try again later."
- ```
- Your agent uses the content usability checklist to provide detailed scoring and improvement suggestions.
- ## How It Works
- This skill uses **model-invoked activation** — Claude, Codex, and Cursor automatically decide when to use it based on your request. You don't need to explicitly call the skill; it activates when you:
- - Write or edit interface copy
- - Create error messages, notifications, or empty states
- - Work on button labels, form fields, or instructions
- - Review product content for consistency
- - Establish voice and tone guidelines
- The AI loads reference materials progressively, using only what's needed for your specific task to maintain efficient context usage.
- **In Codex**, you can also explicitly invoke the skill using `$ux-writing` or through the `/skills` command. **In Cursor**, use `@ux-writing` or reference the skill by name in your prompt.
- ## What You'll Learn
- Using this skill exposes the systematic thinking behind effective UX writing:
- - How to evaluate content objectively with scoring frameworks
- - Why certain patterns work across different product contexts
- - How voice stays consistent while tone adapts to situations
- - The difference between writing for clarity vs. writing for personality
- ## For Content Design Teams
- This skill can serve as:
- - **Onboarding tool**: New team members learn patterns faster
- - **Quality baseline**: Consistent standards across all writers
- - **Efficiency multiplier**: Generate first drafts that follow guidelines
- - **System documentation**: Reference materials that never go stale
- ## Credits
- Built by [Christopher Greer](https://www.linkedin.com/in/christopher-greer/), Staff Content Designer at Stripe, based on established UX writing principles from:
- - Content Design by Sarah Richards
- - Strategic Writing for UX by Torrey Podmajersky
- - Nicely Said by Kate Kiefer Lee and Nicole Fenton
- - Google Material Design writing guidelines
- - Years of practical application building design systems
- ## Contributing
- Contributions welcome! If you have:
- - Additional reference patterns
- - More real-world examples
- - Template improvements
- - Translations to other languages
- Please open an issue or submit a pull request.
- ### Building the Skill Package
- If you're contributing or want to build the skill ZIP locally:
- ```bash
- ./build-skill.sh
- ```
- This creates `dist/ux-writing-skill.zip` containing only the skill files (`SKILL.md`, `docs/`, `examples/`, `references/`, `templates/`).
- The build script excludes repository files like `README.md`, `CONTRIBUTING.md`, `index.html`, and the demo video — these live on GitHub but aren't needed in the skill package.
- ## License
- MIT License — use this skill freely in your projects and teams.
- ## Related Work
- Looking for more agent skills?
- - Learn about the standard: [agentskills.io](https://agentskills.io/)
- - Browse skills on [skills.sh](https://skills.sh)
- - Install skills with the [skills CLI](https://skills.sh/docs/cli)
- **For Claude**
- - Browse the [Claude Code Skills collection](https://github.com/anthropics/skills)
- - Learn about [agent skills architecture](https://claude.com/blog/equipping-agents-for-the-real-world-with-agent-skills)
- - Read [best practices for authoring skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices)
- **For Codex**
- - Explore [Codex Agent Skills documentation](https://developers.openai.com/codex/skills/)
- - Learn how to [create custom skills](https://developers.openai.com/codex/skills/create-skill)
- - Join the [OpenAI Developer Community](https://community.openai.com/) to discuss skills
- **For Cursor**
- - Read about [Cursor Agent Skills](https://cursor.com/docs/context/skills)
- ## Why This Matters
- Content is infrastructure. Every button label, error message, and empty state shapes how people understand and use your product. Good UX writing shouldn't depend on having an expert review every string.
- This skill makes UX writing excellence systematic, scalable, and consistent — exactly what design systems do for visual design.
- ---
- **Status**: Production-ready • **Version**: 1.6.0 • **Last updated**: March 2026
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.