Skip to content
Back to search

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.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/content-designer-ux-writing-skill/badge.svg)](/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

i

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)

  1. ---
  2. name: ux-writing
  3. 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.
  4. ---
  5. # UX Writing
  6. 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.
  7. **Compatible with:** Claude, Codex, Cursor, and other agents that support the agent skills specification.
  8. **Note:** This skill works with Codex CLI/IDE, not ChatGPT. ChatGPT cannot install or use skills.
  9. ## When to Use This Skill
  10. Use this skill when:
  11. - Writing interface copy (buttons, labels, titles, messages, forms)
  12. - Editing existing UX text for clarity and effectiveness
  13. - Creating error messages, notifications, or success messages
  14. - Designing conversational flows or onboarding experiences
  15. - Establishing voice and tone for a product
  16. - Auditing product content for consistency and usability
  17. ## Core UX Writing Principles
  18. ### The Four Quality Standards
  19. Every piece of UX text should be:
  20. 1. **Purposeful** — Helps users or the business achieve goals
  21. 2. **Concise** — Uses the fewest words possible without losing meaning
  22. 3. **Conversational** — Sounds natural and human, not robotic
  23. 4. **Clear** — Unambiguous, accurate, and easy to understand
  24. ### Key Best Practices
  25. **Conciseness**
  26. - Use 40-60 characters per line maximum
  27. - Every word must have a job
  28. - Break dense text into scannable chunks
  29. - Front-load important information
  30. **Clarity**
  31. - Use plain language (7th grade reading level for general, 10th for professional)
  32. - Avoid jargon, idioms, and technical terms
  33. - Use consistent terminology throughout
  34. - Choose meaningful, specific verbs
  35. **Conversational Tone**
  36. - Write how you speak
  37. - Use active voice 85% of the time
  38. - Include prepositions and articles
  39. - Avoid robotic phrasing
  40. **User-Centered**
  41. - Focus on user benefits, not features
  42. - Anticipate and answer user questions
  43. - Use second-person ("you") language
  44. - Match user's language and mental models
  45. ## UX Text Patterns
  46. Apply these common patterns for interface elements.
  47. ### Titles
  48. - **Purpose**: Orient users to where they are
  49. - **Format**: Noun phrases, sentence case
  50. - **Types**: Brand titles, content titles, category titles, task titles
  51. - **Examples**: "Account settings", "Your library", "Create new post"
  52. ### Buttons and Links
  53. - **Purpose**: Enable users to take action
  54. - **Format**: Active imperative verbs, sentence case
  55. - **Pattern**: `[Verb] [object]`
  56. - **Examples**: "Save changes", "Delete account", "View details"
  57. - **Avoid**: Generic labels like "OK", "Submit", "Click here"
  58. ### Error Messages
  59. - **Purpose**: Explain problem and provide solution
  60. - **Format**: Empathetic, clear, actionable
  61. - **Pattern**: `[What failed]. [Why/context]. [What to do].`
  62. **Error Message Types**
  63. **Validation Errors (Inline)**
  64. - Show as user completes field or on blur
  65. - Brief, specific guidance to correct input
  66. - Pattern: `[Field] [specific requirement]`
  67. - Examples:
  68. - "Email must include @"
  69. - "Password must be at least 8 characters"
  70. - "Choose a date in the future"
  71. - Timing: Real-time or on field exit
  72. - Location: Below or beside the field
  73. **System Errors (Modal/Banner)**
  74. - Show when backend operations fail
  75. - Explain what happened and why
  76. - Pattern: `[Action failed]. [Likely cause]. [Recovery step].`
  77. - Examples:
  78. - "Payment failed. Your card was declined. Try a different payment method."
  79. - "Couldn't save changes. Connection lost. Reconnect and try again."
  80. - "Upload failed. File is too large. Choose a file under 10MB."
  81. - Timing: Immediately after failure
  82. - Location: Modal dialog or prominent banner
  83. **Blocking Errors (Full-screen)**
  84. - Prevent continued use until resolved
  85. - Clear explanation of blocker and resolution
  86. - Pattern: `[What's blocked]. [Why]. [Specific action needed].`
  87. - Examples:
  88. - "Update required. This version is no longer supported. Update now to continue."
  89. - "Subscription expired. Your account is paused. Renew subscription to restore access."
  90. - "Verification needed. Confirm your email to access features. Check your inbox."
  91. - Timing: On app launch or feature access
  92. - Location: Full screen or large modal
  93. **Permission Errors**
  94. - Explain benefit before requesting permission
  95. - Pattern: `[User benefit]. [Permission needed].`
  96. - Examples:
  97. - "Get notified when orders ship. Enable notifications."
  98. - "Find nearby stores. Allow location access."
  99. - "Back up your photos. Grant storage permission."
  100. - Timing: When feature is first used
  101. - Location: In context of the feature
  102. **What to Avoid**
  103. - Technical codes without explanation ("Error 403")
  104. - Blame language ("invalid input", "illegal character")
  105. - Robotic tone ("An error has occurred")
  106. - Dead ends (error with no recovery path)
  107. - Vague causes ("Something went wrong")
  108. ### Success Messages
  109. - **Purpose**: Confirm action completion
  110. - **Format**: Past tense, specific, encouraging
  111. - **Pattern**: `[Action] [result/benefit]`
  112. - **Examples**: "Changes saved", "Email sent", "Profile updated"
  113. ### Empty States
  114. - **Purpose**: Guide users when content is absent
  115. - **Types**: First-use, user-cleared, error/no results
  116. - **Format**: Explanation + CTA to populate
  117. - **Example**: "No messages yet. Start a conversation to connect with your team."
  118. ### Form Fields
  119. - **Labels**: Clear noun phrases describing input ("Email address", "Phone number")
  120. - **Instructions**: Verb-first, explain why information is needed
  121. - **Placeholder**: Use sparingly, only for standard inputs like "name@example.com"
  122. - **Helper text**: Static, on-demand, or automatic based on importance
  123. ### Notifications
  124. - **Purpose**: Deliver timely, valuable information
  125. - **Types**: Action-required (intrusive), Passive (less intrusive)
  126. - **Format**: Verb-first title + contextual description
  127. - **Example**: "Update required. Install the latest version to continue."
  128. ## Voice and Tone
  129. ### Voice (Consistent Brand Personality)
  130. Voice is the consistent personality of the product. Establish voice using:
  131. - **Concepts**: 3-5 key brand principles/values
  132. - **Voice characteristics**: Descriptive adjectives for each concept
  133. - **Do/Don't examples**: Concrete examples showing voice in action
  134. See references/voice-chart-template.md for creating a voice chart.
  135. ### Tone (Adaptive to Context)
  136. Tone is how voice adapts to specific situations. While voice remains constant, tone shifts based on user context and emotional state.
  137. **Tone Variables**
  138. - **Purpose**: Why user is seeing this text (information, action, confirmation)
  139. - **Context**: What user is trying to do (learning, completing task, recovering from error)
  140. - **Emotional state**: How user likely feels (frustrated, excited, confused, cautious)
  141. - **Stakes**: Impact of the action (low: changing theme, high: deleting account)
  142. **Tone Adaptation by User Emotional State**
  143. **Frustrated** (errors, failures, blockers)
  144. - Empathetic and solution-focused
  145. - Acknowledge the problem without blame
  146. - Provide clear recovery path
  147. - Example: "Payment failed. Your card was declined. Try a different payment method."
  148. **Confused** (first use, complex features)
  149. - Patient and explanatory
  150. - Break down steps clearly
  151. - Provide context and guidance
  152. - Example: "Connect your bank to see spending insights. We'll guide you through it."
  153. **Confident** (routine tasks, return visits)
  154. - Efficient and direct
  155. - Minimal explanation
  156. - Quick confirmation
  157. - Example: "Saved"
  158. **Cautious** (high-stakes actions, data loss)
  159. - Serious and transparent
  160. - Clear consequences
  161. - Respectful of user's decision
  162. - Example: "Delete account? You'll lose all data and this can't be undone."
  163. **Successful** (completions, achievements)
  164. - Positive and encouraging
  165. - Proportional to achievement
  166. - Brief celebration
  167. - Example: "Profile updated. Your changes are live."
  168. **Tone Adaptation by Content Type**
  169. **Error messages**: Empathetic, reassuring, solution-focused
  170. - Never blame user
  171. - Explain what happened
  172. - Provide clear next step
  173. **Success messages**: Positive, specific, encouraging
  174. - Confirm what happened
  175. - Proportional to action importance
  176. - Brief and clear
  177. **Instructions**: Clear, direct, helpful
  178. - Front-load key action
  179. - Explain why when needed
  180. - Use simple steps
  181. **Onboarding**: Inviting, encouraging, concise
  182. - Welcome without overwhelming
  183. - Focus on value
  184. - Celebrate early wins
  185. **Confirmations**: Serious, transparent, respectful
  186. - Clear about consequences
  187. - No manipulation
  188. - Easy to back out
  189. **Empty states**: Hopeful, actionable, guiding
  190. - Explain why it's empty
  191. - Provide clear next action
  192. - Keep encouraging tone
  193. ## Editing Process
  194. Edit UX text in four phases:
  195. ### Phase 1: Purposeful
  196. - Does text help user achieve their goal?
  197. - Does text serve business objectives?
  198. - Is value to user clear?
  199. - Are concerns anticipated and addressed?
  200. ### Phase 2: Concise
  201. - Remove unnecessary words
  202. - Combine redundant information
  203. - Ensure every word earns its space
  204. - Front-load important concepts
  205. ### Phase 3: Conversational
  206. - Read aloud—would you say this?
  207. - Use active voice (unless passive is clearer)
  208. - Include natural connecting words
  209. - Avoid corporate jargon
  210. ### Phase 4: Clear
  211. - Use specific, accurate verbs
  212. - Maintain consistent terminology
  213. - Test readability (Hemingway Editor, Flesch-Kincaid)
  214. - Ensure unambiguous meaning
  215. ## Workflow
  216. 1. **Understand context**
  217. - User goals and needs
  218. - Business objectives
  219. - Technical constraints
  220. - Emotional state of user
  221. 2. **Draft content**
  222. - Start with conversation (what would you say?)
  223. - Apply appropriate pattern
  224. - Consider voice and tone
  225. - Front-load important information
  226. 3. **Edit iteratively**
  227. - Phase 1: Purposeful
  228. - Phase 2: Concise
  229. - Phase 3: Conversational
  230. - Phase 4: Clear
  231. 4. **Test and measure**
  232. - Review with team
  233. - Test with users when possible
  234. - Measure task completion, comprehension
  235. - Iterate based on feedback
  236. ## Accessibility in UX Writing
  237. Writing accessible content ensures all users, including those using assistive technology, can understand and interact with your product.
  238. ### Core Accessibility Principles
  239. **Screen Reader Optimization**
  240. - Label all interactive elements explicitly ("Submit form" not just "Submit")
  241. - Write descriptive link text ("Read pricing details" not "Click here")
  242. - Structure error messages to work with screen readers (error + field label read together)
  243. - Use ARIA labels when visual context isn't sufficient
  244. **Cognitive Accessibility**
  245. - Target 8-14 words per sentence (8 words = 100% comprehension, 14 words = 90%)
  246. - Break complex information into scannable chunks
  247. - Use clear headings and logical hierarchy
  248. - Provide consistent, predictable patterns
  249. **Multi-Modal Communication**
  250. - Don't rely on color alone to convey meaning
  251. - Pair visual indicators with text ("Error: Email required" with red icon)
  252. - Provide text alternatives for icons and images
  253. - Ensure sufficient color contrast (WCAG AA minimum: 4.5:1)
  254. **Plain Language for All**
  255. - Target 7th-8th grade reading level for general audience
  256. - Define technical terms when first used
  257. - Avoid idioms, metaphors, and cultural references
  258. - Use common, everyday words
  259. ### Accessible Pattern Examples
  260. **Buttons**
  261. - ❌ Poor: "Submit" (context missing for screen readers)
  262. - ✅ Good: "Submit application"
  263. **Links**
  264. - ❌ Poor: "Click here for more information"
  265. - ✅ Good: "Read our privacy policy"
  266. **Error Messages**
  267. - ❌ Poor: Red text showing "Invalid"
  268. - ✅ Good: "Error: Email must include @" (with error icon)
  269. **Form Labels**
  270. - ❌ Poor: Placeholder-only fields
  271. - ✅ Good: Visible label + optional placeholder
  272. ## UX Text Benchmarks
  273. Use these research-backed metrics to create effective UX text.
  274. ### Sentence Length Targets
  275. **By Content Type**
  276. - **Buttons/CTAs**: 2-4 words ideal, 6 word maximum
  277. - **Titles**: 3-6 words, 40 characters maximum
  278. - **Error messages**: 12-18 words (including solution)
  279. - **Instructions**: 20 words maximum, 14 ideal
  280. - **Body copy**: 15-20 words per sentence average
  281. - **Notifications**: 10-15 words for title + body
  282. **Comprehension Rates**
  283. - 8 words or fewer: 100% user comprehension
  284. - 14 words or fewer: 90% user comprehension
  285. - 25 words: Maximum before significant comprehension drop
  286. ### Character and Line Length
  287. **Optimal Ranges**
  288. - **Line length**: 40-60 characters for maximum readability
  289. - **Button labels**: 15-25 characters
  290. - **Page titles**: 30-50 characters
  291. - **Notification titles**: 35-45 characters
  292. ### Reading Level Guidelines
  293. **By Audience**
  294. - **General public**: 7th-8th grade (Flesch-Kincaid)
  295. - **Professional tools**: 9th-10th grade
  296. - **Technical products**: 10th-11th grade
  297. - **Specialized fields**: 11th-12th grade (only when necessary)
  298. **Testing Tools**
  299. - Hemingway Editor: Highlights complex sentences
  300. - Readable.com: Provides multiple readability scores
  301. - Microsoft Word: Built-in Flesch-Kincaid scoring
  302. ## Common Mistakes to Avoid
  303. - Using passive voice excessively
  304. - Generic button labels ("Submit", "OK")
  305. - Blaming users in error messages
  306. - Overly clever humor in serious contexts
  307. - Inconsistent terminology
  308. - Hidden instructions or explanations
  309. - System-oriented language vs. user language
  310. - Too many words (not concise enough)
  311. - Robotic, corporate tone
  312. - Relying on color alone for meaning
  313. - Writing inaccessible link text ("Click here")
  314. ## Quick Reference
  315. **Sentence case**: "Save your changes" (not "Save Your Changes")
  316. **Active imperative for buttons**: "Delete account" (not "Account deletion")
  317. **User-focused**: "Save time with shortcuts" (not "We offer shortcuts")
  318. **Specific verbs**: "Delete" (not "Remove" when permanently deleting)
  319. **Front-loaded**: "Password must be 8 characters" (not "Must be 8 characters for your password")
  320. ## Resources
  321. This skill includes:
  322. - **references/accessibility-guidelines.md**: Comprehensive guide to writing accessible UX text for all users
  323. - **references/voice-chart-template.md**: Template for creating a product voice chart
  324. - **references/content-usability-checklist.md**: Comprehensive checklist for evaluating UX text quality
  325. - **references/patterns-detailed.md**: Extended examples of UX text patterns in different voices
  326. - **examples/real-world-improvements.md**: Before/after transformations with detailed analysis and scoring
  327. - **templates/error-message-template.md**: Fillable template for writing effective error messages
  328. - **templates/empty-state-template.md**: Guide for creating helpful empty states
  329. - **templates/onboarding-flow-template.md**: Framework for designing clear onboarding experiences
  330. - **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)

  1. # Agent Skill for UX Writing
  2. > Scale content quality through AI-powered design system enforcement
  3. **🌐 [View website](https://content-designer.github.io/ux-writing-skill/)**
  4. **📄 [Read docs](https://content-designer-ux-writing-skill-26.mintlify.app/introduction)**
  5. 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.
  6. ## The Problem
  7. 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.
  8. ## The Solution
  9. 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.
  10. ## What Makes This Different
  11. **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.
  12. **Progressive disclosure**: Reference materials are loaded only when needed, keeping Claude's context efficient while providing deep expertise on demand.
  13. **Proven patterns**: Built from real-world UX writing best practices, with examples across different product voices and contexts.
  14. **Immediately actionable**: Every pattern includes concrete before/after examples and scoring against quality standards.
  15. ## What You Get
  16. ### Core Framework
  17. - **Four quality standards**: Purposeful, Concise, Conversational, Clear
  18. - **Common UX patterns**: Buttons, errors, empty states, forms, notifications, onboarding
  19. - **Editing process**: Systematic approach to improving any interface text
  20. - **Voice and tone guidance**: Adapt content to brand personality and context
  21. - **Accessibility guidelines**: Write for screen readers, cognitive accessibility, and WCAG compliance
  22. - **Research-backed benchmarks**: Sentence length targets, comprehension rates, reading levels
  23. ### Reference Materials
  24. - **Accessibility guidelines**: Comprehensive guide for writing inclusive, accessible UX text
  25. - **Voice chart template**: Establish consistent brand personality
  26. - **Content usability checklist**: Evaluate text quality with scoring framework
  27. - **Detailed pattern examples**: See how different voices apply the same patterns
  28. ### Practical Tools
  29. - **Real-world improvements**: Before/after transformations with analysis
  30. - **Fillable templates**: Error messages, empty states, onboarding flows
  31. - **Expanded error patterns**: Validation, system, blocking, and permission errors with examples
  32. - **Tone adaptation framework**: Map emotional states to appropriate tone
  33. - **Quick reference**: Common patterns and anti-patterns
  34. ## Use Cases
  35. **For content designers**: Apply consistent UX writing standards across your product without memorizing every rule.
  36. **For product teams**: Enable non-writers to create interface copy that follows your design system.
  37. **For design system teams**: Enforce content guidelines at scale without becoming a bottleneck.
  38. **For early-stage products**: Build content quality in from the start with proven patterns.
  39. ## Installation
  40. ### What You Need
  41. 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.
  42. **Note:** This skill works with Codex CLI/IDE, not ChatGPT. ChatGPT cannot install or use skills.
  43. ### Install with the Skills CLI
  44. Run this command in your terminal:
  45. ```bash
  46. npx skills add content-designer/ux-writing-skill
  47. ```
  48. The CLI downloads the skill and configures it automatically for your agent. Restart your agent or IDE after installation.
  49. **Verify it's working** by asking your agent:
  50. ```
  51. Write an error message for when a payment fails
  52. ```
  53. Your agent will apply UX writing best practices and produce a clear, empathetic error message.
  54. ### For Teams: Project Installation
  55. Want your whole team to use this skill automatically? Run the CLI from your project root:
  56. ```bash
  57. npx skills add content-designer/ux-writing-skill
  58. ```
  59. Then commit the installed skill files to your repository. Teammates get the skill when they pull the code.
  60. ## Figma Integration
  61. **Review and improve UX copy directly from your Figma designs!**
  62. Connect this skill to Figma through your agent to analyze mockups, audit copy, and suggest improvements based on UX writing best practices. Perfect for:
  63. - Content designers reviewing flows before launch
  64. - Product teams iterating on copy in designs
  65. - Design QA and accessibility audits
  66. - Cross-platform consistency checks
  67. **📖 Setup guide for all agents:** [docs/figma-integration.md](docs/figma-integration.md)
  68. ## Usage Examples
  69. ### Basic Usage
  70. ```
  71. Write an error message for when a payment fails
  72. ```
  73. Your agent applies the skill automatically and generates clear, actionable error messages following best practices.
  74. ### Editing Existing Copy
  75. ```
  76. Review this button label: "Submit your information for processing"
  77. ```
  78. Your agent evaluates against the four quality standards and suggests improvements.
  79. ### Creating Consistent Patterns
  80. ```
  81. Create empty state copy for a task list, keeping voice consistent with:
  82. - Purposeful, Concise, Conversational, Clear
  83. - Professional but friendly tone
  84. ```
  85. Your agent applies the appropriate patterns and maintains voice consistency.
  86. ### Evaluating Quality
  87. ```
  88. Score this error message:
  89. "An error occurred. Please try again later."
  90. ```
  91. Your agent uses the content usability checklist to provide detailed scoring and improvement suggestions.
  92. ## How It Works
  93. 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:
  94. - Write or edit interface copy
  95. - Create error messages, notifications, or empty states
  96. - Work on button labels, form fields, or instructions
  97. - Review product content for consistency
  98. - Establish voice and tone guidelines
  99. The AI loads reference materials progressively, using only what's needed for your specific task to maintain efficient context usage.
  100. **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.
  101. ## What You'll Learn
  102. Using this skill exposes the systematic thinking behind effective UX writing:
  103. - How to evaluate content objectively with scoring frameworks
  104. - Why certain patterns work across different product contexts
  105. - How voice stays consistent while tone adapts to situations
  106. - The difference between writing for clarity vs. writing for personality
  107. ## For Content Design Teams
  108. This skill can serve as:
  109. - **Onboarding tool**: New team members learn patterns faster
  110. - **Quality baseline**: Consistent standards across all writers
  111. - **Efficiency multiplier**: Generate first drafts that follow guidelines
  112. - **System documentation**: Reference materials that never go stale
  113. ## Credits
  114. Built by [Christopher Greer](https://www.linkedin.com/in/christopher-greer/), Staff Content Designer at Stripe, based on established UX writing principles from:
  115. - Content Design by Sarah Richards
  116. - Strategic Writing for UX by Torrey Podmajersky
  117. - Nicely Said by Kate Kiefer Lee and Nicole Fenton
  118. - Google Material Design writing guidelines
  119. - Years of practical application building design systems
  120. ## Contributing
  121. Contributions welcome! If you have:
  122. - Additional reference patterns
  123. - More real-world examples
  124. - Template improvements
  125. - Translations to other languages
  126. Please open an issue or submit a pull request.
  127. ### Building the Skill Package
  128. If you're contributing or want to build the skill ZIP locally:
  129. ```bash
  130. ./build-skill.sh
  131. ```
  132. This creates `dist/ux-writing-skill.zip` containing only the skill files (`SKILL.md`, `docs/`, `examples/`, `references/`, `templates/`).
  133. 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.
  134. ## License
  135. MIT License — use this skill freely in your projects and teams.
  136. ## Related Work
  137. Looking for more agent skills?
  138. - Learn about the standard: [agentskills.io](https://agentskills.io/)
  139. - Browse skills on [skills.sh](https://skills.sh)
  140. - Install skills with the [skills CLI](https://skills.sh/docs/cli)
  141. **For Claude**
  142. - Browse the [Claude Code Skills collection](https://github.com/anthropics/skills)
  143. - Learn about [agent skills architecture](https://claude.com/blog/equipping-agents-for-the-real-world-with-agent-skills)
  144. - Read [best practices for authoring skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices)
  145. **For Codex**
  146. - Explore [Codex Agent Skills documentation](https://developers.openai.com/codex/skills/)
  147. - Learn how to [create custom skills](https://developers.openai.com/codex/skills/create-skill)
  148. - Join the [OpenAI Developer Community](https://community.openai.com/) to discuss skills
  149. **For Cursor**
  150. - Read about [Cursor Agent Skills](https://cursor.com/docs/context/skills)
  151. ## Why This Matters
  152. 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.
  153. This skill makes UX writing excellence systematic, scalable, and consistent — exactly what design systems do for visual design.
  154. ---
  155. **Status**: Production-ready • **Version**: 1.6.0 • **Last updated**: March 2026

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.