New to Claude Skills? Learn how to install them →

jakubkrehel on GitHub

Better Writing

Free

Enhance your UX writing and interface copy.

by jakubkrehel3.3k stars on jakubkrehel/skills
3 views
Updated Aug 6, 2026
Get this skill

Free · Opens the source repo

What Better Writing does

Better Writing is a skill designed to assist developers and designers in crafting clear, concise, and user-friendly interface copy. This skill focuses on various aspects of UX writing, including button labels, error messages, onboarding instructions, and empty states. By adhering to established principles of effective communication, it helps ensure that user-facing text is not only consistent but also aligned with the product's voice and tone.

The skill emphasizes the importance of reconciling existing terminology and style guides before making any changes, ensuring that the brand's character remains intact. It advocates for a single, flexible voice throughout the product, adapting the tone to match the context—whether it’s a success message, routine action, or an error notification. This approach allows for a more cohesive user experience, reducing confusion and enhancing usability.

Additionally, Better Writing promotes direct communication with users by addressing them as "you" rather than as "the user." This shift fosters a more personal connection and improves clarity in instructional text. The skill also stresses the importance of using plain language over clever phrasing, avoiding jargon, and ensuring that buttons and links clearly describe their actions.

By following the guidelines provided by Better Writing, teams can create a more intuitive interface that minimizes user frustration and enhances overall satisfaction. This skill is particularly useful for those involved in UX design, product management, and content strategy, as it provides a structured approach to writing that aligns with best practices in user experience design.

When to use it

Use Better Writing when developing or reviewing any user-facing copy, including buttons, error messages, and onboarding instructions.

When not to use it

This skill may not be suitable for creative writing or contexts where a more playful or artistic tone is appropriate.

What you can build with it

Improving Onboarding Flows

Use Better Writing to refine the copy in onboarding flows, ensuring clarity and a welcoming tone for new users.

Creating Consistent Error Messages

Apply the principles of this skill to develop error messages that are clear and instructive, helping users understand how to resolve issues.

Enhancing Button Labels

Utilize the skill to craft verb-first button labels that clearly indicate the action, improving user comprehension and interaction.

How to install Better Writing

View source

1. Install with the skills CLI

npx skills add jakubkrehel/skills/better-writing --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by jakubkrehel

Writing that disappears into the interface

Clear and brief beats clever, consistency beats variety, and the best error message is the interaction redesigned so the error can't happen. Apply these principles when writing or reviewing any user-facing text.

How copy renders (capitalization via text-transform, truncation, smart punctuation) is covered by the better-typography skill; error markup and announcements (aria-invalid, live regions) by the better-accessibility skill; room for translated strings by the better-layout skill.

Core Principles

1. Recon the Existing Voice

Before writing or reviewing, inspect nearby interface copy, the product's terminology, localization conventions, and any voice or content style guide. Preserve intentional brand character when it remains clear and appropriate to the stakes. Treat a difference from generic plain language as a finding only when it creates inconsistency, ambiguity, translation risk, or an inappropriate tone.

2. One Voice, Flexible Tone

The product has one voice, established by its existing system rather than invented during a local edit. Keep terms consistent: if it's "Archive" in the menu, it isn't "Move to storage" in the toast. Tone flexes with the stakes:

ContextTone
Success, onboarding, empty statesWarm, can be light
Routine actions, settingsNeutral, minimal
Errors, destructive confirmationsCalm, plain, zero playfulness
Data loss, securitySerious, explicit

3. Address the Reader Directly

In instructional interface copy, address the reader directly as "you" rather than "the user." Avoid “we” in errors when it creates ambiguity or reads as deflection: prefer “Unable to load content” over “We're having trouble loading this content.” Preserve an established first-person brand voice in low-stakes contexts when it remains clear. Use possessives sparingly (“Favorites” over “Your Favorites”) and never switch perspective accidentally.

4. Plain Words Over Clever Ones

Choose easily understood words and delete every word that isn't needed. No idioms, colloquialisms, or humor that won't translate. Skip unnecessary gender: "Subscribers can post recipes", not "each subscriber can post his or her recipes". Match the input device: "tap" on touch, "click" with a pointer, "select" when both are possible. Never build sentences by concatenating fragments around variables ("You have " + n + " new messages"); word order changes per language, so use full templated strings with proper pluralization.

5. Verb-First Buttons

Button labels start with a verb naming the specific action: "Send", "Save draft", "Delete project". Never "OK!", "Let's go!", or bare "Yes"/"No" on consequential actions. Confirmation buttons repeat the consequence so the dialog is answerable without reading the body: "Delete this project?" offers Delete project and Cancel, not Yes and No.

6. Consistent Flow Vocabulary

Multi-step flows use one vocabulary: "Get Started" to enter, "Continue" or "Next" (pick one) to advance, "Done" to finish. Alternating synonyms across steps makes users wonder if the buttons do different things.

7. Links Describe Their Destination

Link text makes sense out of context; screen-reader users navigate by a list of the page's links. "Read the billing docs", never "Click here" (which also fails the device-verb rule on touch), and never a bare "Learn more" when several appear on one page. Suffix each: "Learn more about exports".

8. One Capitalization Policy

Pick title case or sentence case per element type (all buttons, all headings) and apply it consistently; sentence case is the safer default: calmer, no per-word case rules, localizes cleanly. "Save Changes" beside "Discard changes" reads as sloppiness.

9. Settings Describe the ON State

Label a toggle for what happens when it's on: "Send read receipts", and users infer the off state. Never label the negative ("Don't send read receipts"), which turns the toggle into a double negative. Link directly to a referenced setting instead of describing the path to it: a "Notification settings" link, not "Go to Settings > Notifications > Email".

10. Errors Say How to Fix, Next to Where It Broke

An error is an instruction, adjacent to the failing field:

BadGood
That password is too shortChoose a password with at least 8 characters
Invalid nameUse only letters for your name
Oops! Something went wrong.Unable to save. Check your connection and try again.

No blame, no "oops", no exclamation marks. Phrase hints positively ("Use only letters", not "Don't use numbers or symbols") and show them before the mistake, not after. If the same error keeps firing for many users, redesign the interaction instead of rewording it.

11. Empty States Point Forward

An empty state says what this place is and how to fill it, with one clear next action:

<!-- Bad: a shrug -->
<p>No results.</p>

<!-- Good: orientation plus a next step -->
<p class="font-medium">No projects yet</p>
<p class="text-sm text-zinc-500">Projects keep your tasks and files together.</p>
<button class="mt-4">Create a project</button>

Search and filter empty states name the query and offer an exit: "No results for 'quarterly'. Clear filters". Never park crucial persistent information in an empty state; it disappears the moment content exists.

12. Placeholders Are Examples, Not Labels

Placeholders show the expected format (name@example.com, DD/MM/YYYY). A placeholder is never the field's only label: it vanishes on input, and every field keeps a visible label.

Common Mistakes

MistakeFix
Local rewrite ignores the product's established terminology or voiceInspect nearby copy and the style guide before proposing a change
"The user" in instructional interface copyAddress the reader directly as "you"
"We're having trouble…" obscures responsibility or recoveryUse a direct status and next step: "Unable to load content"
OK / Yes confirming a destructive dialogRepeat the consequence: "Delete project"
"Continue" on step 2, "Next" on step 3One flow vocabulary throughout
"Click here" or bare "Learn more" linkDescribe the destination: "Read the billing docs"
"Save Changes" beside "Discard changes"One capitalization policy per element type
"Don't send read receipts" toggleLabel the ON state: "Send read receipts"
"Oops! Something went wrong."Say what to do, next to the failing field
"No results." as the whole empty stateOrient and point forward with a next action
Placeholder doing the label's jobVisible label; placeholder shows the format
"You have " + n + " messages"Full templated strings with pluralization

Review Output Format

Use this format only when the user asks for a standalone writing review. When better-interface orchestrates the review, provide domain evidence and findings to that skill and let its output format, severity scale, consolidation rules, cap, and verdict take precedence.

Present the standalone review in two parts.

Findings

Group all confirmed findings by principle. Use a markdown table with Severity, Location, Before, After, and Why columns. Never use separate "Before:" / "After:" lines.

  • Severity: HIGH misleads users, obscures a consequence, or prevents recovery; MEDIUM makes a task harder to understand; LOW is isolated voice or consistency polish.
  • Location: cite path/to/file:line. If the artifact has no source files, cite the exact screen and component instead.
  • Before / After: quote the current copy and its complete replacement.
  • Why: name the violated principle and explain the comprehension or trust cost.

Consolidate a repeated systemic issue into one row and list every affected location. Omit principles with no findings.

Example

Errors say how to fix

SeverityLocationBeforeAfterWhy
MEDIUMsrc/PasswordField.tsx:36"Invalid password""Choose a password with at least 8 characters"The error must say how to fix the problem
HIGHsrc/Editor.tsx:81"We couldn't process your request" toastInline "Unable to save. Check your connection and try again."The current message neither locates the failure nor offers recovery

Verb-first buttons

SeverityLocationBeforeAfterWhy
HIGHsrc/DeleteDialog.tsx:29"OK" on the delete confirmation"Delete project"A consequential action must repeat the consequence
MEDIUMsrc/Signup.tsx:54"Let's go!""Create account"The label must name the action

Verification and Verdict

After the findings:

  1. Verification: list the exact checks run and their observed results, including the complete flow, variable interpolation, pluralization, and narrow-width wrapping when applicable. If a check was not run, state what still needs verification.
  2. Verdict: Block if any HIGH finding remains, Needs changes if only MEDIUM or LOW findings remain, and Approve only when no actionable findings remain.

When there are no findings, omit the tables, state "No actionable writing findings", report verification, and end with Approve.

Frequently asked questions about Better Writing

Similar skills