Menu

Individual skill

ux-writing-audit

0upvotes

Audits an existing corpus of product copy - buttons, labels, errors, empty states, toasts, tooltips - against clarity, consistency, voice, and actionability heuristics, and delivers a scored findings table with rewrites plus a reusable glossary. Use when someone asks "audit our product copy", "why does our UI text feel inconsistent", "review these error messages", "is it log in or sign in", or before a redesign or localization push. Do NOT use for writing new error messages from scratch - use error-message-writer instead; for first-run and activation flows, use onboarding-copy.

skills/ux-writing-audit/SKILL.md

Read pinned source

Source commit 97a13607d669157a4a16d5ba79b77f208319f7b9

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
24
Repository last updated
Oct 13, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# UX Writing Audit

Copy debt is invisible until it isn't: users stall on a button they don't trust, support tickets pile up around one confusing error, and translators quote double because the source text contradicts itself. An audit finds where the words fail and fixes them systematically - not one string at a time, but as a corpus with shared vocabulary and voice. The output is rewrites the team can ship plus a glossary that stops the debt from regrowing.

## Inputs to collect

1. **The strings, with context** - every string in scope, each tagged with its surface (button, field label, error, toast, modal title, empty state, tooltip) and the moment it appears. You cannot audit copy in isolation from the moment it appears. If the team has no string inventory, extracting one is Step 1, not a blocker.
2. **Voice definition** - the product's voice in three adjectives (e.g., "plain, confident, warm"). If none exists, draft one from the best existing copy and label it a proposal.
3. **Locked strings** - legal, regulated, or contractual wording. These get flagged, never rewritten.
4. **Scope priority** - default: errors and empty states first; that is where copy debt concentrates.

## Operating procedure

### Step 1: Inventory
Back to top