Guidance for writing clear interface text, such as button labels, error messages, forms, notifications, and onboarding content. It focuses on copy that helps people understand and complete tasks in software.

Use it to draft or review labels, messages, help text, empty states, success states, and conversational flows.

It helps remove confusing, vague, overly long, or inconsistent wording from user interfaces.

How recomposesh/recompose configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to recomposesh/recompose. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/recomposesh/recompose/main/.agents/skills/ux-writing/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/recomposesh/recompose

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/recomposesh/recompose/ux-writing.svg)](https://agentmods.dev/skills/recomposesh/recompose/ux-writing)

Your own site

<a href="https://agentmods.dev/skills/recomposesh/recompose/ux-writing"><img src="https://agentmods.dev/badge/skills/recomposesh/recompose/ux-writing.svg" alt="Measured on agentmods" height="20"></a>

Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,465 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00137	$0.03465
Opus 5	$0.00068	$0.01733
Sonnet 5	$0.00027	$0.00693
Haiku 4.5	$0.00014	$0.00347

Measured 7d ago against content hash 67dda2a5ba7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ux-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (build-skill.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to ux-writing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/ux-writing/SKILL.md · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

Purposeful — Helps users or the business achieve goals
Concise — Uses the fewest words possible without losing meaning
Conversational — Sounds natural and human, not robotic
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"

Read the full file on GitHub · 418 lines

Files

What ships with it

24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 418 lines · 137 tokens per session scan A 67dda2a5ba7e

Subscribe to this mod's changes

ux-writing is a skill published in the GitHub repository recomposesh/recompose (27 stars, last pushed 10d ago), licensed MIT. It adds 137 tokens to every session and 3,465 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ux-writing, differing in 0 lines, and is treated as a copy.

Design and UX Writing and docs

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

recompose: Skill for Claude Code