ux-writing

ux-writing is a skill for Claude Code from toss/apps-in-toss-harness. It costs 259 tokens per session (2,895 once invoked), scanned A, original, BSD-3-Clause.

A guide for improving the words shown in a mini-app's screens. It reviews existing screen copy and proposes clearer wording based on defined user-experience writing rules.

In plain words
What is it for?
It helps revise labels, instructions, error messages, and other user-facing copy in a mini-app.
Why use it?
Screen text can be unclear, repetitive, or fail to tell users what happened and what to do next. This provides a structured way to find and rewrite those messages.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the ait plugin — 11 skills, 4 commands shipped together

Good fit It helps revise labels, instructions, error messages, and other user-facing copy in a mini-app.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toss/apps-in-toss-harness/ux-writing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add toss/apps-in-toss-harness --skill ux-writing
Clone the repo
git clone --depth 1 https://github.com/toss/apps-in-toss-harness

Made for: Claude Code.

Or install ait, the plugin that ships this one along with the rest of its 11 skills, 4 commands.

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.

agentmods badge for ux-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/ux-writing/github.svg)](https://agentmods.dev/skills/toss/apps-in-toss-harness/ux-writing)
Your own site
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/ux-writing"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/ux-writing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ux-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/ux-writing"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/ux-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 259 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,895 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 original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00259 $0.02895
Opus 5.5 $0.00104 $0.01158
Sonnet 5.5 $0.00052 $0.00579
Haiku 4.5 $0.00026 $0.00290

Measured 6d ago against content hash bb3230c4836f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 6d ago.

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.

packages/agent-plugin/shared/skills/ux-writing/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ux-writing skill

목적

화면 문구가 이미 있고 더 낫게 다듬어야 할 때 쓰는 재작성 조력 skill이다. 판정(카피가 기준에 맞는가)은 design skill의 quality bar G6(카피)·G8 (다크패턴)이 하고, 이 skill은 어떻게 고칠 것인가를 담는다 — 같은 규칙을 두 곳에서 다시 정의하지 않고, 여기서는 재작성 원칙·절차·before/after 예시만 다룬다.

산출은 항상 제안이다. 코드나 문구 파일을 실제로 고치기 전에 사용자 확인을 받는다 — 확인 없이 문자열을 일괄 치환하지 않는다.

언제 쓰나

  • 화면에 이미 문구가 있고, 더 나은 카피로 다듬고 싶을 때.
  • design skill의 품질 판정에서 G6(카피)에 "조정 필요"가 나와서 실제로 손을 대야 할 때.
/ait:ux-writing [화면 또는 파일]
                          # 말로: "이 화면 문구를 UX 라이팅 기준으로 다듬어줘"

대상을 지정하지 않고 불러도 된다 — 1단계에서 현재 프로젝트의 화면 문구를 먼저 훑어 대상 목록을 함께 확인한다.

문구 원칙

아래 축으로 문구를 점검하고 고친다. 괄호 안 표기는 design skill의 references/quality-bar.md에 있는 대응 판정 항목이다 — 이 skill은 그 기준을 참조할 뿐 다시 정의하지 않는다.

  • 사용자가 하는 일을 주어로 쓴다 — "시스템이 처리 중입니다" 같은 수동 문장 대신 사용자가 지금 무엇을 기다리는지, 무엇을 하는지로 쓴다. (판정 항목 아님 — 재작성 관점. quality-bar에 대응 항목이 없다.)
  • 얻는 것으로 말한다 — 손실·불안을 자극하는 프레이밍("놓치면 손해")을 쓰지 않는다(G6-6).
  • 확인 가능한 사실로 쓴다 — 사용자의 감정을 대신 단정하지 않는다 (G6-7).
  • 문장을 나눈다 — 한 문장에 조건·수치를 몰아넣지 않는다(G6-8).
  • 반복하지 않는다 — 같은 주장을 제목·부제·본문에서 표현만 바꿔 되풀이하지 않는다(G6-9).
  • 원인과 다음 행동을 함께 말한다 — 에러 문구는 "오류가 발생했습니다"로 끝내지 않는다(G6-2).
  • 버튼은 결과를 말한다 — "확인"·"완료" 같은 모호한 라벨 대신 눌렀을 때 일어나는 일을 라벨에 담는다. (판정 항목 아님 — 재작성 관점. quality-bar에 대응 항목이 없다.)
  • 어투를 일관되게 유지한다 — 존댓말 수준·숫자 단위 표기를 화면 전반에서 통일한다(G6-1).
  • 언어를 섞지 않는다 — 한 화면 안에서 한국어와 다른 언어를 섞어 쓰지 않는다(G6-4).
  • 사용자를 몰아붙이지 않는다 — 선택을 왜곡하거나 재촉하는 문구를 쓰지 않는다. 패턴 차원(가짜 버튼·닫기 함정 등)의 판정은 G8이 한다 — 여기서는 문구 표현 차원만 본다.

작업 절차

  1. 전수 수집 — 대상 화면의 코드·시안에서 사용자 문구를 훑어 화면별 표로 정리한다: 화면 | 위치(파일·컴포넌트) | 원문.
  2. 축별 점검 — 위 "문구 원칙"의 각 축을 원문에 대조해 위반을 짚는다. 위반이 없으면 그 축은 통과로 표시한다.
  3. before/after 제안 — 위반이 있는 문구마다 대안 문구를 만들고, 무엇이 바뀌었는지 한 줄로 붙인다.
  4. 사용자 확인 후 적용 — 제안을 표로 보여주고, 사용자가 승인한 항목만 실제 코드·문구 파일에 반영한다. 승인 없이 진행하지 않는다.
  5. design G6 재판정으로 hand-off — 반영이 끝나면 design skill로 넘겨 G6를 다시 채점한다(아래 "design과의 관계").

before/after 예시

아래는 이 skill이 새로 쓴 예시다(실제 제품 문구를 그대로 옮긴 것이 아니다). 실제 대상 화면에서는 3단계 절차로 표를 만들어 제안한다.

Read the full file on GitHub · 195 lines

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.

  1. 6d ago First seen · 195 lines · 259 tokens per session scan A bb3230c4836f

Subscribe to this mod's changes

ux-writing is a skill published in the GitHub repository toss/apps-in-toss-harness (186 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 259 tokens to every session and 2,895 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.

Related

Other skills, from other repositories

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

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens