What is ukrainianizer?

A Ukrainian-language editing guide for removing wording that sounds machine-generated. It checks for unnatural expressions, loan translations, bureaucratic wording, repetition, promotional language, and hidden Unicode characters.

Use it to review or rewrite Ukrainian content, especially when checking for Russian-influenced wording, unnecessary formal phrases, AI writing patterns, and hidden text markers.

It helps Ukrainian text sound more natural and less like automatically generated copy. It also removes invisible characters that may have been inserted into the text.

ukrainianizer — Skill for Claude Code and Codex by vitalii4reva

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 vitalii4reva/ukrainianizer --skill ukrainianizer

Clone the repo

git clone --depth 1 https://github.com/vitalii4reva/ukrainianizer

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/vitalii4reva/ukrainianizer/ukrainianizer/github.svg)](https://agentmods.dev/skills/vitalii4reva/ukrainianizer/ukrainianizer)

Your own site

<a href="https://agentmods.dev/skills/vitalii4reva/ukrainianizer/ukrainianizer"><img src="https://agentmods.dev/badge/skills/vitalii4reva/ukrainianizer/ukrainianizer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vitalii4reva/ukrainianizer/ukrainianizer"><img src="https://agentmods.dev/badge/skills/vitalii4reva/ukrainianizer/ukrainianizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,242 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.

Model	Per session	Once invoked
Fable 5.1	$0.00202	$0.02242
Opus 5.5	$0.00081	$0.00897
Sonnet 5.5	$0.00040	$0.00448
Haiku 4.5	$0.00020	$0.00224

Measured 2mo ago against content hash 3073fc457773, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ukrainianizer 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 2mo 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.

SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ukrainianizer v2.0: Професійне видалення AI-патернів з української

Ти — редактор, який виявляє та видаляє ознаки AI-генерованого тексту, щоб він звучав природно по-українськи.

Твоє завдання

Технічна очистка — виявити та видалити приховані Unicode watermarks
Виявити AI-патерни — сканувати текст на всі патерни
Переписати проблемні місця — замінити на природні українські альтернативи
Покращити метрики — підняти burstiness, perplexity, emotional variance
Додати душу — не просто прибрати погане, а додати живе письмо

Словники (завантажуй за потреби)

Русизми: references/rusyzmy.md — найкритичніша проблема
Англіцизми: references/anglicyzmy.md — кальки з англійської
Канцеляризми: references/kancelyaryzmy.md — номіналізації
Плеоназми: references/pleonazmy.md — зайві слова
AI-патерни: references/ai-patterns.md — AI-лексика, промоційна мова, артефакти
Фразеологізми: references/frazeologizmy.md — для додавання живості

КРОК 0: ТЕХНІЧНІ WATERMARKS

Сучасні AI-моделі вбудовують приховані Unicode символи:

U+200B — Zero-Width Space (найчастіший)
U+202F — Narrow No-Break Space (GPT-o3/o4)
U+FEFF — BOM

def clean_watermarks(text):
    invisible = ['\u200B', '\u200C', '\u200D', '\u00A0', '\u00AD', '\u202F', '\u2060', '\uFEFF']
    for char in invisible:
        text = text.replace(char, ' ')
    return ' '.join(text.split())

Онлайн: https://gptcleanup.eu/zero-width-space-remover

УКРАЇНСЬКА ДУША

Стерильний текст без голосу так само очевидний, як і слоп.

Ознаки бездушного тексту

Всі речення однакової довжини (низька burstiness)
Немає думок, лише нейтральне звітування
Немає гумору, гостроти, особистості

Як додати голос

Май думку. "Чесно, я не знаю" — людяніше за нейтральний список
Варіюй ритм. Короткі речення. Потім довші. Міксуй.
Частки: ж, бо, от, ну, та, хіба, невже, адже
Зменшувальні: трішечки, хвилиночку, словечко
Фразеологізми: див. references/frazeologizmy.md
Конкретика: "52 стартапи" замість "багато компаній"

Read the full file on GitHub · 194 lines

Files

What ships with it

6 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.

2mo ago First seen · 194 lines · 202 tokens per session scan A 3073fc457773

Subscribe to this mod's changes

ukrainianizer is a skill published in the GitHub repository vitalii4reva/ukrainianizer (5 stars, last pushed 9mo ago), licensed MIT. It adds 202 tokens to every session and 2,242 once invoked, about $0.0008 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 2026-08-31.

Localization Writing and docs

ukrainianizer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ukrainianizervitalii4reva/ukrainianizer	Skill	5	9mo ago	MIT	A	202	Claude Code, Codex
intl-expansionalirezarezvani/claude-skills	Skill	29k	yesterday	MIT	A	27	Claude Code
azure-ai-translation-text-pymicrosoft/skills	Skill	3.2k	yesterday	MIT	A	60	Claude Code
chinese-documentationjnMetaCode/superpowers-zh	Skill	8.5k	11d ago	MIT	A	62	Claude Code
hardenfengshao1227/ccg-workflow	Skill	6.0k	4d ago	MIT	A	62	Claude Code
edit-sitemicrosoft/power-platform-skills	Skill	1.1k	yesterday	MIT	A	104	Claude Code
asc-subscription-localizationrorkai/app-store-connect-cli-skills	Skill	1.1k	yesterday	MIT	A	60	Claude Code