What is uzbek-humanize?

A slash-command workflow for translating websites and applications into natural Latin Uzbek, the Uzbek writing system used with Latin letters.

Use it to add Uzbek locale files, connect internationalization settings, build a language switcher, translate interface copy, and normalize Uzbek text.

It helps add Uzbek language support without changing translation keys or producing stiff, unnatural interface text.

uzbek-humanize — Skill for Claude Code by xusnitdinov

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 xusnitdinov/uzbek-humanizer --skill uzbek-humanize

Clone the repo

git clone --depth 1 https://github.com/xusnitdinov/uzbek-humanizer

Made for: Claude Code.

Or install uzbek-humanizer, the plugin that ships this one along with the rest of its 2 skills.

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/xusnitdinov/uzbek-humanizer/uzbek-humanize/github.svg)](https://agentmods.dev/skills/xusnitdinov/uzbek-humanizer/uzbek-humanize)

Your own site

<a href="https://agentmods.dev/skills/xusnitdinov/uzbek-humanizer/uzbek-humanize"><img src="https://agentmods.dev/badge/skills/xusnitdinov/uzbek-humanizer/uzbek-humanize/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/xusnitdinov/uzbek-humanizer/uzbek-humanize"><img src="https://agentmods.dev/badge/skills/xusnitdinov/uzbek-humanizer/uzbek-humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,974 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	$0.00080	$0.01974
Opus 5	$0.00040	$0.00987
Sonnet 5	$0.00016	$0.00395
Haiku 4.5	$0.00008	$0.00197

Measured 10d ago against content hash 67f805bc2dcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

uzbek-humanize 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 10d 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.

skills/uzbek-humanize/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/uzbek-humanize

Slash workflow for wiring websites/apps into Latin Uzbek (i18n files, locale config, switcher) with natural copy.

Sister skill boundary

Skill	Owns
`uzbek-humanize` (this slash)	Project i18n: locale JSON, keep keys, next-intl / routing / switcher, edit files when asked
`uzbek-humanizer` (sister)	Uzbek text quality: Siz, soft synonyms, calques, orthography. Load its refs while translating values

User must type /uzbek-humanize. Do not confuse with auto uzbek-humanizer.

Hard product rules (from sister)

Locale values for UI/quiz = Siz only (qilasiz, not qilasan)
Situation-natural verbs (Guruh ishi oʻxshamadi not chiqmadi for "didn't work out")
Orthography ʻ/ʼ - run sister normalize on Uzbek values only; never corrupt Who's / EN locale
After file edits, still print Matn samples + Oʻzgarishlar + Holat in chat
Calque-safe draft - high-stakes quiz/marketing → draft/native_review_required until native pass

How the user invokes it

/uzbek-humanize add Uzbek to this Next.js site - translate UI + landing
/uzbek-humanize localize src/locales/en.json into uz.json with natural Uzbek
/uzbek-humanize translate these React strings to o'zbekcha and keep keys stable
/uzbek-humanize add i18n for Uzbek on this Vite app

Whatever comes after /uzbek-humanize is the task. If empty, ask what to localize (routes, locale files, components).

Goal

Ship spoken clear product/student Latin Uzbek that a real user in Toshkent would accept - not textbook MT, not EN calques, not ASCII ' spam.

Workflow

Inspect the project - find how languages are handled:
- locale JSON/YAML (en.json, messages/en.json, …)
- i18n libs (next-intl, react-i18next, vue-i18n, …)
- hardcoded EN strings in components
- CMS / markdown content
Match existing patterns - same file layout, same key names, same plural / ICU shape the project already uses. Prefer adding uz / uz-UZ the way en already works.
Load sister skill - if uzbek-humanizer is installed next to this skill, follow its Router, gotchas, Holat gate, and glossaries (references/ui-glossary.md, microcopy.md, legal-copy.md, …). Prefer editing locale files over scattering hardcodes - unless the project has no i18n yet and the user asked you to introduce it.
Translate / humanize - natural UZ (keep keys; translate values):
- Buttons short (Saqlash, Bekor qilish, Roʻyxatdan oʻtish)
- Errors soft and clear
- Orthography: oʻ/gʻ with ʻ, tutuq with ʼ - no ASCII '
- One address lane (Siz for product UI)
- Ban EN cool calques (select qil, ship, vibe, stiff haqiqatan ham)
- Latin default - do not ship Cyrillic in the Uzbek site locale unless the user asked
Wire the language if asked - locale config, language switcher label (Oʻzbekcha), routing (/uz/...), hreflang only when the stack already supports it or the user asked for wiring.
Do not invent whole legal ToS / medical advice - mark draft/native_review_required.
Output - make the code/file changes the user asked for. Also summarize:

Read the full file on GitHub · 159 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.

10d ago First seen · 159 lines · 80 tokens per session scan A 67f805bc2dcb

Subscribe to this mod's changes

uzbek-humanize is a skill published in the GitHub repository xusnitdinov/uzbek-humanizer (2 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,974 once invoked, about $0.0004 per session on Opus 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.

Claude Code Localization agent-skills copilot cursor i18n npm-package

video-translate

Translate and dub existing videos into multiple languages using HeyGen. Use when: (1) Translating a video into another language, (2) Dubbing video content with lip-sync, (3) Creating multi-language versions of existing videos, (4) Audio-only translation without lip-sync, (5) Working with HeyGen's /v2/videotranslate…

calesthio/OpenMontage · 77 tokens

french-language

Ensures all project content is written in proper French with correct accents, grammar, and typography. Use when user mentions french, français, langue française, accents, orthographe, typographie, or when working on a project that requires French language content. Also use when generating any text-based file (SVG…

rlespinasse/agent-skills · 100 tokens

globalize-now-cli-use

Manage Globalize translation resources using the CLI. Use this skill when the user asks to create a translation project, add or remove languages, connect a GitHub or GitLab repository, manage glossaries or style guides, invite team members, manage API keys, or perform any Globalize platform operation. Also use when…

globalize-now/globalize-skills · 110 tokens

globalize-now-project-setup

Create a Globalize translation project, connect a GitHub or GitLab repository, and set catalog file patterns. Use this skill when the user asks to create a Globalize project, connect their repo to Globalize, or wire their translation catalogs to the Globalize platform. Assumes the Globalize CLI is already installed…

globalize-now/globalize-skills · 107 tokens

css-i18n

Audit and convert CSS to use logical properties for RTL/bidirectional layout support. Use when the user asks to "make CSS RTL-safe", "use logical properties", "replace left/right with start/end", "audit CSS for i18n", "CSS internationalization", "fix CSS for RTL", "convert to logical properties", or when setting up…

globalize-now/globalize-skills · 123 tokens

globalize-now-account-setup

Install the Globalize CLI, authenticate, and verify your organization. Use this skill when the user asks to set up Globalize, install the Globalize CLI, sign in or authenticate with Globalize, or connect their Globalize account. Also use when the user mentions @globalize-now/cli-client or globalise-now-cli and needs…

globalize-now/globalize-skills · 127 tokens