Cometchat I18n Agent Skill

Localization (i18n) across all CometChat UI Kit families — React, React Native, Angular, Android (V5/V6), iOS, Flutter (V5/V6).

Context cost
1.9k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 7.7 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
—v1.0.0
Servers it uses
Noneruns standalone

What it does

Localize a CometChat integration — set the UI Kit language, register custom/overridden translations, handle RTL, and never leak a raw localization key into the UI. Cross-family: the mechanism is CometChatLocalize on React, Angular, iOS and Android, while React Native uses CometChatI18nProvider (there is no CometChatLocalize in the RN kit); the exact signature is fetched from each family's localize doc.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

androidflutteriosmobilereact

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md7.7 kB · preview
--- name: cometchat-i18n license: "MIT" compatibility: "CometChatLocalize on React v7 · Angular v5 · iOS v5 · Android v6. React Native v5 uses CometChatI18nProvider + the useCometChatTranslation hook (no CometChatLocalize in the RN kit). Flutter v6 is moving to CometChatLocalize but the shipping 6.1.0 kit uses Translations (staged). Exact API per family+major from that family's localize docs." metadata: author: "CometChat" version: "1.0.0" tags: "cometchat i18n localization localize rtl language translations cometchatlocalize" ---
12> **Ground truth:** localization is the **CometChatLocalize** class on **React, Angular, iOS and Android**. Two exceptions: **React Native** uses **CometChatI18nProvider** + the **useCometChatTranslation** hook (there is no CometChatLocalize in the RN kit — catalog-confirmed), and **Flutter** is moving to CometChatLocalize but the shipping **6.1.0** kit still exposes **Translations** (see cometchat-flutter-v6-customization → Localization — **STAGED** pending the kit). Exact methods and built-in string keys differ by family and major — **FETCH the signature from the resolved family's localize doc** via cometchat-<family>-core/references/docs-map.md (intent: localization / localize). Do not carry an API across families or majors (v6 React, for one, renamed language codes and keys). Never assert a key set from memory — look it up in the kit's resources/<lang>/translation.json / the localize page.
13
14## Use this skill when
15Making the chat speak another language, shipping to a multi-locale or RTL market, adding/overriding wording, or fixing a UI that shows a raw key (e.g. group_info) instead of text.
16
17## The mechanism (per family, one shape)
18Most UI Kits localize through CometChatLocalize (React Native is the exception — it uses CometChatI18nProvider + the useCometChatTranslation hook): it can **detect** the user's browser/device language and **set** the active locale, and it exposes the current locale to components (which read their strings from it). The three things you do:
191. **Set the locale** — let it auto-detect, or set it explicitly to match your app's language switcher. Do this **before** the surface renders (alongside init), so components mount already localized. (React v7: pass the locale prop on CometChatProvider — <CometChatProvider locale="fr"> — applied on mount/change.)
202. **Register custom / overridden translations** — add your own strings or override the kit defaults per locale (e.g. React v7: CometChatLocalize.getSharedInstance()?.addTranslation({ "en-us": { key: "value" } }) — an **INSTANCE** method taking a **nested per-language** map; reach the live instance via getSharedInstance(), never new CometChatLocalize(); other families have the equivalent — **React Native** instead uses the CometChatI18nProvider **translations** prop, keyed on the **active** language code: under the default auto-detect that's the 2-letter device code, so use translations={{ "en": { KEY: "value" } }} — a regional key like en-US is ignored unless you also pass selectedLanguage="en-US", and codes must match the kit's keys **exactly (case-sensitive)** — e.g. zh-tw is lowercase but en-US/en-GB are uppercase-region; not addTranslation. Provider props: selectedLanguage · autoDetectLanguage · translations · fallbackLanguage — {DOCS_BASE}/ui-kit/react-native/localize). Fetch the exact call for your family.
213. **Read a string yourself** where you render kit text in your own markup — use the family's localized-string accessor (React v7: useLocale().getLocalizedString(key)), never a hardcoded English literal.
22
23The exact class methods, the supported language list, and the key namespace are per family+major — **fetch them**; this file is the discipline, the docs are the signatures.
24
25## Never render a raw key
26A snake_case token in the UI (group_info, add_members, sample_*) means a **missing or wrong key** — the localizer returns the key on a miss. Causes and fixes:
27- The component isn't inside the kit provider/localization context → wrap it (the provider auto-wires localization).
28- The key changed across majors (v5→v6/v7 moved keys, some under sample_*) → look up the CURRENT key in the kit's resources/<lang>/translation.json or the localize doc; don't guess.
29- You hardcoded a raw key as a label → use the component or the localized-string accessor.
30
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,074 words
Files1
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈290
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,635
on trigger
The instruction body, read only when the skill fires.
0.96%
of a 200k window
Ten skills this size would take about 10% of the window before you open a file.
050k100k150k200k context window

1.9k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 7.7 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md7.7 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Cometchat I18n · 1.9k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/cometchat-i18n/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/cometchat-i18n" ] && { [ ! -e .claude/skills/cometchat-i18n ] || { mv .claude/skills/cometchat-i18n "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/cometchat-i18n" .claude/skills/ && echo "Installed .claude/skills/cometchat-i18n"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add cometchat/cometchat-i18n

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/cometchat-i18n/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/cometchat-i18n/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/cometchat-i18n" ] && { [ ! -e ~/.claude/skills/cometchat-i18n ] || { mv ~/.claude/skills/cometchat-i18n "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/cometchat-i18n" ~/.claude/skills/ && echo "Installed ~/.claude/skills/cometchat-i18n" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/cometchat-i18n/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0.0
Publishedno release date on file
PriceFree
Referencecometchat/cometchat-i18n

Versions

v1.0.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers1
Claim this skill