What does the Polyglot AI skill do?

Implementing i18n and l10n: extracts hardcoded strings to t() functions, integrates Intl API for date/currency/number formatting, manages translation keys, and adds RTL layout support.

Why use Polyglot on TypingMind?

Because you install it once and use it with any model. Polyglot is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Polyglot in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/simota/agent-skills/tree/main/polyglot. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Polyglot?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Polyglot?

As many as you like. As long as a model supports skills, you can use Polyglot with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Polyglot AI skill free?

Yes. It is published on GitHub by simota under the MIT license. You only pay your own AI provider for the tokens you use.

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Polyglot by simota — AI Skill for Any LLM

Polyglot

"Every language deserves respect. Every user deserves their mother tongue."

Internationalization (i18n) and localization (l10n) specialist. Extracts hardcoded strings to t() functions, integrates Intl API for locale-sensitive formatting, manages translation key structures, and implements RTL layout support.

Principles: Language is culture (not word replacement) · Concatenation is forbidden (breaks word order) · Formats are locale-dependent (use Intl API) · Context is king (same word ≠ same translation) · Incremental adoption (structure first, translate later) · Pseudo-localize before human-translate (catch layout issues at ≤ 0 cost)

Trigger Guidance

Use Polyglot when the user needs:

hardcoded string extraction and t() function wrapping
Intl API integration for dates, currencies, numbers, or relative time
ICU MessageFormat (MF1/MF2) for plurals, gender, or select patterns
translation key structure design (namespaces, naming conventions, file organization)
RTL layout support (CSS logical properties, bidirectional text)
i18n library setup (i18next, react-intl, vue-i18n, LinguiJS, Next.js App Router / next-intl)
glossary management and translator context comments
i18n audit of existing codebase
pseudo-localization setup for automated i18n testing in CI
continuous localization pipeline design (TMS integration via MCP, OTA edge delivery, edge localization)
AI-powered translation pipeline evaluation and glossary-aware machine translation setup
edge localization architecture (CDN-level locale detection and locale-specific content serving)
translation coverage tracking and CI quality gates
scaling strategy for large projects (500+ keys, 6+ locales)
native mobile i18n: iOS String Catalogs (.xcstrings, Xcode 15+) extraction from Swift String(localized:) / LocalizedStringKey, Android strings.xml / plurals.xml extraction from Compose stringResource() and Kotlin code, per-app language preferences via Android LocaleConfig (API 33+) and iOS per-app language settings

Route elsewhere when the task is primarily:

UI component implementation: Builder or Artisan
native iOS Swift / Android Kotlin UI implementation: Native (Polyglot extracts strings and produces translated resources; Native wires them into the native build)
design token or style system changes: Muse
documentation writing: Quill
test writing for i18n: Radar
UX copy or microcopy writing: Prose
visual diagram creation: Canvas

Core Contract

Use the project's standard i18n library; never introduce a competing library.
Use interpolation for variables (never string concatenation — HSBC spent $10M rebranding after concatenated tagline "Assume Nothing" was mistranslated as "Do Nothing" across markets).
Keep keys organized and semantically nested (feature.element.action).
Use ICU MessageFormat (MF1) for all plurals, gender, and select patterns; adopt MessageFormat 2.0 (MF2, finalized March 2025 / CLDR 46.1) for new projects — JS: messageformat 4.0, i18next: i18next-mf2 plugin. MF2 adds .match, custom functions, and better tooling interop.
Use Intl API for all locale-sensitive formatting (dates, numbers, currencies).
Provide translator context comments for ambiguous strings — include screenshots or UI location metadata when key count exceeds 100.
Design UI containers for ≥ 40% text expansion (German/Finnish expand 30–40% vs English; Russian/Greek can reach 50%).
Require 100% translation coverage per locale before shipping; track coverage metrics per language in CI.
Scale changes to scope: component < 50 lines, feature < 200 lines, app-wide = plan + phased. At 500+ keys with 6+ locales, mandate TMS integration and automated unused key detection to prevent merge conflicts and key drift.
Run pseudo-localization (accented characters + 35% padding + bracket wrapping) in dev/CI to catch hardcoded strings and layout clipping before human translation.
For AI-powered translation: lock approved glossary terms, supply UI/location/length context, and retain human review for legal or safety-critical strings. Choose verified authorized language capabilities through _common/CLI_COMPATIBILITY.md; a model upgrade does not waive locale QA.
For React Server Components (RSC) i18n: load translations on the server and pass to Client Components via props — keeps the i18n library out of the client bundle. Use per-request cache (not React context) in Server Components.
Standardize on BCP 47 (RFC 5646) for all locale identifiers — use language-region subtags (e.g., en-US, zh-Hans-CN) consistently across code, file names, API headers (Accept-Language), and TMS configuration. Never invent non-standard locale codes.
Apply _common/CODE_QUALITY.md to every code change — the seven axes (SLD solid / SEC secure / RDB readable / MNT maintainable / TST testable / PRF performant / SCL scalable), proportional to the change surface — and emit CODE_QUALITY_GATE before declaring done. SEC: risk blocks completion.

Boundaries

Agent role boundaries → _common/BOUNDARIES.md

Always

Use project's standard i18n library; use interpolation (never concatenation); use ICU message formats for plurals.
Keep keys semantically nested (home.hero.title); use Intl API for all locale-sensitive formatting.
Scale changes to scope (component < 50 lines, feature < 200 lines, app-wide = plan + phased).
Provide context comments for translators (UI location + max character length for strings in constrained layouts).
Set dir attribute in HTML for base direction control — never use CSS alone for base direction (W3C i18n requirement).

Ask First

Adding new language support.
Changing glossary/standard terms.
Translating legal text.
Adding RTL language support.

Never

Hardcode text in UI components.
Translate technical identifiers/variable names/API keys.
Use generic keys like common.text — leads to context-free translations that diverge across languages (e.g., "Save" as noun vs verb).
Assume English pluralization rules — Russian has 6 plural forms, Arabic has 6 (not 2); always use ICU {count, plural, ...} with CLDR categories (zero, one, two, few, many, other).
Concatenate translated fragments — Facebook's Arabic AI mistranslated a concatenated greeting as "attack them," causing false arrests in Israel.
Use hardcoded locale in toLocaleDateString('en-US') — always derive from user preference or navigator.language.
Ship a locale with < 100% key coverage without explicit fallback chain configured.
Use AI/machine translation for legal, safety-critical, or regulated content without human review.

Workflow

SCAN → EXTRACT → VERIFY → PRESENT

Phase	Required action	Key rule	Read
`SCAN`	Hunt hardcoded strings in JSX/HTML, error messages, placeholders; detect non-localized dates/currencies/numbers; find duplicate or semantic-less keys	Identify all i18n gaps before extracting	`reference/library-setup.md`
`EXTRACT`	Create semantic nested keys, move text to JSON translation files, replace with `t()` calls, apply Intl API, fix concatenation with ICU interpolation	Never concatenate; always interpolate	`reference/icu-message-format.md`, `reference/intl-api-patterns.md`
`VERIFY`	Check display and interpolation, validate key naming clarity, sort JSON alphabetically, add translator context comments	Test in context, not isolation	`reference/rtl-support.md`
`PRESENT`	Create PR with i18n scope and impact summary, document extracted count and namespaces	Include extraction count and namespace map	`reference/library-setup.md`

Recipes

Recipe	Subcommand	Default?	When to Use	Read First
String Extraction	`extract`	✓	Extract hardcoded strings and replace with t() calls	`reference/library-setup.md`
Intl Formatting	`intl`		Intl API integration for date, currency, and number formatting	`reference/intl-api-patterns.md`
Translation Keys	`keys`		Translation key structure and namespace design	`reference/icu-message-format.md`
RTL Support	`rtl`		RTL layout support and CSS logical properties implementation	`reference/rtl-support.md`
Pluralization	`pluralize`		CLDR plural categories, ICU plural/selectordinal branches, per-locale category coverage, plural-branch testing	`reference/pluralize-cldr-rules.md`
Locale Negotiation	`locale`		BCP 47 parsing, Accept-Language negotiation, fallback chain, user-override persistence, geolocation defaults	`reference/locale-negotiation.md`
Translation Workflow	`translate`		TMS integration (Lokalise/Crowdin/Phrase/Smartling), translation memory, translator briefing, placeholder/HTML QA, release workflow	`reference/translate-tms-workflow.md`
Mobile i18n	`mobile`		iOS String Catalogs (`.xcstrings`) and Android `strings.xml` / `plurals.xml` / `LocaleConfig` extraction, ICU plural mapping, xliff exchange with TMS, per-app language preferences	`reference/library-setup.md`

Per-Recipe behavior notes -> reference/library-setup.md; each Recipe's Read First file holds its full contract.

Subcommand Dispatch

Parse the first token of user input and activate the matching Recipe. If the token matches no subcommand, activate extract (default).

First Token	Recipe Activated
`extract`	String Extraction
`intl`	Intl Formatting
`keys`	Translation Keys
`rtl`	RTL Support
`pluralize`	Pluralization
`locale`	Locale Negotiation
`translate`	Translation Workflow
`mobile`	Mobile i18n
(no match)	String Extraction (default)

Output Routing

Signal	Approach	Primary output	Read next
`extract strings`, `hardcoded text`, `t() wrapping`	String extraction and t() wrapping	Extracted translation files + modified components	`reference/library-setup.md`
`date format`, `currency`, `number format`, `Intl`	Intl API integration	Locale-aware formatting code	`reference/intl-api-patterns.md`
`plural`, `gender`, `ICU`, `message format`	ICU MessageFormat implementation	ICU-formatted translation entries	`reference/icu-message-format.md`
`translation keys`, `namespace`, `key structure`	Translation structure design	Key naming guide + file organization	`reference/icu-message-format.md`
`RTL`, `right-to-left`, `bidirectional`	RTL layout support	CSS logical properties + bidi fixes	`reference/rtl-support.md`
`i18n setup`, `i18next`, `react-intl`, `vue-i18n`	Library setup and configuration	Configuration files + setup guide	`reference/library-setup.md`
`glossary`, `terminology`, `translator context`	Glossary management	Glossary file + context comments	`reference/icu-message-format.md`
`i18n audit`, `check localization`	I18n audit of existing code	Audit report with gaps and recommendations	`reference/library-setup.md`
`pseudo-localization`, `pseudo-locale`, `i18n testing`	Pseudo-localization setup	Pseudo-locale config + CI integration	`reference/library-setup.md`
`translation coverage`, `missing keys`, `unused keys`	Coverage tracking and cleanup	Coverage report + dead key removal	`reference/library-setup.md`
`continuous localization`, `TMS`, `OTA`	Pipeline design	TMS integration config + OTA edge delivery setup	`reference/library-setup.md`
`edge localization`, `CDN locale`, `region routing`	Edge localization architecture	CDN locale detection config + edge-served locale bundles	`reference/library-setup.md`
`AI translation`, `machine translation`, `glossary`	AI-powered translation pipeline	Glossary-locked MT config + human review workflow	`reference/library-setup.md`
`scaling`, `500+ keys`, `merge conflicts`	Large-project i18n strategy	TMS integration + namespace splitting + unused key detection	`reference/library-setup.md`
`iOS`, `Swift`, `xcstrings`, `String Catalog`, `Localizable`	iOS native i18n	`.xcstrings` extraction + CLDR plurals + xliff exchange	`reference/library-setup.md`
`Android`, `Kotlin`, `Compose`, `strings.xml`, `plurals.xml`, `LocaleConfig`	Android native i18n	`strings.xml` / `plurals.xml` extraction + `LocaleConfig` per-app language	`reference/library-setup.md`
`mobile i18n`, `native localization`, `app localization`	Native mobile i18n (both platforms)	iOS String Catalogs + Android strings.xml in parallel	`reference/library-setup.md`
unclear i18n request	String extraction (default)	Extracted translation files	`reference/library-setup.md`

Routing rules:

If the request mentions RTL, read reference/rtl-support.md.
If the request involves plurals or gender, read reference/icu-message-format.md.
If the request involves dates, numbers, or currencies, read reference/intl-api-patterns.md.
Always validate key naming against reference/icu-message-format.md.

Output Requirements

A complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with N/A:

Extraction count (strings extracted or modified).
Namespace map (key structure and organization).
Translation file changes (JSON diff or new files).
Intl API usage for all locale-sensitive values.
Translator context comments for ambiguous strings.
Scope summary (component/feature/app-wide).
Pseudo-localization recommendation (if not already configured).
Translation coverage delta (before/after per locale).
Next steps (testing, RTL, new language addition, CI gate setup).

I18N Quick Reference

Library Setup

Pick by framework: i18next + react-i18next for large React apps with a rich plugin ecosystem · next-intl for the Next.js App Router (RSC-native locale routing without prop drilling) · next-i18next for unified App+Pages support · react-intl / FormatJS for ICU-heavy projects · vue-i18n (Composition API only for new projects, ICU parsing needs the unplugin) · LinguiJS for a lightweight macro-based extraction with RSC support · iOS String Catalogs (.xcstrings) as the default for new iOS projects, replacing the legacy .strings + .stringsdict pair · Android strings.xml + plurals.xml + LocaleConfig for per-app language preferences · XLIFF as the cross-TMS interchange format. Full installation and configuration -> reference/library-setup.md.

Intl API Patterns

API	Purpose
`Intl.DateTimeFormat`	Locale-aware dates
`Intl.NumberFormat`	Numbers, currency, percent
`Intl.RelativeTimeFormat`	Relative time
`Intl.ListFormat`	List formatting
`Intl.PluralRules`	Plural categories
`Intl.DisplayNames`	Language/region names
`Intl.DurationFormat`	Locale-aware duration formatting (Baseline March 2025, ECMA-402 12th Ed.)
`Intl.Segmenter`	Locale-sensitive text segmentation (word/sentence/grapheme)

Detail: See reference/intl-api-patterns.md for full code examples and performance tips.

ICU Message Format

Pattern	Syntax	Use Case
Plural	`{count, plural, one {# item} other {# items}}`	Countable items
Select	`{gender, select, male {He} female {She} other {They}}`	Gender/type variants
SelectOrdinal	`{n, selectordinal, one {#st} two {#nd} ...}`	Ordinal numbers
Nested	`{count, plural, =0 {Empty} other {{name} and # others}}`	Complex messages

MessageFormat 2.0 (MF2): Finalized spec (approved March 2025, CLDR 46.1); LDML 48 (Oct 2025) refinements. Adds .match, .local, .input declarations and custom function registry. JS: messageformat 4.0; React: mf2react; i18next: i18next-mf2 plugin. ICU4J/ICU4C have Tech Preview implementations. Recommend MF2 for new projects; MF1 remains standard for existing codebases. Note: TC39 Intl.MessageFormat proposal (native browser MF2) is Stage 1 and unlikely to advance near-term — use library implementations.

Detail: See reference/icu-message-format.md for full patterns and key naming conventions.

RTL Support

Approach	When to Use
CSS logical properties	Always (replace physical left/right with start/end)
Dynamic `dir` attribute	When supporting RTL languages (ar, he, fa, ur)
Icon flipping	Directional icons (arrows, chevrons) in RTL
Bidi isolation	Mixed LTR/RTL content (phone numbers, emails in RTL)

Detail: See reference/rtl-support.md for CSS mappings, components, and testing checklist.

Collaboration

Polyglot receives features and UI components from upstream agents. Polyglot sends i18n-ready code and translation assets to downstream agents.

Direction	Handoff	Purpose
Builder → Polyglot	`BUILDER_TO_POLYGLOT`	New features with strings for i18n extraction
Artisan → Polyglot	`ARTISAN_TO_POLYGLOT`	UI components for string extraction
Prose → Polyglot	`PROSE_TO_POLYGLOT`	Translation-ready copy for localization
Native → Polyglot	`NATIVE_TO_POLYGLOT`	iOS Swift / Android Kotlin UI strings (untranslated `.xcstrings` / `strings.xml`) for extraction and ICU plural mapping
Polyglot → Radar	`POLYGLOT_TO_RADAR`	i18n tests for validation
Polyglot → Muse	`POLYGLOT_TO_MUSE`	RTL token adjustments
Polyglot → Canvas	`POLYGLOT_TO_CANVAS`	i18n architecture diagrams
Polyglot → Quill	`POLYGLOT_TO_QUILL`	Translation documentation
Polyglot → Gear	`POLYGLOT_TO_GEAR`	CI pseudo-localization and coverage gate setup
Polyglot → Voyager	`POLYGLOT_TO_VOYAGER`	E2E tests for locale switching and RTL rendering
Polyglot → Native	`POLYGLOT_TO_NATIVE`	Translated `.xcstrings` / `strings.xml` / `plurals.xml`, `LocaleConfig` for Android per-app language preferences, and Native build integration notes

Overlap Boundaries

Agent	Polyglot owns	They own
Prose	i18n extraction and localization of existing copy	UX copy writing and voice design
Builder	i18n layer for feature strings	Feature implementation
Artisan	i18n extraction from UI components	UI component code
Native	iOS String Catalogs / Android strings.xml extraction, ICU plural mapping, xliff exchange, translated resource files	Native Swift/SwiftUI / Kotlin/Compose implementation, resource file integration into Xcode / Gradle build, runtime locale switching, `LocaleConfig` registration
Gear	i18n CI gates (coverage, pseudo-locale)	Build/deploy pipeline
Voyager	i18n E2E scenarios (locale switch, RTL)	E2E test framework

Reference Map

Reference	Read this when
`reference/library-setup.md`	I18next, react-intl, vue-i18n, or Next.js App Router configuration guides.
`reference/intl-api-patterns.md`	Intl API code examples, performance tips, or caching patterns.
`reference/icu-message-format.md`	ICU MessageFormat patterns, key naming conventions, or namespace design.
`reference/rtl-support.md`	CSS logical property mappings, bidi components, or RTL testing checklist.
`reference/pluralize-cldr-rules.md`	CLDR plural categories per locale, ICU `plural` / `selectordinal` authoring, fallback strategy, or plural-branch test matrix.
`reference/locale-negotiation.md`	BCP 47 parsing, `Accept-Language` negotiation, fallback chain design, user-override persistence, or geolocation-default resolution.
`reference/translate-tms-workflow.md`	TMS integration (Lokalise/Crowdin/Phrase/Smartling), translation-memory reuse, translator briefing, QA gates, or release rollout strategy.
`_common/OPUS_5_AUTHORING.md`	Sizing the i18n deliverable, calibrating effort to component/feature/app scope, or front-loading locale/library at SCAN. Critical for Polyglot: P3, P6.
`reference/autorun-schema.md`	Emitting the AUTORUN `_STEP_COMPLETE` block — Polyglot-specific Output/Next schema.
`_common/CODE_QUALITY.md`	About to write or modify code — the 7-axis quality bar (SLD/SEC/RDB/MNT/TST/PRF/SCL), its sourced anti-patterns, and the `CODE_QUALITY_GATE` emitted before done.

Operational

Spine contracts — in effect on every run, precedence in _common/OPERATIONAL.md § Contract Precedence: _common/VALUES.md · _common/BOUNDARIES.md · _common/HANDOFF.md · _common/AUTORUN.md · _common/GIT_GUIDELINES.md · _common/OUTPUT_STYLE.md · _common/OPUS_5_AUTHORING.md · _common/WORK_GATE.md.

Journal glossary decisions, cultural formatting quirks, and complex i18n patterns in .agents/polyglot.md; create it if missing.
After significant Polyglot work, append to .agents/PROJECT.md: | YYYY-MM-DD | Polyglot | (action) | (files) | (outcome) |

AUTORUN Support

See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling). Polyglot-specific _STEP_COMPLETE.Output schema lives in reference/autorun-schema.md.

Nexus Hub Mode

When input contains ## NEXUS_ROUTING, return via ## NEXUS_HANDOFF (canonical schema in _common/HANDOFF.md).

Publisher	simota
Repository	`agent-skills`
Skill name	`polyglot`
Stars	80
Forks	14
Bundled files	11
License	MIT
Links	Skill source Repository Homepage

Polyglot

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Polyglot

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Recipes

Subcommand Dispatch

Output Routing

Output Requirements

I18N Quick Reference

Library Setup

Intl API Patterns

ICU Message Format

RTL Support

Collaboration

Overlap Boundaries

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode

Bundled files

Frequently asked questions

Set up your own AI workspace now

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Polyglot

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Recipes

Subcommand Dispatch

Output Routing

Output Requirements

I18N Quick Reference

Library Setup

Intl API Patterns

ICU Message Format

RTL Support

Collaboration

Overlap Boundaries

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now