Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Thalarch Localization

ASecurity

Localization and i18n quality workflow for multi-locale applications. Use when adding or changing user-facing strings, locale resources, plurals, formatting, RTL behavior, or when a UI redesign must remain complete and natural across all languages supported by the project.

2 stars
0 votes
0 copies
3 views
Added 9/19/2026
ai-agentsgit

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add LUC4N3X/antigravity-thalarch --skill thalarch-localization --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Thalarch Localization?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Thalarch Localization
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/luc4n3x-thalarch-localization/badge)](https://www.skillsdirectory.com/skills/luc4n3x-thalarch-localization)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: thalarch-localization
description: >
  Localization and i18n quality workflow for multi-locale applications. Use when adding or changing
  user-facing strings, locale resources, plurals, formatting, RTL behavior, or when a UI redesign
  must remain complete and natural across all languages supported by the project.
---

# Thalarch Localization

Localization completeness is a product contract, not a side effect of the default locale compiling.

## 1. Discover the real locale surface

Inspect the repository rather than assuming a language list.

Identify:

- default locale resources;
- all translated locale/resource sets;
- plural/select resources;
- locale-specific assets/layout behavior where present;
- existing translation conventions and terminology;
- generated/localization tooling if the project uses one.

Do not add a new parallel i18n system when the project already has one.

## 2. Key parity

For changed user-facing strings, check:

- missing keys;
- extra/stale keys when relevant;
- duplicate keys;
- raw/unresolved key display risk;
- fallback to the default language that would create mixed-language screens.

A successful default-locale build does not prove translated resource parity.

## 3. Placeholder and formatting safety

Preserve the semantic contract of:

- positional placeholders such as `%1$s`, `%2$d`;
- number/date/time formatting;
- plural quantities;
- escaped apostrophes/quotes where the resource format requires them;
- markup/spans;
- newline intent;
- parameter order differences across languages.

Never "fix" a translation by deleting a placeholder needed by call-site logic.

## 4. Natural terminology

Translate for the product/domain, not word-by-word.

For established technical/product terms, determine whether the target locale normally:

- translates them;
- transliterates them;
- keeps the standard English/product spelling.

Terms such as `Equalizer`, `ReplayGain`, `Crossfade`, `Preamp`, codec names, protocol names, or brand
names may legitimately remain unchanged in some locales. Avoid awkward literal translations that a
native user would not recognize.

Do not invent premium/marketing wording absent from the source product intent.

## 5. Layout expansion

Review changed UI for:

- longer translations;
- wrapping;
- ellipsis/truncation;
- button width;
- chips/tabs/segmented controls;
- slider labels/units;
- dialog height;
- small-screen overflow;
- font scaling.

Short English source strings are not a safe layout bound.

## 6. RTL

For supported RTL locales, inspect:

- mirrored navigation/directional icons;
- start/end vs left/right alignment;
- padding/margins;
- row ordering when directionally meaningful;
- mixed LTR technical tokens inside RTL text;
- number/unit readability.

Prefer platform-aware start/end semantics and AutoMirrored icon variants where appropriate.

## 7. Translation review strategy

When authoritative human translations are unavailable:

- preserve existing project terminology;
- keep phrasing concise and idiomatic;
- avoid adding semantic claims not present in the source;
- flag uncertain high-impact wording rather than fabricating domain meaning.

Machine-generated text may be a draft, not proof of native-quality localization.

## 8. Automated checks

When practical, add or run checks for:

- key parity;
- placeholder signature parity;
- malformed resource syntax;
- duplicate identifiers;
- unresolved localization keys;
- locale resource compilation.

Keep checks aligned with the project's real resource format rather than installing a new framework
for a small change.

## 9. Rendered verification

For a UI change, combine with `thalarch-compose-ui` or the relevant platform UI skill.

Render representative locales, especially:

- one language with longer labels;
- one RTL locale when supported;
- the default locale.

Source-resource parity does not prove clipping, wrapping, or visual hierarchy.

## 10. Completion report

State:

- locales discovered;
- keys changed;
- parity/placeholder checks run;
- representative rendered locales tested;
- any translations/layouts still `UNVERIFIED`.

Attribution

LUC4N3XLUC4N3X
View sourceSee grades on GitHubMore from LUC4N3X →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

697551 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →