agentleFS
fritzprixfritzprix/libr-agent/.agents/skills/i18n-language-standards/SKILL.md

i18n-language-standards

Skill12 starsChanged 6 days agoMITView on GitHub

Enforce ASD-STE100 (English) and clear Korean UI language standards across LibrAgent. Audits UI text, Settings descriptions, and i18n locales for prohibited engineering jargon, internal code identifiers (browser="userChrome", awaitAgent, pollProcess, createSession), passive translations, and ensures terminology parity across all 8 supported languages. Triggers on: "언어 규약", "language standards", "i18n standards", "ASD-STE100", "i18n audit", "i18n 검증", "언어 규약 검사", "layman-friendly UI text", "i18n-language-standards".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never expose code syntax or internal function names in user-facing text.

    line 19
  2. Very specific:

    All settings keys and UI strings must maintain semantic and structural parity across en, ko, ja, zh, de, fr, es, and pt.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

i18n Language Standards & Enforcement

This skill defines, audits, and enforces user-facing language standards across LibrAgent. It ensures that UI labels, settings descriptions, tool documentation, and i18n locales adhere to ASD-STE100 for English and Clear Korean UI Standards for Korean, while maintaining rigorous parity across all 8 supported languages (en, ko, ja, zh, de, fr, es, pt).

1. Core Principles

  1. No Internal Code Identifiers in UI:
    • Never expose code syntax or internal function names in user-facing text.
    • Prohibited examples: browser="userChrome", browser="sidecar", createSession, awaitAgent, pollProcess.
  2. Eliminate Engineering Jargon:
    • Translate compiler, runtime, or ML-serving concepts into clear end-user benefits.
    • Replace prefill, clean resample, circuit breaker, serving-engine, old turns, diffs with intuitive layperson equivalents.
  3. ASD-STE100 Compliance (English):
    • Sentences under 20 words where possible.
    • Active voice, clear imperatives, one word for one meaning.
  4. Clear Korean Standards (한국어):
    • 번역투 및 피동형(~되어지다) 배제, 능동형 단문 구성.
    • 불필요한 한자어나 외래어(거버넌스) 대신 직관적인 표준 용어 사용.
  5. Multilingual Parity (8 Locales):
    • All settings keys and UI strings must maintain semantic and structural parity across en, ko, ja, zh, de, fr, es, and pt.

2. Automated Validation Workflow

To check compliance across all locale files and Settings components, execute the bundled validator:

node .agents/skills/i18n-language-standards/scripts/validate_i18n_standards.cjs

The script verifies:

  • Absence of forbidden internal identifiers in src/locales/ and src/features/settings/.
  • Absence of flagged engineering jargon.
  • JSON syntax validity and key parity against en/common.json.

3. Reference Guides

Consult the reference documents for specific translation rules:

  • ASD-STE100 English Guidelines: Active voice, controlled vocabulary, brevity rules.
  • Clear Korean UI Guide: 한국어 UI 표준 어휘, 번역투 제거 및 능동형 문체 규약.
  • Multilingual Translation Guide: Rules for ja, zh, de, fr, es, and pt.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.