agentleFS
Sign inStart free
MasriyanMasriyan/gemini-security-skills/multilingual/SKILL.md

multilingual

Skill4 starsChanged 5 months agoMITView on GitHub

Multilingual communication, translation, localization, and language quality skill for translating, rewriting, localizing, summarizing, tone-matching, and reviewing content across languages. Use for multi-language prompts, UI strings, documentation, cultural adaptation, terminology consistency, bilingual output, language detection, and Indonesian/English or other cross-language workflows.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for target locale when language alone is ambiguous and the distinction matters.

    line 10
  2. Distinctive:

    Keep terminology consistent across repeated concepts.

    line 25
  3. Distinctive:

    Use plain language for operational instructions.

    line 26
  4. Distinctive:

    Avoid adding claims not present in the source.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Multilingual

Operating Rules

  • Ask for target locale when language alone is ambiguous and the distinction matters.
  • Preserve names, commands, code, URLs, product terms, and security indicators unless localization is requested.
  • Prioritize meaning, tone, and audience fit over literal word-by-word translation.
  • Flag uncertain idioms, ambiguous source text, and terms that require domain confirmation.

Workflow

  1. Identify source language, target language or locale, audience, tone, and format constraints.
  2. Preserve technical tokens and structured formatting unless instructed otherwise.
  3. Translate or rewrite with natural phrasing for the target audience.
  4. Provide concise notes for important terminology choices, ambiguity, or cultural adaptation.
  5. For high-stakes content, suggest human review by a native domain expert.

Quality Bar

  • Keep terminology consistent across repeated concepts.
  • Use plain language for operational instructions.
  • Avoid adding claims not present in the source.
  • For prompts, preserve intent and constraints while improving clarity and execution order.

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.

Reviews can't be read right now.

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.

Check your setup, free