agentleFS
kuju63kuju63/skills/translate/SKILL.md

translate

Skill0 starsChanged 3 months agoApache-2.0View on GitHub

Translate documentation between English and Japanese while preserving code, links, and structure. Automatically uses software development terminology glossary (56 terms including Docker, K8s, OCI, API, CLI, SDK, etc.) for consistency. Use when translating README files, test guides, or documentation updates. Usage: /translate [filename] [source-lang-code] [target-lang-code]

48 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use faq, summarize and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    faq

    Turn repeat questions into a pinned FAQ. Use when a champion keeps answering the same questions.

    Also in 3 projects that use this

  • mitsuhikoSkill

    summarize

    Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize

    Also in 8 projects that use this

  • jacobraskSkill

    calendar

    Interact with Apple Calendar via AppleScript. Use when the user asks to check calendar, view events, create events, manage schedule, find free time, or list calendars. Triggers include "my calendar", "my schedule", "calendar events", "create event", "add to calendar", "what's on my calendar", "free time", "available slots", "upcoming events", "today's events". Requires macOS with Calendar.app.

    Also in 3 projects that use this

  • AnthropicSkill

    analyze

    Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

    Also in 4 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 5 projects that use this

  • VercelSkill

    publish

    Publish a single demo to v0 and optionally create Typefully drafts. Use when the user says "publish", "publish to v0", or "create typefully draft" for a demo.

    Also in 3 projects that use this

  • +2 more from anthropics

The file

Show its rules and text

We split this skill into the rules it gives an agent

20 rules. 0 are common, 20 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 40 edited versions we read keep these.

  • 20

    Distinctive

    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:

    IMPORTANT: Before starting translation, read the complete translation glossary:

    line 14
  2. Distinctive:

    When translating software development terms:

    line 23
  3. Distinctive:

    Acronyms: Keep acronyms in English (API, CLI, SDK, OCI, K8s)

    line 24
  4. Distinctive:

    Proper nouns: Keep proper nouns unchanged (Docker, Podman, GitHub, Kubernetes)

    line 25
  5. Distinctive:

    Technical terms: Use glossary translations (workspace → ワークスペース, container → コンテナ)

    line 26
  6. Distinctive:

    Code-related: Keep code identifiers, variable names, and command names in English

    line 27
  7. Distinctive:

    Code blocks: Keep identical (no translation)

    line 31
  8. Distinctive:

    Update relative links if pointing to language-specific files

    line 36
  9. Distinctive:

    Use existing translations from parallel documentation as reference

    line 40
  10. Distinctive:

    Code identifiers: Keep unchanged

    line 43
  11. Distinctive:

    Technical abbreviations: Keep in English with Japanese explanation if needed

    line 47
  12. Distinctive:

    Before considering the translation complete, verify:

    line 61
  13. Distinctive:

    If invalid, display error message with usage example

    line 85
  14. Distinctive:

    Use the Read tool to read the complete source file.

    line 93
  15. Distinctive:

    Read the translation glossary to ensure terminology consistency:

    line 100
  16. Distinctive:

    Before editing, explain your approach:

    line 107
  17. Distinctive:

    Create or edit the target file:

    line 115
  18. Distinctive:

    Use consistent terminology from glossary

    line 117
  19. Distinctive:

    Keep all links (update paths only if language-specific)

    line 119
  20. Distinctive:

    Check the translation quality:

    line 128

“Common” is measured: kept by at least 6 in 10 of the 40 edited versions of this file we could read. “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

Translation Skill

Translate documentation files between English and Japanese while maintaining technical accuracy and consistency with existing translations.

Guidelines

Translation Glossary

IMPORTANT: Before starting translation, read the complete translation glossary:

  • File: ./translate/glossary.md
  • Terms: 56 software development terms including:
    • Container technology: Docker, Podman, OCI, K8s, image, volume, daemon, etc.
    • DevOps/CI/CD: GitHub Actions, workflow, pipeline, deployment, PR, etc.
    • General software development: API, CLI, SDK, library, framework, dependency, etc.

Software Development Terms

When translating software development terms:

  1. Acronyms: Keep acronyms in English (API, CLI, SDK, OCI, K8s)
  2. Proper nouns: Keep proper nouns unchanged (Docker, Podman, GitHub, Kubernetes)
  3. Technical terms: Use glossary translations (workspace → ワークスペース, container → コンテナ)
  4. Code-related: Keep code identifiers, variable names, and command names in English

Translation Rules

  1. Code blocks: Keep identical (no translation)
    • Bash scripts, YAML, JSON, code examples must be unchanged
    • Comments in code blocks may be translated if appropriate
  2. Links and URLs: Preserve exactly
    • Update relative links if pointing to language-specific files
    • Example: README.md → README.ja.md in language selector links
  3. Section headings: Translate consistently
    • Use existing translations from parallel documentation as reference
    • Maintain heading hierarchy (same number of #)
  4. Code identifiers: Keep unchanged
    • File paths, variable names, function names, command names
    • Example: provider.yaml, PODMAN_MACHINE_NAME, devpod up
  5. Technical abbreviations: Keep in English with Japanese explanation if needed
    • Good: "OCI (Open Container Initiative)"
    • Bad: "オーシーアイ"

File Structure

Maintain identical structure between English and Japanese versions:

  • Same section ordering
  • Same heading hierarchy
  • Same code examples (identical)
  • Same links (update paths only if pointing to language-specific content)

Quality Checklist

Before considering the translation complete, verify:

  • All technical terms match the glossary
  • Code blocks are identical in both versions
  • Links are functional in both versions
  • Language selection links point to correct files
  • Section structure matches between versions
  • Acronyms and proper nouns are preserved correctly

Task

Translate the file specified in the arguments from the source language to the target language.

Arguments:

  • $ARGUMENTS[0]: Filename to translate (e.g., README.md)
  • $ARGUMENTS[1]: Source language code (en or ja)
  • $ARGUMENTS[2]: Target language code (en or ja)

Steps

0. Validate language codes

Validate the language code arguments:

  • $ARGUMENTS[1] (source) must be en or ja
  • $ARGUMENTS[2] (target) must be en or ja
  • If invalid, display error message with usage example

Language code mappings:

  • en: English
  • ja: Japanese (日本語)

1. Read source file

Use the Read tool to read the complete source file.

  • Identify all sections and their content
  • Note code blocks, links, and special formatting
  • Identify the file structure

2. Load translation glossary

Read the translation glossary to ensure terminology consistency:

  • File: ./translate/glossary.md
  • Pay attention to software development terms
  • Note any special translation rules

3. Plan translation approach

Before editing, explain your approach:

  • Identify technical terms that should use the glossary
  • Identify sections that have parallel translations in existing files
  • Plan how to maintain structure
  • Note any links that need path updates

4. Perform translation

Create or edit the target file:

  • Maintain identical structure to source
  • Use consistent terminology from glossary
  • Preserve all code examples without changes
  • Keep all links (update paths only if language-specific)
  • Maintain all formatting (bold, italic, lists, tables)

Target filename:

  • en → ja: Add .ja before extension (e.g., README.md → README.ja.md)
  • ja → en: Remove .ja from filename (e.g., README.ja.md → README.md)

5. Verification

Check the translation quality:

  • All code blocks are identical to source
  • Section structure matches source exactly
  • Technical terms are consistent with glossary
  • Links are appropriate for the target language
  • Language selector links are updated
  • No untranslated sections remain (except code)

6. Report

Provide a summary of the translation:

  • Source file and target file paths
  • Number of sections translated
  • Notable technical terms used
  • Any manual review recommendations

Examples

For detailed examples of expected translation quality, see examples.md.

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.