MCP HubMCP Hub
スキル一覧に戻る

Translating Technical Articles

camoneart
更新日 Today
124 閲覧
2
2
GitHubで表示
デザインword

について

このスキルは、英語の技術記事やドキュメントを日本語に翻訳し、見出し、コードブロック、画像リンクを含む元の構造を保持します。ユーザーが記事の翻訳、英語コンテンツの変換、またはURLやブログ投稿の処理を要求したときに発動します。処理プロセスは、コンテンツの取得、翻訳の実行、ファイルへの保存を含みます。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/camoneart/claude-code
Git クローン代替
git clone https://github.com/camoneart/claude-code.git ~/.claude/skills/Translating Technical Articles

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Translating Technical Articles

Overview

This Skill translates English technical articles to Japanese Markdown while preserving:

  • Heading structure and hierarchy
  • Image links and URLs
  • Code blocks and formatting
  • List structures (numbered, bulleted)

Translation workflow

Copy this checklist and track progress:

Translation Progress:
- [ ] Step 1: Fetch article content
- [ ] Step 2: Translate to Japanese
- [ ] Step 3: Save to file
- [ ] Step 4: Verify translation (no garbled text)
- [ ] Step 5: Create implementation log

Step 1: Fetch article content

Priority order for fetching:

  1. Firecrawl MCP (mcp__firecrawl__firecrawl_scrape): Most reliable

    🌟Claudeは Firecrawl MCP サーバー を唱えた!
    

    Use formats: ["markdown"] and maxAge for caching

  2. Brave Search MCP: If Firecrawl unavailable

  3. WebFetch: Last resort

Step 2: Translate to Japanese

Key translation principles:

  • Preserve layout: Keep all heading levels, lists, images, code blocks
  • Technical terms:
    • Proper nouns: Keep original (e.g., "Claude Code", "Agent Skills")
    • Common tech terms: Translate with original in parentheses on first use
    • Industry terms: Use original if well-established
  • Natural Japanese: Avoid literal translation, use natural expressions
  • Consistency: Use same translation for same terms throughout

Add metadata header:

# [Translated Title]

**公開日:** YYYY年MM月DD日

**原文:** [Original URL]

---

[Translated content]

Step 3: Save to file

File naming:

  • Directory: User-specified path or kebab-case title directory
  • Filename: Kebab-case title + .md
  • Example: cc-catch-up/agent-skills/agent-skills.md

Step 4: Verify translation quality

Critical verification step:

After saving the translated file, 必ず必ず必ず最終確認を実行すること:

  1. Read the saved file to verify content
  2. Check for garbled text (文字化け):
    • Japanese characters display correctly
    • No mojibake (e.g., "文字化ã'" instead of "文字化け")
    • Code blocks and special characters intact
  3. If garbled text found:
    • Identify the cause (encoding issue, incorrect character conversion)
    • Fix the garbled sections immediately
    • Save the corrected version
    • Re-verify until no issues remain
  4. If no issues found:
    • Confirm completion to user
    • Proceed to Step 5

Important: Do not skip this verification. Garbled text makes the translation unusable.

Step 5: Create implementation log

Save log to _docs/templates/YYYY-MM-DD_translated-title.md:

# [Feature Name]

- **日付**: YYYY-MM-DD HH:MM:SS (from `date "+%Y-%m-%d %H:%M:%S"`)
- **概要**: Translation purpose and background
- **実装内容**: MCP server used, translation approach
- **設計意図**: Why preserve layout, how handle technical terms
- **翻訳のポイント**: Key translation decisions
- **副作用**: Any concerns (e.g., external image dependencies)
- **関連ファイル**: Path to translated file, original URL

Quality checklist

Before completion, verify:

  • Heading structure matches original
  • Image links and URLs preserved
  • Code blocks properly formatted
  • Technical terms consistent
  • Natural Japanese expressions
  • No garbled text (文字化けなし)
  • Metadata header included
  • Implementation log created

Example translation

Input: "Agent Skills extend Claude's capabilities..."

Output: "Agent Skillsは、Claudeの機能を拡張し..."

Note: "Agent Skills" kept as original (proper noun), natural Japanese structure.

GitHub リポジトリ

camoneart/claude-code
パス: skills/translate-article

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

cloudflare-turnstile

メタ

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

スキルを見る

llamaindex

メタ

LlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.

スキルを見る

canvas-design

メタ

The canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing it on a canvas. The skill focuses on original compositions using form, color, and space while avoiding copyright infringement by never copying existing artists' work.

スキルを見る