Translating Technical Articles
关于
This skill translates English technical articles and documentation into Japanese while preserving the original structure, including headings, code blocks, and image links. It is triggered when a user requests to translate an article, convert English content, or process a URL or blog post. The process involves fetching the content, performing the translation, and saving it to a file.
技能文档
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:
-
Firecrawl MCP (
mcp__firecrawl__firecrawl_scrape): Most reliable🌟Claudeは Firecrawl MCP サーバー を唱えた!Use
formats: ["markdown"]andmaxAgefor caching -
Brave Search MCP: If Firecrawl unavailable
-
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:
- Read the saved file to verify content
- Check for garbled text (文字化け):
- Japanese characters display correctly
- No mojibake (e.g., "æ–‡å—化ã'" instead of "文字化け")
- Code blocks and special characters intact
- 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
- 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.
快速安装
/plugin add https://github.com/camoneart/claude-code/tree/main/translate-article在 Claude Code 中复制并粘贴此命令以安装该技能
GitHub 仓库
相关推荐技能
go-test
元go-test Skill为Go开发者提供全面的测试指导,涵盖单元测试、性能基准测试和集成测试的最佳实践。它能帮助您正确实现表驱动测试、子测试组织、mock接口和竞态检测,同时指导测试覆盖率分析和性能基准测试。当您编写_test.go文件、设计测试用例或优化测试策略时,这个Skill能确保您遵循Go语言的标准测试惯例。
issue-documentation
元该Skill为开发者提供标准化的issue文档模板和指南,适用于创建bug报告、GitHub/Linear/Jira问题等场景。它能系统化地记录问题状况、复现步骤、根本原因、解决方案和影响范围,确保团队沟通清晰高效。通过实施主流问题跟踪系统的最佳实践,帮助开发者生成结构完整的故障排除文档和事件报告。
llamaindex
元LlamaIndex是一个专门构建RAG应用的开发框架,提供300多种数据连接器用于文档摄取、索引和查询。它具备向量索引、查询引擎和智能代理等核心功能,支持构建文档问答、知识检索和聊天机器人等数据密集型应用。开发者可用它快速搭建连接私有数据与LLM的RAG管道。
business-rule-documentation
元该Skill为开发者提供标准化的业务规则和领域知识文档模板,遵循领域驱动设计原则。它能系统化地捕获业务规则、流程、决策树和术语表,确保业务需求与技术实现的一致性。适用于创建领域模型、业务规则库、流程映射,以及改善业务与技术团队之间的沟通。
