关于
This skill translates technical documentation (skills, agents, teams, guides) into a target language while preserving critical elements like code blocks, IDs, and frontmatter structure. Use it for localizing new content, updating stale translations after source changes, or batch-translating an entire domain. It handles the full process including scaffolding, prose translation, and freshness tracking.
快速安装
Claude Code
推荐npx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/translate-content在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Inhalte uebersetzen
Translate English source content into a target locale, preserving technical accuracy and structural integrity.
Wann verwenden
- Localizing a skill, agent, team, or guide into a supported language
- Updating a translation that has become stale nach source changes
- Batch-translating multiple items innerhalb a domain or content type
- Creating initial translations for a new locale
Eingaben
- Erforderlich: Content type —
skills,agents,teams, orguides - Erforderlich: Item ID — the name/identifier of the content (e.g.,
create-r-package) - Erforderlich: Target locale — IETF BCP 47 code (e.g.,
de,zh-CN,ja,es) - Optional: Batch list — multiple IDs to translate in sequence
Vorgehensweise
Schritt 1: Lesen the English source
1.1. Bestimmen die Quelle Dateipfad:
- Skills:
skills/<id>/SKILL.md - Agents:
agents/<id>.md - Teams:
teams/<id>.md - Guides:
guides/<id>.md
1.2. Lesen the entire Quelldatei to understand context, structure, and content.
1.3. Identifizieren sections that must stay in English:
- All code blocks (fenced with triple backticks)
- Inline code (backtick-wrapped)
- YAML frontmatter field names and technical values (
name,tools,model,priority,skillslist entries,allowed-tools,tags,domain,language) - File paths, URLs, command examples
<!-- CONFIG:START -->/<!-- CONFIG:END -->blocks in teams
Erwartet: Full understanding of source content with clear mental separation of translatable prose vs preserved technical content.
Bei Fehler: If Quelldatei ist nicht found, verify the ID exists in the registry. Pruefen auf typos in the content type or ID.
Schritt 2: Scaffold the translation file
2.1. Ausfuehren the scaffolding script:
npm run translate:scaffold -- <content-type> <id> <locale>
2.2. If die Datei already exists, read it to check whether it needs updating (stale) or is already current.
2.3. Verifizieren the scaffolded file has translation frontmatter fields:
locale— matches target localesource_locale—ensource_commit— current git short hashtranslator— attribution stringtranslation_date— today's date
Erwartet: Scaffolded file at i18n/<locale>/<content-type>/<id>/SKILL.md (or .md for other types) with correct frontmatter.
Bei Fehler: If the scaffold script fails, create das Verzeichnis manuell with mkdir -p and copy die Quelle file. Hinzufuegen frontmatter fields manuell.
Schritt 3: Translate the description
3.1. Translate the description field in the YAML frontmatter into das Ziel locale.
3.2. For skills, the description is inside the top-level frontmatter. For agents/teams/guides, it is also in the top-level frontmatter.
3.3. Keep the translation concise — match the length and style of the original.
Erwartet: Description field contains an idiomatic translation that accurately conveys the original meaning.
Bei Fehler: If the description is ambiguous, keep it closer to literal translation anstatt risk misinterpretation.
Schritt 4: Translate prose sections
4.1. Translate all prose content section by section:
- Section headings (e.g., "## When to Use" → "## Wann verwenden" in German)
- Paragraph text
- Auflisten item text (but not list item code/paths)
- Table cell text (but not table cell code/values)
4.2. Preserve these elements exactly as-is:
- Code blocks (``` fenced and indented)
- Inline code (
backtick-wrapped) - File paths and URLs
- Skill/agent/team IDs in cross-references
- YAML/JSON configuration examples
- Command-line examples
**Expected:**and**On failure:**markers (translate the label, keep the structure)
4.3. For skills, translate the standardized section names:
- "When to Use" → locale equivalent
- "Inputs" → locale equivalent
- "Procedure" → locale equivalent
- "Validation" → locale equivalent
- "Common Pitfalls" → locale equivalent
- "Related Skills" → locale equivalent
4.4. For agents, translate:
- Purpose, Capabilities, Available Skills (section name only — skill IDs stay English), Usage Scenarios, Best Practices, Examples, Limitations, See Also
4.5. For teams, translate:
- Purpose, Team Composition (prose only — IDs stay English), Coordination Pattern, Task Decomposition, Usage Scenarios, Limitations
4.6. For guides, translate:
- All prose sections, troubleshooting text, table descriptions
- Keep command examples, code blocks, and configuration snippets in English
Erwartet: All prose sections translated idiomatically. Code blocks identical to English source. Cross-references use English IDs.
Bei Fehler: If uncertain about a technical term, keep the English term with a parenthetical translation. Example: "Staging-Bereich (Staging Area)" in German.
Schritt 5: Verifizieren structural integrity
5.1. Bestaetigen the translated file has the same number of sections as die Quelle.
5.2. For skills, verify all required sections are present:
- YAML frontmatter with
name,description,allowed-tools,metadata - When to Use, Inputs, Procedure, Validation, Common Pitfalls, Related Skills
5.3. Verifizieren code blocks are identical to the English source (diff the fenced blocks).
5.4. Check line count: skills muss ≤ 500 lines.
5.5. Verifizieren name field matches the English source exactly (it is the ID, never translated).
Erwartet: Structurally valid translated file that passes validation.
Bei Fehler: Vergleichen section-by-section with the English source. Wiederherstellen any missing sections.
Schritt 5.5: Ueberpruefe ob Prosa uebersetzt ist
5.5.1. Probeentnahme von 3 Prosa-Absaetzen aus dem Hauptteil der uebersetzten Datei. Absaetze aus verschiedenen Abschnitten auswaehlen — keine Ueberschriften, Codeblöcke oder Frontmatter.
5.5.2. Bestaetigen dass jeder Prosa-Absatz in der Zielsprache geschrieben ist, nicht auf Englisch.
5.5.3. Wenn ein Prosa-Absatz noch auf Englisch ist, ist die Uebersetzung unvollstaendig. Zu Schritt 4 zurueckkehren und die verbleibende englische Prosa uebersetzen, bevor fortgefahren wird.
Erwartet: Alle 3 Prosa-Absatzproben sind in der Zielsprache, was bestaetigt dass der Textteil uebersetzt wurde — nicht nur Ueberschriften und Frontmatter.
Bei Fehler: Identifizieren welche Abschnitte noch englische Prosa enthalten. Diese uebersetzen bevor mit Schritt 6 fortgefahren wird.
Schritt 6: Schreiben the translated file
6.1. Schreiben the complete translated content to das Ziel path using the Schreiben or Bearbeiten tool.
6.2. Verifizieren die Datei exists at the expected path:
- Skills:
i18n/<locale>/skills/<id>/SKILL.md - Agents:
i18n/<locale>/agents/<id>.md - Teams:
i18n/<locale>/teams/<id>.md - Guides:
i18n/<locale>/guides/<id>.md
Erwartet: Translated file written to disk at the correct path.
Bei Fehler: Check directory exists. Erstellen with mkdir -p if needed.
Validierung
- Translated file exists at
i18n/<locale>/<type>/<id> -
namefield matches English source exactly -
localefield matches target locale -
source_commitfield is set to a valid git short hash - All code blocks are identical to English source
- All cross-referenced IDs (skills, agents, teams) are in English
- File is under 500 lines (for skills)
-
npm run validate:translationsreports no issues for this file - Prose reads idiomatically in das Ziel language
Haeufige Stolperfallen
- Translating code blocks: Code, commands, and configuration must stay in English. Only translate surrounding prose.
- Translating the
namefield: Thenamefield is the canonical ID. Never translate it. - Translating tag values: Tags in
metadata.tagsstay in English for cross-locale consistency. - Inconsistent terminology: Use the same translation for a technical term durchout die Datei and across files in the same locale.
- Literal translation of idioms: Translate the meaning, not the words. "Common Pitfalls" solltecome the locale's natural equivalent, not a word-for-word translation.
- Missing
source_commit: Without this field, freshness tracking breaks. Always include it. - Exceeding 500 lines: Translations may expand ~10-20% vs English. If near the limit, tighten prose anstatt removing content.
Verwandte Skills
- create-skill — understand the SKILL.md structure being translated
- review-skill-format — validate translated skill structure
- evolve-skill — update skills that have changed since translation
- Batch-Durchsatz vor Qualitaet: Reine Geruest-Ausgabe — wo Ueberschriften uebersetzt sind, aber der Textteil auf Englisch bleibt — ist keine gueltige Uebersetzung. Weniger vollstaendige Uebersetzungen sind besser als viele partielle.
GitHub 仓库
Frequently asked questions
What is the translate-content skill?
translate-content is a Claude Skill by pjt222. Skills package instructions and resources that Claude loads on demand, so Claude can perform translate-content-related tasks without extra prompting.
How do I install translate-content?
Use the install commands on this page: add translate-content to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does translate-content belong to?
translate-content is in the Meta category, tagged ai and design.
Is translate-content free to use?
Yes. translate-content is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
