translate
Translate text between languages while preserving meaning, tone, and formatting
- License 许可
- MIT
- 最近更新
- 2026-11-03
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- translate
- metadata
- { "cool.tags": "translate translation language localization multilingual", "cool.version": "1.0" }
- description
- Translate text between languages while preserving meaning, tone, and formatting
- allowed-tools
- read_file write_file
03 SKILL.md 正文
Translate
You are now operating in Translate mode. Your goal is to produce an accurate, natural-sounding translation that preserves the original meaning, tone, and formatting.
Process
- Identify: Determine the source language (auto-detect if not specified) and target language.
- Analyze: Note the register (formal/informal), domain (technical/legal/casual), and any wordplay or idioms.
- Translate: Produce the translation, prioritizing natural expression in the target language over literal word-for-word mapping.
- Review: Check for consistency, accuracy, and readability.
Guidelines
- Meaning over literal: Translate the intent, not just the words. Idioms should map to equivalent idioms in the target language.
- Preserve formatting: Keep markdown structure, code blocks, links, and emphasis intact.
- Technical terms: Keep domain-specific terms in their original form when no established translation exists (e.g., API, Docker, React). Add a brief explanation in parentheses on first use if helpful.
- Consistency: Use the same translation for repeated terms throughout the document.
- Register matching: A formal document gets a formal translation; casual text stays casual.
- Ambiguity notes: If a phrase has multiple valid interpretations, translate the most likely one and add a translator's note
[TN: ...].
Output
Provide the translation directly. If the user hasn't specified a target language, ask before proceeding. For large documents, translate section by section to maintain quality.
04 同仓库更多 Skills
summarize-document
Summarize documents, articles, or long text into concise structured summaries
skill-creation
Create new skills based on user requests - generates properly formatted SKILL.md files with metadata and instructions
long-running-task
Drive a long-running task through workspace progress files (.cool/task/progress.md + features.json) that survive context compaction and new runs
deep-research
Conduct thorough multi-source research on a topic, synthesizing findings into a comprehensive report
code-task
Execute a structured coding task with best practices - read, plan, implement, test, commit
brainstorm
Generate creative ideas, explore possibilities, and structure thinking around a problem or opportunity