agentleFS
tyxo0o315tyxo0o315/epub-bilingual-translator/skills/review-translation/SKILL.md

review-translation

Skill1 starsChanged 3 months agoMITView on GitHub

Review chapters from a bilingual EPUB in the browser, take notes on translation issues, and save parameter suggestions for future translations. Triggers on /review-translation with a bilingual .epub path.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. team-attention/stanford-cs146s-kr★ 294same name
    2. rmarsigli/p10t★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When the user invokes /review-translation, follow these steps exactly.

    line 8
  2. Distinctive:

    If the user provided a path, use it.

    line 12
  3. Distinctive:

    Verify the file exists. If not, tell the user and stop.

    line 18
  4. Distinctive:

    If yes, ask for the second EPUB path and chapter number, then run:

    line 54
  5. Distinctive:

    If the user provides notes, parse each line into:

    line 73
  6. Very specific:

    Create the directory ~/.claude/translation-notes/ if it doesn't exist.

    line 104

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

EPUB Translation Reviewer

When the user invokes /review-translation, follow these steps exactly.

Step 1: Get EPUB Path

If the user provided a path, use it. Otherwise ask:

请输入双语 EPUB 文件路径(拖入文件即可):

Verify the file exists. If not, tell the user and stop.

Step 2: List Chapters

Run:

python3 ~/.claude/scripts/review_epub.py "<epub_path>" --list

Show the output to the user.

Step 3: Select Chapters

Ask:

请选择要预览的章节:
(支持单章、多章、范围,例如:3 / 1,3,5 / 2-6)

Wait for input.

Step 4: Open in Browser

Run:

python3 ~/.claude/scripts/review_epub.py "<epub_path>" --open <chapters>

Tell the user: "已在浏览器打开,请查看翻译效果。"

Then ask:

是否需要对比另一个版本的翻译?(例如不同引擎/题材的同一本书)(y/n)

If yes, ask for the second EPUB path and chapter number, then run:

python3 ~/.claude/scripts/review_epub.py "<epub_path>" --compare "<epub2_path>" --chapter <N>

Step 5: Collect Feedback Notes

Ask:

请记录你发现的翻译问题(可多条,完成后输入"完成"):

格式示例:
  第3章 人名不一致 → 建议加 --glossary "Elena=叶莲娜"
  第5章 成语太多   → 建议加 --prompt "避免使用成语,用现代白话文"
  整体  语气太正式  → 建议改用 --genre romance

直接回车跳过记录。

If the user provides notes, parse each line into:

  • chapter: 章节编号或"整体"
  • issue: 问题描述
  • suggestion: 建议的参数调整

Step 6: Save Notes

Determine the notes file path:

import re
book_name = re.sub(r'[^\w一-鿿\-]', '_', Path(epub_path).stem)[:60]
notes_path = f"~/.claude/translation-notes/{book_name}.json"

Load existing notes if the file exists, then append the new notes. Save as JSON:

{
  "book": "<stem of epub filename>",
  "epub_path": "<full path>",
  "updated": "<YYYY-MM-DD>",
  "notes": [
    {
      "chapter": "第3章",
      "issue": "人名不一致",
      "suggestion_type": "glossary",
      "suggestion": "--glossary \"Elena=叶莲娜\""
    }
  ]
}

Create the directory ~/.claude/translation-notes/ if it doesn't exist.

Run:

mkdir -p ~/.claude/translation-notes

Then write the JSON file. Confirm: "笔记已保存到 <notes_path>。"

Step 7: Summary

Show a summary:

✅ 预览完成

📋 本次记录了 N 条笔记:
  · 第3章:人名不一致 → --glossary "Elena=叶莲娜"
  · 第5章:成语太多   → --prompt "避免使用成语..."

下次翻译这本书时,/translate-ebook 会自动加载这些建议。

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.