name: epub-translator
description: Translates EPUB ebook files between languages with parallel processing. Supports Japanese, English, Chinese, and other languages. Handles large files by splitting into sections, manages multiple volumes simultaneously, and preserves EPUB structure and formatting. Includes translation quality validation. Use when translating novels, books, or any EPUB content.
compatibility: Requires Python 3.8+, zip/unzip commands. Optional epubcheck for validation.
allowed-tools: Read Write Edit Bash(python3:) Bash(bash:) Bash(mkdir:) Bash(find:) Bash(echo:) Bash(wc:) Bash(cat:) Bash(ls:)
metadata:
author: Haze Lee
version: "1.0.0"
category: translation

EPUB Translation Skill

Translate EPUB files between any language pair with optimized support for Japanese and English to Korean.

When to Use This Skill

Use this skill when:
- User wants to translate an EPUB ebook to another language
- User mentions translating Japanese/English/Chinese novels or books
- User has multiple EPUB files to translate in batch
- User needs to preserve EPUB formatting and structure during translation

Usage

/epub-translator <epub_path> [options]

Arguments

• <epub_path>: EPUB file or directory containing EPUBs

Options

Language Codes

ja (Japanese), en (English), ko (Korean), zh (Chinese), es (Spanish), fr (French), de (German), ru (Russian), ar (Arabic), or any ISO 639-1 code.

Examples

# Japanese novel to Korean (default)
/epub-translator "/books/novel.epub"

# English to Korean
/epub-translator "/books/english.epub" --source-lang en

# Japanese to English
/epub-translator "/books/jp_novel.epub" --source-lang ja --target-lang en

# High-quality translation using Opus model
/epub-translator "/books/important.epub" --high-quality

# Batch with larger split threshold (less splitting)
/epub-translator "/books/" --split-threshold 50 --parallel 10

# More aggressive splitting for slower connections
/epub-translator "/books/large.epub" --split-threshold 20 --split-parts 6

# English to Japanese with vertical writing (우종서/縦書き)
/epub-translator "/books/novel.epub" --source-lang en --target-lang ja --vertical

# Korean to Chinese with vertical writing
/epub-translator "/books/korean.epub" --source-lang ko --target-lang zh --vertical

Architecture

graph TB
    O["ORCHESTRATOR<br/>• Analyzes EPUBs and creates task manifest<br/>• Spawns parallel translator agents (foreground)<br/>• Collects results directly from agent responses<br/>• Validates translation quality<br/>• Handles retries and error recovery"]
    T1["Translator<br/>Agent 1"]
    T2["Translator<br/>Agent 2"]
    TN["Translator<br/>Agent N"]

    O --> T1
    O --> T2
    O --> TN

Key Constraint: Sub-agents do NOT have Task tool access. They use only Read, Edit, Write, and Bash.

Execution Model: All Task agents run in foreground mode (not background). Multiple Tasks can be spawned in a single message for parallel execution, but results are collected synchronously.

Model Selection

Default (no flags)

With --high-quality

Automatic Upgrade

• If quality score < 70: Re-translate flagged files with Opus
• If translation fails: Retry with upgraded model

Execution Workflow

Phase 1: Analysis

1. Create work directory:
   bash WORK_DIR="/tmp/epub_translate_$(date +%s)" mkdir -p "$WORK_DIR"/{extracted,sections,translated,status,logs}

2. Analyze EPUBs (with configurable split threshold):
   bash python3 scripts/analyze_epub.py \ --epub "{EPUB_PATH}" \ --work-dir "$WORK_DIR" \ --source-lang "{SOURCE_LANG}" \ --target-lang "{TARGET_LANG}" \ --split-threshold 30 \ --split-parts 4

3. Review $WORK_DIR/manifest.json for task count.

Phase 2: Translation

1. Select translator prompt from references/:
2. Japanese: translator_ja.md
3. English: translator_en.md

4. Other: translator_generic.md

5. Spawn Task agents in foreground mode (batched):

6. model: "sonnet"
7. CRITICAL: Multiple Tasks in single message for parallel execution
8. Process in batches of --parallel count (default: 5)

9. Results are returned directly - no status file monitoring needed

10. Batch execution pattern:
    ```
    For each batch of N tasks:

    • Spawn N Task agents in a single message (foreground, parallel)
    • Collect results directly from agent responses
    • Track completed/failed tasks
    • Proceed to next batch
      ```

11. Retry failed tasks (max 2 attempts, upgrade to opus if persistent)

Phase 3: Finalization

1. Merge split files:
   bash python3 scripts/merge_xhtml.py --work-dir "$WORK_DIR" --manifest manifest.json

2. Translate metadata and navigation (LLM-based):

3. Spawn metadata translation agent using translator_metadata.md
4. Translate: toc.ncx, nav.xhtml, content.opf (title, author, description)
5. Translate: cover.xhtml, titlepage.xhtml (if present)

6. Ensure TOC entries match translated chapter headings

7. Apply layout conversion (CRITICAL - must be done before packaging):

Determine conversion type based on target language and --vertical option:

A. Horizontal output (default for all languages):
```bash
TRANSLATED_DIR="$WORK_DIR/translated/{VOLUME_ID}"

# Convert CSS files: vertical-rl → horizontal-tb
find "$TRANSLATED_DIR" -name ".css" -exec sed -i '' \
-e 's/writing-mode:[[:space:]]vertical-rl/writing-mode: horizontal-tb/g' \
-e 's/-webkit-writing-mode:[[:space:]]vertical-rl/-webkit-writing-mode: horizontal-tb/g' \
-e 's/-epub-writing-mode:[[:space:]]vertical-rl/-epub-writing-mode: horizontal-tb/g' \
{} \;

# Convert content.opf: page direction and writing mode
find "$TRANSLATED_DIR" -name "content.opf" -exec sed -i '' \
-e 's/page-progression-direction="rtl"/page-progression-direction="ltr"/g' \
-e 's/primary-writing-mode" content="vertical-rl"/primary-writing-mode" content="horizontal-tb"/g' \
{} \;

# Convert XHTML inline styles if present
find "$TRANSLATED_DIR" -name ".xhtml" -exec sed -i '' \
-e 's/writing-mode:[[:space:]]vertical-rl/writing-mode: horizontal-tb/g' \
{} \;
```

B. Vertical output (only when --vertical AND target is ja/zh):
```bash
TRANSLATED_DIR="$WORK_DIR/translated/{VOLUME_ID}"

# Convert CSS files: horizontal-tb → vertical-rl
find "$TRANSLATED_DIR" -name ".css" -exec sed -i '' \
-e 's/writing-mode:[[:space:]]horizontal-tb/writing-mode: vertical-rl/g' \
-e 's/-webkit-writing-mode:[[:space:]]horizontal-tb/-webkit-writing-mode: vertical-rl/g' \
-e 's/-epub-writing-mode:[[:space:]]horizontal-tb/-epub-writing-mode: vertical-rl/g' \
{} \;

# Convert content.opf: page direction and writing mode for vertical
find "$TRANSLATED_DIR" -name "content.opf" -exec sed -i '' \
-e 's/page-progression-direction="ltr"/page-progression-direction="rtl"/g' \
-e 's/primary-writing-mode" content="horizontal-tb"/primary-writing-mode" content="vertical-rl"/g' \
{} \;

# Convert XHTML inline styles if present
find "$TRANSLATED_DIR" -name ".xhtml" -exec sed -i '' \
-e 's/writing-mode:[[:space:]]horizontal-tb/writing-mode: vertical-rl/g' \
{} \;
```

C. RTL output (for ar/he/fa targets):
```bash
# Convert page direction
sed -i '' 's/page-progression-direction="ltr"/page-progression-direction="rtl"/g' "$TRANSLATED_DIR"/content.opf

# Convert CSS direction
find "$TRANSLATED_DIR" -name ".css" -exec sed -i '' \
-e 's/direction:[[:space:]]ltr/direction: rtl/g' \
{} \;
```

Note: If source is already vertical and --vertical is set, skip CSS conversion (keep existing vertical layout).

See references/layout_conversion.md for complete conversion patterns.

1. Verify source text removed:
   bash python3 scripts/verify.py --work-dir "$WORK_DIR" --source-lang "{SOURCE_LANG}"

Phase 4: Quality Validation (LLM-Based)

1. Extract text for validation (token-efficient format):
   bash python3 scripts/extract_for_validation.py \ --dir "$WORK_DIR/translated" \ --output-dir "$WORK_DIR/validation" \ --max-tokens 8000

2. Select validator prompt from references/:

3. Korean target: validator_ko.md (extends validator_generic.md)

4. Other targets: validator_generic.md

5. Spawn validation Task agents in foreground mode (batched):

6. Read $WORK_DIR/validation/validation_manifest.json
7. For each chunk, spawn a validator agent with:
   • model: "haiku" (sufficient for validation)
8. CRITICAL: Multiple Tasks in single message for parallel execution

9. Process in batches, collect results directly

10. Aggregate results:

11. Collect validation results from agent responses
12. Calculate average quality score

13. Identify files flagged for re-translation

14. If average score < 70: Re-translate flagged files with model: "opus"

Phase 5: Packaging

1. Package EPUB:
   bash bash scripts/package_epub.sh "$WORK_DIR" "{OUTPUT_DIR}"

2. Generate final report with quality metrics

File Splitting Configuration

Conservative defaults prevent context overflow in translation agents:

Tuning Guidelines

• Slow connection / Timeouts: Lower threshold (20 KB), more parts (6)
• Fast connection / Large context: Higher threshold (50 KB), fewer parts (3)
• Very large files (100KB+): Will be split into more parts automatically

Quality Validation (LLM-Based)

Translation quality is validated by LLM sub-agents, not regex patterns. This provides:
- Context-aware naturalness assessment
- Understanding of literary style and tone
- Detection of subtle translation issues

Validator Instructions

Korean-Specific Checks

• Translationese (번역투): ~하는 것이다, ~라고 하는, etc.
• Pronoun overuse: Excessive 그녀는, 그는
• Particle chains: Awkward 의의의 patterns
• Honorific consistency: Speech level matching

Quality Score

• 90-100: Excellent - reads naturally
• 75-89: Good - minor issues
• 60-74: Acceptable - review recommended
• <60: Poor - re-translation needed

Validation Workflow

1. Text extracted in token-efficient format
2. Chunked for parallel validation (8000 tokens each)
3. LLM validators spawned in foreground batches
4. Results collected directly from agent responses
5. Results aggregated into final report

Language-Specific Processing

Source Language Handling

Layout Conversion (Target-Based)

Key Principle: All languages default to horizontal LTR (except RTL languages).

Note: --vertical option is only valid for Japanese (ja) and Chinese (zh) targets. It will be ignored for other languages.

See references/layout_conversion.md for complete conversion scripts.

Custom Dictionary (Optional)

The translator works without external dictionary files. It naturally translates based on context.

Use custom dictionaries ONLY for:
- Proper nouns: names, places, organizations, brands
- Document-specific terms: proprietary terms unique to this document

Do NOT add common words - let the translator handle them naturally.

Creating a Custom Dictionary

See assets/template.json for format:

{
  "proper_nouns": { "names": { "田中太郎": "Tanaka Taro" } },
  "domain_terms": { "ProprietaryTech": "고유 기술명" }
}

Academic/Technical Template

For academic or technical documents, use assets/template_academic.json.

Work Directory Structure

$WORK_DIR/
├── manifest.json           # Task manifest
├── extracted/              # Extracted EPUB contents
├── sections/               # Split large files
├── translated/             # Translated files
├── validation/             # Validation input/output files
│   ├── validation_manifest.json
│   ├── validate_001_input.txt
│   ├── validate_001_result.json
│   └── ...
├── status/                 # Task status files
└── logs/                   # Log files

Status Codes

Error Handling

File Reference