txt-to-epub

# TXT to EPUB

## Role

你是一个专门将 TXT 文本转换为 EPUB 的助手。你只做规则分章，不调用任何外部模型 API。

## What This Skill Does

1. 自动检测 TXT 编码并读取内容
2. 基于规则识别章节标题并分章
3. 生成带目录导航的 EPUB 文件
4. 支持保留完整标题（默认）或清理编号前缀

## Split Strategy

- 支持 `auto | novel | tutorial | length` 四种模式
- 标题规则覆盖：
  - 中文小说：`第一章 ...` / `第十回 ...`
  - 英文结构：`Chapter 1 ...` / `Part 2 ...`
  - 教程编号：`1.2 ...` / `2.3.4 ...`
  - 中文序号：`一、...`
- 当规则无法识别章节时，自动按长度切分为 `Part 1/2/...`

## Title Handling

- 默认 `--title-style full`：保留完整标题
  - 例如输入是 `第一章 xxx`，目录和章节标题都保持 `第一章 xxx`
- 可选 `--title-style clean`：去掉编号前缀，仅保留正文标题

## Script Path

`/Users/loid/.claude/skills/txt-to-epub/scripts/txt_to_epub.py`

## Install Dependencies

```bash
python3 -m pip install -r /Users/loid/.claude/skills/txt-to-epub/requirements.txt
```

## Usage

最小示例：

```bash
python3 /Users/loid/.claude/skills/txt-to-epub/scripts/txt_to_epub.py \
  --input /path/to/book.txt
```

常用示例（小说）：

```bash
python3 /Users/loid/.claude/skills/txt-to-epub/scripts/txt_to_epub.py \
  --input /path/to/novel.txt \
  --output /path/to/novel.epub \
  --title "我的小说" \
  --author "作者名" \
  --language zh-CN \
  --split-mode novel \
  --title-style full \
  --verbose
```

常用示例（教程）：

```bash
python3 /Users/loid/.claude/skills/txt-to-epub/scripts/txt_to_epub.py \
  --input /path/to/tutorial.txt \
  --split-mode tutorial \
  --title-style full
```

## Parameters

- `--input` 输入 TXT 文件路径（必填）
- `--output` 输出 EPUB 路径（可选，默认同名 `.epub`）
- `--title` 书名（可选，默认取输入文件名）
- `--author` 作者（可选）
- `--language` 语言，默认 `zh-CN`
- `--split-mode` 分章模式：`auto|novel|tutorial|length`
- `--title-style` 标题样式：`full|clean`，默认 `full`
- `--min-chapter-chars` 过短章节合并阈值，默认 `300`
- `--chunk-chars` 长度切分块大小，默认 `8000`
- `--verbose` 输出额...

# txt-to-epub

A lightweight, rule-based converter from `.txt` to `.epub`, designed for novels, tutorials, and other long-form text.

[简体中文 README](README.zh.md)

## Features

- Rule-based chapter splitting (no built-in model API dependency)
- Automatic text encoding detection (UTF-8/GBK/Big5/UTF-16, etc.)
- Multiple heading patterns for novels and tutorials
- Length-based fallback splitting when no headings are found
- Standard EPUB output with navigable TOC

## Project Structure

```text
txt-to-epub/
  SKILL.md
  requirements.txt
  scripts/
    txt_to_epub.py
```

## Installation

```bash
python3 -m pip install -r requirements.txt
```

## Quick Start

Run in the `txt-to-epub` directory:

```bash
python3 scripts/txt_to_epub.py --input /path/to/book.txt
```

By default, the output EPUB is created next to the input TXT file with the same base name.

## Common Commands

Novel mode (recommended, keep full chapter titles):

```bash
python3 scripts/txt_to_epub.py \
  --input /path/to/novel.txt \
  --split-mode novel \
  --title-style full \
  --verbose
```

Tutorial mode:

```bash
python3 scripts/txt_to_epub.py \
  --input /path/to/tutorial.txt \
  --split-mode tutorial \
  --title-style full
```

Force length-based splitting:

```bash
python3 scripts/txt_to_epub.py \
  --input /path/to/long_text.txt \
  --split-mode length \
  --chunk-chars 8000
```

## Arguments

- `--input`: Input TXT path (required)
- `--output`: Output EPUB path (optional)
- `--title`: Book title (optional; defaults to file name)
- `--author`: Author (optional)
- `--language`: Language (default: `zh-CN`)
- `--split-mode`: `auto | novel | tutorial | length`
- `--title-style`: `full | clean` (default: `full`)
  - `full`: Keep full headings, such as `第一章 旧土`
  - `clean`: Remove numbering prefixes and keep only heading text
- `--min-chapter-chars`: Merge threshold for very short chapters (default: `300`)
- `--chunk-chars`: Chunk size for length mode (default: `8000`)
- `--verbose`: Print extra...