1oid/txt-to-epub/SKILL.md
将txt文本转换为epub文件,使用纯规则进行章节识别与分割。适用于小说、教程和一般长文,不内置AI接口。
npx skillsauth add openclaw/skills txt-to-epubInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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。
auto | novel | tutorial | length 四种模式第一章 ... / 第十回 ...Chapter 1 ... / Part 2 ...1.2 ... / 2.3.4 ...一、...Part 1/2/...--title-style full:保留完整标题
第一章 xxx,目录和章节标题都保持 第一章 xxx--title-style clean:去掉编号前缀,仅保留正文标题/Users/loid/.claude/skills/txt-to-epub/scripts/txt_to_epub.py
python3 -m pip install -r /Users/loid/.claude/skills/txt-to-epub/requirements.txt
最小示例:
python3 /Users/loid/.claude/skills/txt-to-epub/scripts/txt_to_epub.py \
--input /path/to/book.txt
常用示例(小说):
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):
python3 /Users/loid/.claude/skills/txt-to-epub/scripts/txt_to_epub.py \
--input /path/to/tutorial.txt \
--split-mode tutorial \
--title-style full
--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 输出额外信息当用户请求转换时:
--input)--title-style full--split-mode:
noveltutorialauto--split-mode 或调整 --chunk-charstools
Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.
development
Web scraping platform — Twitter/X data, Vinted marketplace, and general web scraping API
development
SlowMist AI Agent Security Review — comprehensive security framework for skills, repositories, URLs, on-chain addresses, and products (Claude Code version)
data-ai
去除中文文本中的 AI 写作痕迹,使其读起来自然。基于维基百科 AI 写作特征指南,检测 24 种 AI 模式。触发词:humanizer-cn、去除 AI 痕迹、去除 AI 写作痕迹、中文文本人性化。