fullwidth-halfwidth-normalizer

全角/半角字符规范化工具。读取结构化数据文件，将文本中的全角ASCII字符（字母、数字、标点）转换为半角形式，并可按需执行指定 Unicode 正规化。适用于中日韩混排科研文本的统一预处理，不负责空白行删除、拼写纠错或重复标点合并。当用户提到全角转半角、半角规范化、全半角统一、全角字母数字转换等需求时使用此skill。

Jump to install

Repository: cas-bigdatalab/piflow
Last source activity: July 9, 2026 at 03:08
Detected SKILL.md language: Chinese
Stars: 539
Forks: 171

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/cas-bigdatalab/piflow --skill fullwidth-halfwidth-normalizer

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

4 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

name	fullwidth_halfwidth_normalizer
description	全角/半角字符规范化工具。读取结构化数据文件，将文本中的全角ASCII字符（字母、数字、标点）转换为半角形式，并可按需执行指定 Unicode 正规化。适用于中日韩混排科研文本的统一预处理，不负责空白行删除、拼写纠错或重复标点合并。当用户提到全角转半角、半角规范化、全半角统一、全角字母数字转换等需求时使用此skill。
name_zh	fullwidth_halfwidth_normalizer_全角半角规范化算子
input_params	[{"name":"input_path","type":"string","required":true,"description":"输入文件路径（支持CSV/TSV/Excel等）"},{"name":"output_path","type":"string","required":true,"description":"输出文件路径"},{"name":"text_columns","type":"string","required":false,"description":"处理的文本列，逗号分隔；默认全部字符串列"},{"name":"norm_form","type":"string","required":false,"description":"Unicode正规化形式：NFC/NFD/NFKC/NFKD；默认不执行"},{"name":"keep_newlines","type":"string","required":false,"description":"保留换行符（默认折叠为空格）"}]
output_params	[{"name":"output_path","type":"csv_file","description":"全角转半角后的结构化数据文件"}]
tag	数据清洗
publisher	COMMUNITY