evo-text-normalize
SkillDev toolsPreprocesses and normalizes noisy multilingual (Chinese-English mixed) industrial text. Handles full-width to half-width conversion, Unicode NFKC normalization, lowercasing, whitespace cleanup, punctuation normalization, abbreviation expansion, and splitting compound reasons.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the evo-text-normalize skill
What this skill tells your AI
The instructions your AI receives, as published by openlair/openskill in tasks-evolved/manufacturing-codebook-normalization/environment/skills/evo-text-normalize/SKILL.md and read by ahel’s review.
Text preprocessing for noisy manufacturing defect logs with mixed Chinese-English content.
Key Functions
normalize_width(text)- NFKC normalization + Chinese punctuation mappingpreprocess_text(text)- Full pipeline: width norm, lowercase, whitespace, abbreviationsexpand_abbreviations(text)- Expand common manufacturing abbreviationssplit_mixed_text(text)- Split mixed Chinese/English into contiguous blockssplit_compound_reasons(raw_text)- Split compound reasons by delimiters, preserving spans
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-text-normalize/scripts')
from utils import preprocess_text, split_compound_reasons, normalize_width
clean = preprocess_text("ＰＣＢ Ｆａｉｌ")
segments = split_compound_reasons("scratch on panel, button stuck; 屏幕坏了")
Signals
- GitHub stars
- 89
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
evo-text-normalize- Source
- github.com/openlair/openskill