Fuzzy string matching

Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/financial-analysis/fuzzy-string-matching

A skill for finding best string matches in datasets using fuzzy matching libraries like fuzzywuzzy or rapidfuzz.From its SKILL.md

Install

npx -y skills add cxcscmu/SkillLearnBench --skill fuzzy-string-matching

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

0.8 KB, 170 tokens by cl100k_base, as published. Nobody here has run it

Fuzzy String Matching

This skill demonstrates how to use fuzzy string matching to find company or fund names in a dataset.

Requirements

fuzzywuzzy or rapidfuzz
python-Levenshtein (optional but recommended for speed)

Installation

pip install rapidfuzz

Usage

import pandas as pd
from rapidfuzz import process, fuzz

df = pd.read_csv('data.tsv', sep='\t')
names = df['NAME_COLUMN'].dropna().unique()

# Find the best match
query = "Renaissance Technologies"
best_match = process.extractOne(query, names, scorer=fuzz.token_sort_ratio)

print(f"Best match: {best_match[0]} with score {best_match[1]}")

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.