Fuzzy name search

Skill cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-opus-4-6/financial-analysis/fuzzy-name-search

Fuzzy search fund names in SEC 13F COVERPAGE data or stock names in INFOTABLE data. Use this skill whenever searching for a fund or stock by name when the exact spelling or format is uncertain, or when performing case-insensitive partial matching on SEC filing data.From its SKILL.md

Install

npx -y skills add cxcscmu/SkillLearnBench --skill fuzzy-name-search

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

SKILL.md

1.4 KB, 302 tokens by cl100k_base, as published. Nobody here has run it

Fuzzy Name Search for 13F Data

Fund Name Search

Search COVERPAGE.tsv column FILINGMANAGER_NAME using case-insensitive substring or fuzzy matching.

import pandas as pd

cover = pd.read_csv('/root/2025-q3/COVERPAGE.tsv', sep='\t')
# Case-insensitive substring match
matches = cover[cover['FILINGMANAGER_NAME'].str.contains('renaissance', case=False, na=False)]
# Returns ACCESSION_NUMBER, FILINGMANAGER_NAME, etc.

Handling Multiple Matches

If multiple rows match, prefer non-amendment filings (ISAMENDMENT column is empty or 'N')
If still ambiguous, pick the best name match

Stock CUSIP Search

Search INFOTABLE.tsv column NAMEOFISSUER for a stock name, then extract the unique CUSIP.

info = pd.read_csv('/root/2025-q3/INFOTABLE.tsv', sep='\t')
matches = info[info['NAMEOFISSUER'].str.contains('palantir', case=False, na=False)]
cusip = matches['CUSIP'].unique()

Notes

CUSIP is 9 characters and uniquely identifies a security
A stock may have multiple entries in INFOTABLE (one per fund holding it)
Use .unique() on CUSIP to deduplicate

What ships with it

Read from the repository

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