agentsclimarketplace

File data extraction

Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-flash-lite-preview/financial-analysis/file-data-extraction

Techniques for parsing TSV/JSON files for financial reporting data (13F).From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill file-data-extraction

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, 166 tokens by cl100k_base, as published. Nobody here has run it

File Data Extraction

When dealing with 13F financial data, the primary data formats encountered are TSV (Tab Separated Values) and JSON.

Parsing TSV

TSV files (like COVERPAGE.tsv and INFOTABLE.tsv) should be treated as structured datasets. Use pandas in Python to quickly aggregate, filter, and compare data.

Example snippet:

import pandas as pd

# Load TSV
df = pd.read_csv('COVERPAGE.tsv', sep='\t')
# Filter for specific fund
fund_data = df[df['name'].str.contains('RENAISSANCE TECHNOLOGIES', case=False)]

Parsing JSON

Metadata files often use JSON. Use the standard json library or pandas.read_json for consistency with TSV processing.

What ships with it

Read from the repository

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

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.