Run2 13f fund summary
How to calculate a fund's actual AUM and total unique stock count for modern SEC 13F data.From its SKILL.md
npx -y skills add cxcscmu/SkillLearnBench --skill run2_13f-fund-summaryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.4 KB, 348 tokens by cl100k_base, as published. Nobody here has run it
Overview
Starting in 2023, the SEC began requiring funds to report exact dollar amounts in the SUMMARYPAGE.tsv and INFOTABLE.tsv VALUE columns, replacing the old system where values were reported in thousands.
Usage Patterns
Calculating True AUM
The total value is now precisely reported in exact dollars.
import pandas as pd
accession_number = "0001037389-25-000064"
quarter = "2025-q3"
summary = pd.read_csv(f"/root/{quarter}/SUMMARYPAGE.tsv", sep="\t", dtype=str)
match = summary[summary["ACCESSION_NUMBER"] == accession_number]
if not match.empty:
# 13F forms currently report VALUES in EXACT dollars (no longer in thousands)
aum = float(match["TABLEVALUETOTAL"].iloc[0])
print(f"Total AUM: ${aum:,.2f}")
Counting Unique Stock Holdings
Since one CUSIP can have multiple rows (for different investment discretion types or voting authority), use nunique() on the CUSIP column.
import pandas as pd
infotable = pd.read_csv(f"/root/2025-q3/INFOTABLE.tsv", sep="\t", dtype=str)
holdings = infotable[infotable["ACCESSION_NUMBER"] == "0001037389-25-000064"]
# Number of unique CUSIPs represents the total number of stocks held
unique_stocks = holdings["CUSIP"].nunique()
print(f"Number of Unique Stocks Held: {unique_stocks}")
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.