Run2 fund analysis pro

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/financial-analysis/run2_fund-analysis-pro

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Install

npx -y skills add cxcscmu/SkillLearnBench --skill run2_fund-analysis-pro

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

What its author says it does

Copied from the file, not written here

Advanced fund analysis with share change verification to distinguish between price movement and deliberate investment.

SKILL.md

1.0 KB, 229 tokens by cl100k_base, as published. Nobody here has run it

Usage

Handling Script Bugs

The provided one_fund_analysis.py may have bugs in its stock classification list (missing commas). For accurate results, use a custom Python script or manual aggregation:

import pandas as pd
df = pd.read_csv("/root/2025-q3/INFOTABLE.tsv", sep="\t", dtype=str)
df["VALUE"] = df["VALUE"].astype(float)
df["SHARES"] = df["SSHPRNAMT"].astype(float)
# Filter by accession number and aggregate by CUSIP
fund_data = df[df["ACCESSION_NUMBER"] == "XXXXX-XX-XXXXXX"]
summary = fund_data.groupby("CUSIP").agg({"VALUE": "sum", "SHARES": "sum", "NAMEOFISSUER": "first"})

Distinguishing Investment Decisions

"Increased investment" should be verified by checking SHARE_CHANGE.

Calculate SHARE_CHANGE = SHARES_q3 - SHARES_q2.
Filter for SHARE_CHANGE > 0.
Rank by VALUE_CHANGE.

What ships with it

Read from the repository