القائمة
How to compare fund holdings between Q2 and Q3 to find top stocks with increased investment by dollar value
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/cxcscmu/SkillLearnBench --skill sec-13f-compare-holdings-q2-q3يبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Handles reading, populating, and saving .docx files using the python-docx library. Use this skill for any tasks involving template filling or modifying Word documents.
Perform various data analysis on SEC 13-F and obtain some insights of fund activities such as number of holdings, AUM, and change of holdings between two quarters.
This skill includes search capability in 13F, such as fuzzy search a fund information using possibly inaccurate name, or fuzzy search a stock cusip info using its name.
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | sec-13f-compare-holdings-q2-q3 |
| description | How to compare fund holdings between Q2 and Q3 to find top stocks with increased investment by dollar value |
# Check for holding comparison script
cat /root/2025-q3/scripts/holding_analysis.py 2>/dev/null
# It may accept two accession numbers for comparison
python /root/2025-q3/scripts/holding_analysis.py "<Q2_ACCESSION>" "<Q3_ACCESSION>" 2>/dev/null
import pandas as pd
# Search in Q2
cover_q2 = pd.read_csv('/root/2025-q2/COVERPAGE.tsv', sep='\t', low_memory=False)
search = "berkshire hathaway"
# Find the name column first
print(cover_q2.columns.tolist())
name_col = 'FILINGMANAGER_NAME' # adjust as needed
q2_matches = cover_q2[cover_q2[name_col].astype(str).str.lower().str.contains(search, na=False)]
print(q2_matches[['ACCESSION_NUMBER', name_col]])
accession_q2 = q2_matches['ACCESSION_NUMBER'].iloc[0]
# Search in Q3
cover_q3 = pd.read_csv('/root/2025-q3/COVERPAGE.tsv', sep='\t', low_memory=False)
q3_matches = cover_q3[cover_q3[name_col].astype(str).str.lower().str.contains(search, na=False)]
accession_q3 = q3_matches['ACCESSION_NUMBER'].iloc[0]
info_q2 = pd.read_csv('/root/2025-q2/INFOTABLE.tsv', sep='\t', low_memory=False)
info_q3 = pd.read_csv('/root/2025-q3/INFOTABLE.tsv', sep='\t', low_memory=False)
holdings_q2 = info_q2[info_q2['ACCESSION_NUMBER'] == accession_q2].copy()
holdings_q3 = info_q3[info_q3['ACCESSION_NUMBER'] == accession_q3].copy()
# Filter to stocks only (exclude options)
for df in [holdings_q2, holdings_q3]:
# Check PUTCALL values first
print(df['PUTCALL'].value_counts(dropna=False))
# Keep only non-option rows
def filter_stocks(df):
return df[df['PUTCALL'].isna() | (df['PUTCALL'].astype(str).str.strip().isin(['', 'nan', 'NaN', 'None']))]
holdings_q2 = filter_stocks(holdings_q2)
holdings_q3 = filter_stocks(holdings_q3)
# Aggregate VALUE by CUSIP (VALUE is in thousands)
q2_agg = holdings_q2.groupby('CUSIP')['VALUE'].sum().reset_index()
q2_agg.columns = ['CUSIP', 'VALUE_Q2']
q3_agg = holdings_q3.groupby('CUSIP')['VALUE'].sum().reset_index()
q3_agg.columns = ['CUSIP', 'VALUE_Q3']
# Merge
merged = q3_agg.merge(q2_agg, on='CUSIP', how='outer').fillna(0)
merged['VALUE_CHANGE'] = merged['VALUE_Q3'] - merged['VALUE_Q2']
# Top 5 increased investments
top5_increased = merged.sort_values('VALUE_CHANGE', ascending=False).head(5)
print(top5_increased[['CUSIP', 'VALUE_Q2', 'VALUE_Q3', 'VALUE_CHANGE']])
top5_cusips = top5_increased['CUSIP'].tolist()