13f-analyzer
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.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- 13f-analyzer
- description
- 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.
02 资源文件 2
- 脚本scripts/holding_analysis.py1.4 KB
- 脚本scripts/one_fund_analysis.py4.2 KB
03 SKILL.md 正文
Overview
The helper programs are installed under /skills/13f-analyzer/scripts. Run them
from that absolute path; the task workspace is normally /root, so
scripts/... and /root/scripts/... are not equivalent paths. If a helper
cannot be found, check /skills/13f-analyzer/scripts before writing a replacement
analysis pipeline.
Analyze the holding summary of a particular fund in one quarter:
python3 /skills/13f-analyzer/scripts/one_fund_analysis.py \
--accession_number ... \
--quarter 2025-q2 \
This script will print out several basic information of a given fund on 2025-q2, including total number of holdings, AUM, total number of stock holdings, etc.
Interpret the printed fields precisely:
Total AUMis the fund AUM across all reported holdings.Total number of holdingscounts all reported holding rows.Number of stock holdingscounts rows remaining after the helper's stockTITLEOFCLASSfilter. When a question asks how many stocks the fund holds, use this field—not total holdings,TABLEENTRYTOTAL, or the number of unique CUSIPs.
Analyze the change of holdings of a particular fund in between two quarters:
python3 /skills/13f-analyzer/scripts/one_fund_analysis.py \
--quarter 2025-q3 \
--accession_number <accession number assigned in q3> \
--baseline_quarter 2025-q2 \
--baseline_accession_number <accession number assigned in q2>
Picking the right accession_number for each quarter
Accession numbers are per-filing, so the same manager will have different accession numbers in Q2 and Q3. Resolve each quarter independently:
- Use
/skills/fuzzy-name-search/scripts/search_fund.py --keywords "<name>" --quarter <2025-qN>to list candidate filers. Large managers (e.g., Berkshire Hathaway) often return multiple affiliated entities. - Among non-amendment matches, choose the filer whose
Total AUM(equivalently SUMMARYPAGEtableValueTotal) is the largest — that is the primary filer. You can confirm by running the single-quarter mode above and inspecting the printedTotal AUM. - Repeat the resolution in the other quarter before invoking the cross-quarter command. Do NOT reuse a Q2 accession number in Q3.
What the cross-quarter output actually contains
Internally the script joins the two quarters on CUSIP (outer join; missing
side filled with 0) and computes a signed dollar-value delta
ABS_CHANGE = VALUE (current quarter) - VALUE_base (baseline quarter).
It then prints two blocks:
Top 10 Buys from <baseline_quarter> to <quarter>: rows withABS_CHANGE > 0, sorted byABS_CHANGEdescending. This block already includes both brand-new positions (baseline VALUE = 0) AND increases on positions that already existed in the baseline quarter. Do not post-filter to "only new positions".Top 10 Sells from <baseline_quarter> to <quarter>: rows withABS_CHANGE < 0, sorted byABS_CHANGEascending (largest dollar decrease first).
Ranking is by the printed Abs change column (the signed dollar-value delta),
NOT by the current-quarter notional VALUE. For a question of the form
"top N stocks that received increased investment, ranked by dollar value
increase", the answer is the first N rows of the Top Buys block; report their
CUSIPs as printed (upper-case, as stored).
Scope note: the cross-quarter comparison reuses the same stock TITLEOFCLASS
whitelist as the single-quarter mode, so the Top Buys / Top Sells blocks are
already restricted to stock holdings and are appropriate for stock-only
questions without further filtering.
Analyze which funds hold a stock to the most extent
python3 /skills/13f-analyzer/scripts/holding_analysis.py \
--cusip <stock cusip> \
--quarter 2025-q3 \
--topk 10
This script will print out the top 10 hedge funds who hold a particular stock with highest notional value.
04 同仓库更多 Skills
video-frame-extraction
Extract frames from video files and save them as images using OpenCV
openai-vision
Analyze images and multi-frame sequences using OpenAI GPT vision models
image-ocr
Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms
video-frame-extraction
Extract frames from video files and save them as images using OpenCV
openai-vision
Analyze images and multi-frame sequences using OpenAI GPT vision models
image-ocr
Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms