run2_fuzzy-fund-search
Fuzzy search for hedge funds or stocks by name in SEC 13F filings; handles cases where rank 1 is skipped due to amendment filtering.
- License 许可
- MIT
- 最近更新
- 2026-10-02
- Stars
- ★ 93
- Forks
- 7
01 前言 Front Matter
- name
- run2_fuzzy-fund-search
- description
- Fuzzy search for hedge funds or stocks by name in SEC 13F filings; handles cases where rank 1 is skipped due to amendment filtering.
03 SKILL.md 正文
Fuzzy Fund and Stock Search (Improved)
Overview
Uses Levenshtein-based fuzzy search to find fund names and stock CUSIPs in SEC 13F data.
Setup
- Scripts:
/root/.claude/skills/fuzzy-name-search/scripts/ - Data:
/root/2025-q2/and/root/2025-q3/
IMPORTANT: Rank 1 May Be Skipped
The search_fund.py script filters out amendments (ISAMENDMENT == 'N'). If the best match only has amendments, rank 1 is silently skipped and output starts from rank 2.
Workaround: Always grep COVERPAGE.tsv directly when the fund isn't in rank 1:
grep -i "renaissance technologies" /root/2025-q3/COVERPAGE.tsv
This gives the raw row with ACCESSION_NUMBER (column 1) and FILINGMANAGER_NAME.
Search a Fund by Name
python3 /root/.claude/skills/fuzzy-name-search/scripts/search_fund.py \
--keywords "renaissance technologies" \
--quarter 2025-q3 \
--topk 5
If rank 1 is missing, use grep fallback (see above).
Search a Fund by Accession Number
python3 /root/.claude/skills/fuzzy-name-search/scripts/search_fund.py \
--accession_number 0001037389-25-000064 \
--quarter 2025-q3
Search a Stock CUSIP by Name
python3 /root/.claude/skills/fuzzy-name-search/scripts/search_stock_cusip.py \
--keywords "palantir" \
--topk 3
Returns consistent CUSIP regardless of rank (same stock repeated): 69608A108 for Palantir.
Known Fund Accession Numbers (Q3 2025)
- Renaissance Technologies LLC:
0001037389-25-000064 - Berkshire Hathaway Inc (Q3):
0001193125-25-282901 - Berkshire Hathaway Inc (Q2):
0000950123-25-008343
04 同仓库更多 Skills
object_counter
Count occurrences of an object in the image using computer vision algorithm.
travel-planning-workflow
Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.
bundled-dataset-search-tool
invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.
glm-output
Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final /root/metrics.json.
glm-calibration
Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.
glm-basics
A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.