Run3 Load Holdings Data by Accession Number
Retrieve and load the complete holdings dataset for a specific fund using its accession_number. Use this to access position-level details needed for AUM, stock count, and comparative analysis.From its SKILL.md
npx -y skills add cxcscmu/SkillLearnBench --skill run3_Load-Holdings-Data-by-Accession-NumberAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.3 KB, 234 tokens by cl100k_base, as published. Nobody here has run it
Steps
-
Construct the file path
- Use the accession_number to locate the holdings file in the data folder
- Typical path structure:
/root/[quarter]/[accession_number]_holdings.txtor similar - Check folder structure if path is unclear
-
Load the holdings data
- Read the file into a DataFrame with appropriate delimiters
- Preserve data types (especially numeric fields for share counts and values)
-
Inspect loaded data
- Confirm number of rows matches expected holdings count
- Verify all required columns are present: security identifiers, share count, market value, security type
- Check for null values that might affect calculations
-
Validate data integrity
- Spot-check a few rows for reasonable values (positive shares, positive values)
- Confirm security identifiers (CUSIP, ticker) are properly formatted
- Flag any data quality issues before proceeding
-
Cache or store for reuse
- If the same accession_number is needed multiple times, store the DataFrame
- Avoid reloading the same data multiple times in subsequent steps
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.