agentsclimarketplace

Run3 one fund analysis

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/financial-analysis/run3_one_fund_analysis

[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 run3_one_fund_analysis

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

Extracts AUM and total holdings count for a specific fund using its accession number and the quarter folder path.

SKILL.md

0.7 KB, 151 tokens by cl100k_base, as published. Nobody here has run it

To retrieve fund metrics, use the scripts/one_fund_analysis.py tool.

  1. Parameters:
    • --accession_number: The ID found via fuzzy search.
    • --quarter_path: The directory path (e.g., /root/2025-q3).
  2. Unit Handling: Ensure the final AUM calculation accounts for the 1,000x scaling factor typically used in SEC filings (if the raw data is in thousands, multiply by 1,000 to reach the base unit).
  3. Execution: 
    python3 scripts/one_fund_analysis.py --accession_number <acc_num> --quarter_path /root/2025-q3

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 327,132. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.