Jaypatel1511
UserAI skills for NMTC eligibility, bank-CDFI peer benchmarking & HMDA analysis — grounded in audited PyPI tools, not hallucinated.
Categories
Indexed Skills (3)
cdfi-peer-benchmark
Benchmark a bank CDFI against a peer group on FDIC call-report metrics (NIM, ROAA, ROAE, efficiency ratio, Tier 1 capital, loans-to-deposits, NPL ratio, loan-loss coverage). Use when the user says "benchmark this CDFI", wants a "peer comparison", or asks "how does this bank CDFI compare". Bank CDFIs only (FDIC-insured) — no credit unions, no unregulated loan funds. Backed by the audited PyPI package cdfi-benchmark; import name is `cdfibenchmark`.
hmda-analysis
Pull and describe HMDA mortgage-lending data (LAR records) for a county, state, lender (LEI), or multiple years, and compute a CRA-PROXY borrower- and tract-income distribution. Use when the user says "pull HMDA data", "LAR records", "mortgage lending data for [county/state/lender]", or "multi-year HMDA". DESCRIPTIVE ONLY — this skill does not do disparity, disparate-impact, or fair-lending analysis. Backed by the audited PyPI package hmda-analyzer.
nmtc-eligibility
Check whether a U.S. address or census tract is New Markets Tax Credit (NMTC) eligible as a Low-Income Community, and screen a project's NMTC feasibility. Use when the user asks "is this address/tract NMTC eligible", about "distress criteria", "severe distress", "deep distress", "low-income community" / "LIC" status, or wants a first-pass NMTC deal feasibility score. Backed by the audited PyPI packages nmtc-mapper and nmtc-screener — never estimate eligibility from general knowledge.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.