Cdfi Superpowers — AI skill for Claude Code
AI skills for NMTC eligibility, bank-CDFI peer benchmarking & HMDA analysis — grounded in audited PyPI tools, not hallucinated.
How to install Cdfi Superpowers
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Jaypatel1511/cdfi-superpowers and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cdfi Superpowers does
AI skills for NMTC eligibility, bank-CDFI peer benchmarking & HMDA analysis — grounded in audited PyPI tools, not hallucinated.
Alternatives in AI
- Codex — openai-codex Adversarial code review, Codex CLI integration, cross-model analysis 9.6k ★
- Geo SEO Claude — GEO-first SEO skill for Claude Code 3.6k ★
- Dive Into Claude Code — A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems 2.1k ★
README
cdfi-superpowers
**Your AI, grounded in audited CDFI tooling instead of hallucinating tract eligibility.**
`cdfi-superpowers` is an **AI skill layer for the CDFI industry** — NMTC eligibility, bank CDFI peer benchmarking, and HMDA lending analysis, built for lenders, CDEs, compliance teams, and community development researchers.
Generic AI assistants confidently invent answers in this domain: wrong tract eligibility, fabricated peer medians, "CRA performance" claims from proxy data. In a field where numbers end up in loan committees, applications, and compliance reviews, that's not a quirk — it's a liability. These skills fix that by making your AI call real, open-source, audited tools and report exactly what they return — including N/A and errors — rather than inventing a plausible-sounding number.
The skills contain **no new analytical code**. Each one `pip install`s independently versioned, openly published Python packages (MIT-licensed, on [PyPI](https://pypi.org/user/thejaypatel1511/)) and teaches the AI to use them correctly, with the methodology caveats those tools ship with.
The three skills
| Skill | What it does | Backed by |
|---|---|---|
| nmtc-eligibility | Is this address/tract NMTC eligible? Distress tier? Project feasibility? | nmtc-mapper >=0.5.0, nmtc-screener 0.1.0 |
| cdfi-peer-benchmark | Benchmark a bank CDFI against FDIC peers (NIM, ROAA, capital, …) | cdfi-benchmark >=0.3.0 |
| hmda-analysis | Pull HMDA LAR data and produce descriptive cuts + a CRA-proxy distribution | hmda-analyzer >=0.6.0 |
Versions were verified against live PyPI at time of writing; every code example in each skill was actually executed and shows real output. Where a floor is shown as `>=`, it is **load-bearing** and the skill says why: `nmtc-mapper >=0.5.0` is where `is_opportunity_zone` stops returning a confident `False` — below it the package answers "not an Opportunity Zone" about 78,039 tracts it cannot distinguish from a 2010/2020
Related Skills
Peer AI
AI-to-AI peer consultation: install symmetric skills in Claude Code, Codex CLI, and Gemini CLI so any installe
Karpathy Wiki Protocol
Battle-tested protocol for AI agents (Claude Code, Codex, Cursor) to build and maintain Karpathy-style wikis.
Customer Service
A multi-provider AI customer service agent that automates order lookup, return-eligibility checks, and Stripe
Godot Agent Arena
Dockerized Godot Engine accessible via browser (noVNC + Guacamole) — a testbed for benchmarking browser-based
Fidelis
Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusio
AI Skills Bank
AI Skills Bank is a unified, multi-tool platform designed to aggregate, manage, and route AI skills across var
Related Agents
Peer Reviewer Qual
A simulated peer reviewer specializing in qualitative and ethnographic methods — in-depth interviews, ethnogra
Literature Expert
Expert literature discovery and citation metadata agent for peer-reviewed papers, preprints, DOI lookup, and e
Design Scout
Use this agent for competitive UX analysis, design benchmarking, user insight synthesis, design pattern resear
