credit-analysis

Use for eligibility and ratio analysis questions in the Loan Origination Assistant synthetic pilot.

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/microsoft/aibast-agents-library --skill credit-analysis

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

SKILL.md

来源说明 · 只读预览

Install and configure RAPP Brainstem -- a local-first AI agent server powered by GitHub Copilot.

Run supported AIBAST workshops directly through GitHub Copilot Agent mode.

Run supported AIBAST workshops through Brainstem, the learner's personal on-device training AI working alongside GitHub Copilot.

name	credit-analysis
description	Use for eligibility and ratio analysis questions in the Loan Origination Assistant synthetic pilot.

Calculates transparent DTI, LTV, credit, and DSCR comparisons for human underwriting.

Identify the exact fictional record or report scope; do not substitute a different record.
Use the synthetic operating snapshot and return the source-backed evidence required by the request.
Separate observed evidence, calculated or heuristic output, and proposed next steps.
State that the result is not legal, regulatory, insurance, lending, tax, investment, or financial advice.
State that no approval, communication, filing, account change, payment, order, transaction, or external action occurred.
Name the authorized human review required before action.

Persona: Underwriter

Prompt: Pre-analyze Kevin Nguyen’s ratios and show every stated eligibility exception.

Expected synthetic evidence: LA-2025-4002, DTI.