Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/aifinlab/FinClaw --skill early-repayment-churn-analysisThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Based on SOC occupation classification
Showing SKILL.md
| name | early-repayment-churn-analysis |
| description | 识别零售信贷客户的提前还款行为和结清后流失风险，基于强/中/弱信号分级评估，输出优先维系对象和挽留建议。 |
零售信贷客户提前还款后，银行面临利息收入损失和客户关系断裂的双重风险。部分客户提前结清贷款后迅速转移资产、关闭账户，导致综合贡献归零。需要及时识别提前还款行为特征，评估结清后的流失风险等级，锁定高价值维系对象，在客户流失前采取挽留措施。
| 输入项 | 说明 | 是否必填 |
|---|---|---|
| 客户编号/客户列表 | 单个或批量客户标识 | 必填 |
| 贷款信息 | 贷款品种、金额、期限、利率、已还期数 | 必填 |
| 提前还款记录 | 提前还款日期、金额、部分/全部结清 | 必填 |
| AUM变化 | 结清前后AUM变化趋势 | 选填 |
| 交易行为 | 结清后交易频次和金额变化 | 选填 |
| 产品持有变化 | 结清后产品持有数量变化 | 选填 |
| 渠道行为 | 结清后登录频次变化 | 选填 |
| 客户价值层级 | 当前分层结果（如有） | 选填 |
# 调用 skill
result = run_skill({
"param1": "value1",
"param2": "value2"
})
python scripts/run_skill.py --input data.json