Skip to content
Back to skills

Bank T168 Retail Finance Complaint Attribution Assistant

ASecurity

当用户需要在银行零售金融场景下,对客户投诉进行归因拆解、驱动项识别、问题定位与改进建议输出时使用本技能。适合输出归因结论、证据链与后续改进动作。

  • 232 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added June 6, 2026
documentationpythonbash

Security analysis

A100/100

Pro scans all 11 files and shows the line behind each finding

Scanned June 6, 2026

npx -y skills add aifinlab/FinClaw --skill bank-t168-retail-finance-complaint-attribution-assistant --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Bank T168 Retail Finance Complaint Attribution Assistant?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Bank T168 Retail Finance Complaint Attribution Assistant
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aifinlab-bank-t168-retail-finance-complaint-attribution-ass/badge)](https://www.skillsdirectory.com/skills/aifinlab-bank-t168-retail-finance-complaint-attribution-ass)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: bank-t168-retail-finance-complaint-attribution-assistant
description: "当用户需要在银行零售金融场景下,对客户投诉进行归因拆解、驱动项识别、问题定位与改进建议输出时使用本技能。适合输出归因结论、证据链与后续改进动作。"
---

# 客诉归因助手

本技能用于将投诉数据转化为“可解释的归因结论 + 可落地的改进动作”。强调口径一致、证据链清晰、相关性与因果区分,不用于替代审计或法律意见。

## 适用范围
- 客服与运营的投诉归因分析
- 重点产品或渠道的客诉专题诊断
- 服务改进与流程复盘

## 何时使用
- 需要识别投诉的主要驱动项与集中环节时
- 需要把投诉数据翻译成业务可执行的改进建议时

## 何时不要使用
- 没有样本、口径或时间窗口时
- 需要正式审计或法律意见才能定责的场景

## 默认工作流
1. 明确投诉口径、时间窗口与样本范围
2. 进行类型/产品/渠道/环节分布拆解
3. 识别TOP驱动项与证据链缺口
4. 输出改进动作与复盘指标

## 重点分析框架
- 现象是否稳定,是否为结构性问题
- 驱动项是否可解释、可行动
- 流程环节是否存在共性阻塞点
- 归因结论的证据充分度

## 输入要求
- 最低可用输入:`time_window`、`complaints`
- 推荐输入字段见 `references/input-schema.md`

## 输出要求
- 投诉归因摘要与TOP驱动项
- 类型、产品、渠道、环节分布
- 证据缺口与补充建议
- 改进动作与复盘建议

## 风险与边界
- 不将相关性直接等同因果
- 不输出“定责”结论,需保留待核验提示

## 信息不足时的处理
- 样本不足时仅输出趋势观察与补充建议
- 缺少口径说明时必须标注

## 交付标准
- 归因结论可解释、可追溯
- 动作建议可落地、可复盘

## 配套脚本

```bash
python scripts/run_skill.py --input assets/example-input.json --format markdown
python scripts/run_skill.py --input assets/example-input.json --format json
```

脚本入口:`scripts/run_skill.py`(调用 `shared/retail_service_ops_skill_engine.py` 的 `t168` 场景)。

Files in this skill

  • SKILL.md2.2 KB
  • assets/example-input.json741 B
  • assets/templates/attribution-report-template.md296 B
  • assets/templates/driver-tree-template.md93 B
  • assets/templates/improvement-actions-template.md115 B
  • references/attribution-methodology.md154 B
  • references/complaint-taxonomy.md298 B
  • references/evidence-standards.md174 B
  • references/input-schema.md467 B
  • references/output-schema.md512 B
  • scripts/run_skill.py1.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.