SuperAPI AI Directory

kpi-root-cause-analysis

Data & analytics

View repository

Updated 10-16 08:46

About this skill

Load context

On first use: Read ../../CLAUDE.md to obtain scenario-level configuration (KPI definitions/historical benchmarks/improvement resources).


/kpi-root-cause-analysis — KPI Root Cause Analysis

Examples

→ Example: The user says "Gross margin has been below budget for 3 consecutive months. The business says it is due to rising raw material prices, but Finance thinks there is more to it than that." The system should invoke this skill and perform multi-dimensional root cause decomposition.

→ Example: The user says "Inventory turnover days suddenly increased by 15 days this month. Help me find the reason." The system should invoke this skill and perform root cause analysis by supply chain and sales dimensions.

→ Example: The user says "Operating profit margin dropped by 2 points. The CFO requires identifying exactly whose responsibility it is." The system should invoke this skill and perform responsibility unit attribution analysis.

Step 1: KPI Performance Confirmation

KPI target miss situation:

□ KPI 名称:[名称]
□ 目标值:[X]
□ 实际值:[X]
□ 缺口值:[X](目标 - 实际)
□ 达成率:[X]%(实际 / 目标 × 100%)
□ 未达标期间:[YYYY-MM]
□ 持续未达标期数:[X] 期(首次:[YYYY-MM])

Historical performance:

□ 近期表现:
| 期间   | 目标值 | 实际值 | 达成率 | 趋势 |
|--------|--------|--------|--------|------|
| [上期] | [X]    | [X]    | [X]%   | —    |
| [本期] | [X]    | [X]    | [X]%   | [↓]  |

□ 长期均值 vs 目标:[X] vs [X]
□ 未达标频率:[X] 次 / [X] 期

Step 2: Factor Decomposition

KPI decomposition tree (waterfall decomposition):

□ 第一层拆解(按业务维度):
KPI 总缺口 = [X]
├── [维度A] 贡献 [X]([占比]%)
│   ├── [子维度A1] 贡献 [X]
│   └── [子维度A2] 贡献 [X]
├── [维度B] 贡献 [X]([占比]%)
│   └── [子维度B1] 贡献 [X]
└── [维度C] 贡献 [X]([占比]%)

□ 主要缺口来源(Top 3):
1. [维度A]:[X],贡献 [X]% 的缺口
2. [维度B]:[X],贡献 [X]% 的缺口
3. [维度C]:[X],贡献 [X]% 的缺口

Quantitative analysis:

□ 各因素贡献度:
| 因素 | 贡献值 | 贡献占比 | 可控性 |
|------|--------|---------|--------|
| [因素A] | [X] | [X]% | [高/中/低] |
| [因素B] | [X] | [X]% | [高/中/低] |

Step 3: 5Why Root Cause Analysis

Perform 5Why analysis on the main gap factor:

□ 针对 [因素A] 的 5Why 分析:

Why 1:KPI 未达标的原因是什么?
→ Because:[因素A] 表现低于预期

Why 2:[因素A] 低的原因是什么?
→ Because:[更深层原因]

Why 3:[更深层原因] 的原因是什么?
→ Because:[更深层原因]

Why 4:[更深层原因] 的原因是什么?
→ Because:[更深层原因]

Why 5(根因):[最深层的根本原因]

□ 根因分类:
→ [人员能力 / 流程缺陷 / 系统限制 / 资源不足 / 外部因素 / 目标设定问题]

5Why for the second main factor (brief):

□ 针对 [因素B] 的根因:
→ Why 1 → Why 3:[简述链条]
→ 根因:[最深原因]
→ 根因分类:[分类]

Step 4: One-off vs Systemic Attribution

Attribution classification assessment:

□ 各因素归因:
| 因素 | 根因 | 归因类型 | 比重 |
|------|------|---------|------|
| [因素A] | [根因] | [一次性/系统性] | [X]% |
| [因素B] | [根因] | [一次性/系统性] | [X]% |

□ 一次性因素:
→ 名称:[因素]
→ 一次性贡献:[X](占总缺口 [X]%)
→ 说明:[为什么会发生]
→ 是否会重复:[可能/不太可能]

□ 系统性因素:
→ 名称:[因素]
→ 系统性贡献:[X](占总缺口 [X]%)
→ 说明:[根源于结构性/流程性/能力性问题]
→ 短期是否可解决:[是/否 — 预计 [X] 月]

Attribution conclusion:

□ 一次性因素合计贡献:[X]%(剔除后缺口 [X])
□ 系统性因素合计贡献:[X]%(须长期解决)
□ 目标设定问题(如有):[X]%(目标本身是否合理)

Step 5: Improvement Recommendations

Improvement recommendations for systemic factors:

□ 改进措施 1:[描述]
  → 针对根因:[根因描述]
  → 预期改善效果:[X](KPI 提升 [X])
  → 实施周期:[X] 周
  → 资源需求:[描述]
  → 责任人:[岗位/部门]
  → 预期完成:[YYYY-MM-DD]

□ 改进措施 2:[描述]
  → ...

Preventive recommendations for one-off factors:

□ 监控改进:[描述]
  → 针对 [一次性因素]
  → 建立监控指标:[指标]
  → 预警阈值:[X]

Target reset recommendation (if the target itself is unreasonable):

□ 建议:[调整目标至 X / 维持原目标但延长达成时间]
□ 理由:[描述]
□ 调整方案:[具体建议]
□ 调整后预期达成率:[X]%

Step 6: Generate Root Cause Analysis Report

═══════════════════════════════════════
KPI 根因分析报告
KPI:[名称]
期间:[YYYY-MM]
分析日期:[YYYY-MM-DD]
═══════════════════════════════════════

【KPI 表现】
□ 目标:[X] | 实际:[X] | 达成率:[X]%
□ 缺口:[X] | 持续未达标:[X] 期

【主要因素拆解】
□ Top 3 缺口来源:
1. [维度A] — 贡献 [X]%([X])
2. [维度B] — 贡献 [X]%([X])
3. [维度C] — 贡献 [X]%([X])

【根因分析(5Why)】
□ [因素A] 根因:
  → 根因:[最深原因]
  → 类型:[系统性/一次性]
  → 贡献:[X]%

□ [因素B] 根因:
  → ...

【归因汇总】
□ 系统性因素:[X]%(须长期改进)
□ 一次性因素:[X]%(短期规避 + 监控)
□ 目标问题(如有):[X]%

【改进建议】
□ 系统性改进:
  1. [措施] — 责任人 [X] — 完成 [日期] — 预期效果 [X]
  2. [措施] — 责任人 [X] — 完成 [日期] — 预期效果 [X]

□ 监控改进:[措施]
□ 目标调整建议:[有/无 — 理由]

【预测】
□ 如实施改进,[YYYY-MM] 预期 KPI 达成率 [X]%

═══════════════════════════════════════
置信度:[✅ 高 / ⚠️ 中 / 🔴 低]
根因确定性:[✅ 高(多因素分析)/ ⚠️ 中 / 🔴 低(信息不足)]
═══════════════════════════════════════

Escalation Trigger Conditions

  • Root cause analysis finds issues involving coordination across multiple departments (requires escalation)
  • Systemic factors require significant resource investment (> [X] ten thousand)
  • One-off factors recur (> [X] times), indicating that systemic root causes may exist
  • Root cause involves external factors (customers/suppliers/market) and cannot be directly influenced
  • KPI continues to miss targets and shows no trend of improvement
  • Recommend target reset (requires management approval)

Finance Skills — kpi-root-cause-analysis atomic skill