clerk-structure-analysis
分析门店导购的表现结构,识别导购波动对门店业绩波动的贡献度,输出下钻分析目标列表。
python
import sys
sys.path.insert(0, '~/.openclaw/skills/clerk-structure-analysis')
from analyze import analyze
# 基础用法(默认累计贡献度80%)
result = analyze(
store_id="416759_1714379448487",
from_date="2026-03-01",
to_date="2026-03-25",
store_name="正义路60号店"
)
# 自定义选择标准
result = analyze(
store_id="416759_1714379448487",
from_date="2026-03-01",
to_date="2026-03-25",
store_name="正义路60号店",
selection_mode="cumulative", # 累计贡献度模式
cumulative_threshold=0.7 # 阈值70%
)
参数类型必填默认值说明store_idstr是-门店IDfrom_datestr是-分析开始日期 (YYYY-MM-DD)to_datestr是-分析结束日期 (YYYY-MM-DD)store_namestr否""门店名称(用于输出)selection_modestr否"cumulative"选择模式: cumulative/top_n/thresholdcumulative_thresholdfloat否0.8累计贡献度阈值 (0-1)top_nint否3固定取前N名min_loss_thresholdfloat否None最小损失阈值(元)
模式标准适用场景cumulative累计贡献度达到阈值找"关键少数",帕累托法则top_n固定取前N名明确要分析几名导购threshold超过最小损失阈值过滤掉小额波动
json
{
"status": "ok",
"store_id": "...",
"store_name": "...",
"analysis_period": {"from": "...", "to": "..."},
"structure": {
"clerk_count": 7,
"total_sales": 313226,
"top3_share": 0.609,
"bottom3_share": 0.252,
"pareto_ratio": 0.216,
"efficiency_cv": 0.43,
"mean_sales": 44747
},
"contributions": [...],
"key_persons": {
"selection_criteria": {...},
"total_decline": -253022,
"total_growth": 45678,
"growth_clerks": [...],
"decline_clerks": [...],
"key_contributors": [...],
"key_drags": [...],
"drill_down_targets": [
{
"rank": 1,
"name": "陈二妹",
"sales_change": -83464,
"change_pct": -72.3,
"cumulative_share": 33.0,
"current_sales": 31922,
"prev_sales": 115386,
"current_orders": 50,
"prev_orders": 146,
"atv": 638,
"attach": 1.4
}
]
},
"findings": [...],
"total_change": -207344
}
指标说明健康范围top3_shareTOP3导购业绩占比< 70%efficiency_cv人效变异系数< 0.5pareto_ratio20%导购贡献的业绩占比-
指标说明rank下滑排名sales_change销售额变化(元)change_pct变化率(%)cumulative_share累计贡献度(%)current_sales本期销售额prev_sales上期销售额current_orders本期订单数prev_orders上期订单数atv客单价attach连带率
问题判断条件严重程度导购大面积下滑下滑导购占比 > 50%🔴 高头部集中度过高TOP3占比 > 70%🟡 中人效差异过大变异系数 > 0.5🟡 中关键拖累者累计贡献度前80%的下滑导购🔴 高
v1.0.0 - 导购表现结构与波动归因分析