funnel-analysis

GitHub

诊断业务漏斗各环节转化率,定位流失点并提供优先行动建议。通过确认阶段定义、查询数据计算转化与流失、细分最大损失来源,最终输出量化结论及三项核心优化策略。

skills/funnel-analysis/SKILL.md Zafer-Liu/Data-Analysis-Agent

Trigger Scenarios

分析用户注册到付费的转化漏斗 定位电商下单流程中的主要流失环节 评估营销活动各步骤的用户留存情况

Install

npx skills add Zafer-Liu/Data-Analysis-Agent --skill funnel-analysis -g -y
More Options

Use without installing

npx skills use Zafer-Liu/Data-Analysis-Agent@funnel-analysis

指定 Agent (Claude Code)

npx skills add Zafer-Liu/Data-Analysis-Agent --skill funnel-analysis -a claude-code -g -y

安装 repo 全部 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --all -g -y

预览 repo 内 skill

npx skills add Zafer-Liu/Data-Analysis-Agent --list

SKILL.md

Frontmatter
{
    "icon": "🔻",
    "name": "funnel-analysis",
    "description": "诊断业务漏斗各环节转化率,定位主要流失点并给出优先行动建议(conversion 转化分析)",
    "allowedTools": [
        "get_schema",
        "query_data",
        "generate_chart"
    ]
}

Funnel analysis workflow

Apply this workflow to the user's request:

$ARGUMENTS

  1. Confirm the funnel stages, entity identifier, time field, and analysis period. Ask one concise question if a critical definition is missing.
  2. Inspect the schema before querying. Never invent stage names or event definitions.
  3. Calculate the entity count at each stage, step conversion rate, cumulative conversion rate, and loss from the preceding stage.
  4. Segment the largest loss by relevant dimensions such as channel, region, product, or customer cohort when the data supports it.
  5. Separate observed facts from hypotheses. Quantify every important claim and cite the source table or analysis result.
  6. End with the top three prioritized actions, their expected mechanism, and the metric that should be monitored.

Prefer a funnel chart or a compact stage-by-stage table. If stage ordering is ambiguous, do not guess—ask the user.

Tool routing

  1. Use get_schema to identify candidate event, stage, entity, time, and segmentation fields.
  2. Use query_data to compute stage counts, conversion rates, cumulative conversion, and loss by segment.
  3. Use generate_chart only after the funnel table is available and the stage order is explicit.
  4. If stage definitions or ordering are missing, ask one concise clarification before querying.

Implementation reference

  • Query tool entry: agent/tools/business/data.py::_tool_query_data
  • Chart tool entry: agent/tools/business/data.py::_tool_generate_chart
  • Chart implementation: Function/Charts_generation/chart_generate.py

Version History

  • d6a2c3e Current 2026-07-24 12:12

Same Skill Collection

skills/ab-test-analysis/SKILL.md
skills/bcg-matrix/SKILL.md
skills/business-model-canvas/SKILL.md
skills/swot-analysis/SKILL.md
skills/value-proposition/SKILL.md
skills/arima/SKILL.md
skills/chart/SKILL.md
skills/dashboard/SKILL.md
skills/data/SKILL.md
skills/decile/SKILL.md
skills/export/SKILL.md
skills/feishu-bitable/SKILL.md
skills/gru/SKILL.md
skills/inset/SKILL.md
skills/kmeans/SKILL.md
skills/logistic/SKILL.md
skills/ppt/SKILL.md
skills/prophet/SKILL.md
skills/regression/SKILL.md
skills/report/SKILL.md
skills/sarima/SKILL.md
skills/screening/SKILL.md
skills/sql/SKILL.md
skills/tree/SKILL.md
skills/trimming/SKILL.md
skills/var/SKILL.md
skills/winsorize/SKILL.md

Metadata

Files
0
Version
6464cc1
Hash
5d4a15ff
Indexed
2026-07-24 12:12

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-10 07:42
浙ICP备14020137号-1 $お客様$