ワンクリックでManusで任意のスキルを実行

funnel-analysis

スター3

フォーク3

更新日2026年6月14日 05:06

Analyse conversion through a multi-step process, identify where users drop off, and diagnose why. Activate when conversion is low, when comparing conversion across segments, or when optimising a user journey.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

ryudkiss-hue

ryudkiss-hue/nyc_data

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

When to use

Conversion is low and the team needs to know where users are dropping off
Comparing conversion rates across channels, devices, or user segments
A product change was made and you need to measure its effect on funnel completion
Building a business case for investing in a specific funnel step

Process

Define funnel steps and timeframe — list ordered steps (e.g. Visit → Signup → Activate → Purchase); define completion window (e.g. must complete within 7 days). Ambiguous definitions here will invalidate the analysis.
Build user-level dataset — extract first occurrence of each event per user within the completion window using scripts/funnel_analyzer.py
Calculate conversion metrics — compute absolute counts, step-to-step conversion rates, and overall funnel conversion rate
Analyse time-to-convert — calculate median and distribution of time between steps; identify whether slow converters have lower overall completion
Segment the funnel — break conversion by available dimensions (channel, device, geography, user segment); identify highest-impact differences
Prioritise recommendations — rank drop-off points by (users lost × revenue impact per user); fill assets/funnel_report_template.md

Inputs the skill needs

Required: event log data with user ID, event name, and timestamp
Required: ordered list of funnel steps
Required: completion window (e.g. 30 days from first step)
Optional: segmentation dimensions
Optional: estimated revenue value of a completed conversion

Output

scripts/funnel_analyzer.py — computes step-by-step conversions and drop-offs from event logs
references/funnel_design_guide.md — funnel definition patterns and common measurement pitfalls
assets/funnel_report_template.md (filled) — funnel table, segment comparison, and ranked recommendations

このリポジトリの他の Skills

同じリポジトリ

data-catalog-entry

ryudkiss-hue/nyc_data

Create standardized metadata for data assets. Use when documenting new datasets, building data catalogs, improving data discoverability, or creating data dictionaries for teams.

2026-06-173

analysis-planning

ryudkiss-hue/nyc_data

Structure analysis approach before starting work. Use when receiving new analysis requests, breaking down complex questions into steps, or planning iterative analysis workflows.

2026-06-173

data-quality-audit

ryudkiss-hue/nyc_data

Comprehensive data quality assessment against business rules, schema constraints, and freshness expectations. Activate when validating production pipelines, onboarding new data sources, or when stakeholders report data quality concerns.

2026-06-143

segmentation-analysis

ryudkiss-hue/nyc_data

Identify distinct customer or user segments based on behavior, attributes, or value. Activate when you need to answer "who are our best customers?" or "what distinct groups exist in our user base?" and need data-driven profiles to inform strategy.

2026-06-143

visualization-builder

ryudkiss-hue/nyc_data

Create effective, publication-ready data visualizations. Use when choosing chart types, designing presentation visuals, building dashboard charts, or applying visual design best practices to data output.

2026-06-143

methodology-explainer

ryudkiss-hue/nyc_data

Create a clear, transparent explanation of analytical methodology for any audience level. Activate when you deliver findings that require the audience to trust the method — A/B tests, attribution models, forecasts, statistical analyses, or anything where "how did you get that?" is a likely question.

2026-06-143

name	funnel-analysis
description	Analyse conversion through a multi-step process, identify where users drop off, and diagnose why. Activate when conversion is low, when comparing conversion across segments, or when optimising a user journey.

When to use

Conversion is low and the team needs to know where users are dropping off
Comparing conversion rates across channels, devices, or user segments
A product change was made and you need to measure its effect on funnel completion
Building a business case for investing in a specific funnel step

Process

Define funnel steps and timeframe — list ordered steps (e.g. Visit → Signup → Activate → Purchase); define completion window (e.g. must complete within 7 days). Ambiguous definitions here will invalidate the analysis.
Build user-level dataset — extract first occurrence of each event per user within the completion window using scripts/funnel_analyzer.py
Calculate conversion metrics — compute absolute counts, step-to-step conversion rates, and overall funnel conversion rate
Analyse time-to-convert — calculate median and distribution of time between steps; identify whether slow converters have lower overall completion
Segment the funnel — break conversion by available dimensions (channel, device, geography, user segment); identify highest-impact differences
Prioritise recommendations — rank drop-off points by (users lost × revenue impact per user); fill assets/funnel_report_template.md

Inputs the skill needs

Required: event log data with user ID, event name, and timestamp
Required: ordered list of funnel steps
Required: completion window (e.g. 30 days from first step)
Optional: segmentation dimensions
Optional: estimated revenue value of a completed conversion

Output

scripts/funnel_analyzer.py — computes step-by-step conversions and drop-offs from event logs
references/funnel_design_guide.md — funnel definition patterns and common measurement pitfalls
assets/funnel_report_template.md (filled) — funnel table, segment comparison, and ranked recommendations