What is funnel-analysis?

A conversion-funnel analysis tool for examining how people move through a series of steps, such as visiting a page, signing up, and buying. It calculates how many continue at each step and can show the results in interactive charts.

Use it to study marketing campaigns, website or app journeys, onboarding, sales pipelines, and lead-nurturing processes. It helps identify bottlenecks and suggest where a process could improve.

It helps reveal where people drop out of a process instead of relying on overall totals. It can also compare different groups, such as users on different devices or from different locations.

funnel-analysis — Skill by nicepkg

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/nicepkg/ai-workflow/funnel-analysis

Any agent

npx skills add nicepkg/ai-workflow --skill funnel-analysis

Clone the repo

git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 637 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00053	$0.00637
Opus 5	$0.00026	$0.00318
Sonnet 5	$0.00011	$0.00127
Haiku 4.5	$0.00005	$0.00064

Measured 2d ago against content hash 040b43ce54d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

funnel-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (examples/basic_funnel.py, examples/segmented_funnel.py, scripts/funnel_analyzer.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

workflows/marketing-pro-workflow/.claude/skills/funnel-analysis/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Funnel Analysis Skill

Analyze user behavior through multi-step conversion funnels to identify bottlenecks and optimization opportunities in marketing campaigns, user journeys, and business processes.

Quick Start

This skill helps you:

Build conversion funnels from multi-step user data
Calculate conversion rates between each step
Perform segmentation analysis by different user attributes
Create interactive visualizations with Plotly
Generate business insights and optimization recommendations

When to Use

Marketing campaign analysis (promotion → purchase)
User onboarding flow analysis
Website conversion funnel optimization
App user journey analysis
Sales pipeline analysis
Lead nurturing process analysis

Key Requirements

Install required packages:

pip install pandas plotly matplotlib numpy seaborn

Core Workflow

1. Data Preparation

Your data should include:

User journey steps (clicks, page views, actions)
User identifiers (customer_id, user_id, etc.)
Timestamps or step indicators
Optional: user attributes for segmentation (gender, device, location)

2. Analysis Process

Load and merge user journey data
Define funnel steps and calculate metrics
Perform segmentations (by device, gender, etc.)
Create visualizations
Generate insights and recommendations

3. Output Deliverables

Funnel visualization charts
Conversion rate tables
Segmented analysis reports
Optimization recommendations

Example Usage Scenarios

E-commerce Purchase Funnel

# Steps: Promotion → Search → Product View → Add to Cart → Purchase
# Analyze by device type and customer segment

User Registration Funnel

# Steps: Landing Page → Sign Up → Email Verification → Profile Complete
# Identify where users drop off most

Content Consumption Funnel

# Steps: Article View → Comment → Share → Subscribe
# Measure engagement conversion rates

Common Analysis Patterns

Read the full file on GitHub · 99 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 99 lines · 53 tokens per session scan A 040b43ce54d3

Subscribe to this mod's changes

funnel-analysis is a skill published in the GitHub repository nicepkg/ai-workflow (283 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 637 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Productivity agent agent-skills ai anthropic claude claude-code

funnel-analysis