Growth funnel analysis
Skill duandigi/duandigi-growth-marketing-skill/skills/growth-funnel-analysis
Evidence-first AI Agent Skills for growth marketing — multi-channel analytics (SEO, paid media, social, local search, CRM), secure account integration, AI evaluation, experimentation & approval-safe optimization for Claude Code.
npx -y skills add duandigi/duandigi-growth-marketing-skill --skill growth-funnel-analysisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use this skill when mapping, diagnosing, or comparing a growth funnel across acquisition, activation, retention, referral, and revenue, including service-business lead funnels and product-led onboarding funnels.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.8 KB, 459 tokens by cl100k_base, as published. Nobody here has run it
Growth Funnel Analysis
Purpose
Find the highest-leverage bottleneck in a customer journey using evidence rather than channel assumptions.
Inputs
- Stage definitions and event names
- Counts or conversion rates by stage
- Time window and segment definitions
- Known tracking gaps and business constraints
If critical input is unavailable, label it unknown and create a research or instrumentation task. Do not invent values.
Workflow
- Normalize the funnel so each stage has one clear entry condition and one clear success condition.
- Check denominator consistency, duplicate users or leads, attribution windows, and missing events.
- Calculate stage-to-stage and end-to-end conversion where data permits.
- Segment by channel, landing page, device, geography, customer type, or cohort only when sample size is useful.
- Identify the constraint with the largest combination of volume, value, and controllability.
- Separate measurement failure from actual customer-behavior failure.
- Return one primary bottleneck, secondary bottlenecks, and recommended next evidence.
Required output
Return a concise, decision-oriented response containing:
- Funnel table
- Primary bottleneck
- Evidence and confidence
- Segment differences
- Tracking gaps
- Recommended next analyses
Label important statements as confirmed, inferred, assumed, or unknown when the distinction affects the decision.
Guardrails
Do not:
-
Optimizing the stage with the lowest rate without considering volume or value
-
Comparing incompatible time windows
-
Treating correlation as causation
-
Claim guaranteed growth or present an estimate as observed fact.
-
Recommend spam, fake reviews, impersonation, deceptive urgency, dark patterns, policy evasion, or unauthorized production changes.
-
Hide material uncertainty, tracking limitations, or possible harm.
When an action can spend money, publish content, contact people, change production systems, delete data, or alter access, produce a plan and request explicit authorization rather than executing automatically.
Completion check
Before finishing, verify that the output:
- answers a specific growth decision;
- uses the supplied business context;
- separates evidence from assumptions;
- defines a measurable next step;
- includes risks, constraints, and missing data;
- is no longer than necessary for the decision.