# Funnel audit Human Guide

## What This Is For
Analyze the complete customer acquisition and conversion funnel to identify where prospects drop off, why they disengage, and what changes will have the highest impact on overall. It gives the agent a clearer input/output frame for funnel audit: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Funnel audit agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for funnel audit.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Funnel audit guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- **Funnel stages**: The stages to analyze (or use standard: Awareness > Interest > Consideration > Intent > Purchase > Retention)
- **Funnel data**: Metrics per stage (traffic, leads, MQLs, SQLs, opportunities, customers) or qualitative description
- **Traffic sources**: Where visitors/leads originate
- **Conversion points**: Key actions at each stage (form fill, demo request, trial start, purchase)
- **Known pain points**: Any stages the user already suspects are underperforming
- **Tech stack**: CRM, analytics, and marketing automation tools in use
- Map the current funnel with conversion rates between each stage
- Benchmark stage-to-stage conversion rates against industry averages
- Identify the biggest drop-off points and calculate revenue impact of each gap
- Analyze potential causes per bottleneck: messaging, targeting, UX, timing, offer, follow-up
- Evaluate lead quality signals — are the right people entering the funnel?
- Assess nurture effectiveness at each stage

## Decision Points And Nuance
The original skill emphasizes: Purpose, Input Required, Process, Output, Agents Used, Supporting file: skills/context-engine/compliance-rules.md, Section 1: Geographic Privacy Laws, 1.1 EU/EEA — General Data Protection Regulation (GDPR), 1.1b EU/EEA — AI Act Article 50 (Generative AI Disclosure), 1.1b.i — Article 50 draft implementing guidelines (May 2026).

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- The user must provide (or will be prompted for):
- | **Penalty Range** | Up to EUR 20 million or 4% of global annual turnover, whichever is higher. Supervisory authorities may also issue warnings, bans on processing, and orders to erase data. |
- **Treat the carve-out as conditional, not a free pass.** "Human-reviewed" requires named accountability. Don't claim editorial responsibility unless a named editor is willing to be on the record.
- | **Consent Model** | Opt-out. No prior consent required to send commercial email. Recipients must be given a clear way to opt out, and opt-out requests must be honored within 10 business days. |
- | **Consent Model** | Opt-out for sale/sharing of personal information. Opt-in required for consumers under 16 (under 13 requires parental consent). "Sharing" includes cross-context behavioral advertising. |
- | **Consent Model** | Opt-in. Consent must be free, informed, and unambiguous for a specific purpose. Legitimate interest is available as an alternative basis but requires a Legitimate Interest Assessment (LIA). |
- | **Penalty Range** | Up to 2% of revenue in Brazil, capped at BRL 50 million (~USD 10 million) per violation. ANPD may also issue warnings, publicize violations, and block or delete data. |
- | **Email Rules** | Specified Electronic Mail Act: opt-in required for commercial email. Sender ID and unsubscribe required. APPI requires specifying the purpose of use at collection. |

## Copy-And-Paste Prompt
```text
Use the Funnel audit human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the indranilbanerjee/digital-marketing-pro skill entry for `funnel-audit`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# /digital-marketing-pro:funnel-audit

## Purpose

Analyze the complete customer acquisition and conversion funnel to identify where prospects drop off, why they disengage, and what changes will have the highest impact on overall conversion rate.

## Input Required

The user must provide (or will be prompted for):

- **Funnel stages**: The stages to analyze (or use standard: Awareness > Interest > Consideration > Intent > Purchase > Retention)
- **Funnel data**: Metrics per stage (traffic, leads, MQLs, SQLs, opportunities, customers) or qualitative description
- **Traffic sources**: Where visitors/leads originate
- **Conversion points**: Key actions at each stage (form fill, demo request, trial start, purchase)
- **Known pain points**: Any stages the user already suspects are underperforming
- **Tech stack**: CRM, analytics, and marketing automation tools in use

## Process

1. **Load brand context**: Read `~/.claude-marketing/brands/_active-brand.json` for the active slug, then load `~/.claude-marketing/brands/{slug}/profile.json`. Apply brand voice, compliance rules for target markets (`skills/context-engine/compliance-rules.md`), and industry context. **Also check for guidelines** at `~/.claude-marketing/brands/{slug}/guidelines/_manifest.json` — if present, load restrictions and relevant category files. Check for custom templates at `~/.claude-marketing/brands/{slug}/templates/`. Check for agency SOPs at `~/.claude-marketing/sops/`. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.
2. Map the current funnel with conversion rates between each stage
3. Benchmark stage-to-stage conversion rates against industry averages
4. Identify the biggest drop-off points and calculate revenue impact of each gap
5. Analyze potential causes per bottleneck: messaging, targeting, UX, timing, offer, follow-up
6. Evaluate lead quality signals — are the right people entering the funnel?
7. Assess nurture effectiveness at each stage
8. Model improvement scenarios: "If stage X improves by Y%, overall revenue increases by Z%"
9. Prioritize recommendations by revenue impact and implementation effort
10. **Size and validate the fix**: For the top recommendation, size the validating experiment with `python "${CLAUDE_PLUGIN_ROOT}/scripts/sample-size-calculator.py" --baseline-rate {stage-rate} --mde {mde} --mde-type absolute --significance 0.95 --power 0.80` (pass `--mde-type relative` if the target is a relative lift — the two differ by ~40× at a 5% baseline). Once the fix has run, confirm the improvement is statistically real with `python "${CLAUDE_PLUGIN_ROOT}/scripts/significance-tester.py" --control-visitors {n} --control-conversions {n} --variant-visitors {n} --variant-conversions {n} --confidence 0.95` rather than declaring a winner off raw rate deltas.

## Output

A structured funnel audit containing:

- Funnel visualization with conversion rates per stage
- Industry benchmark comparison per stage
- Top 3 bottlenecks ranked by revenue impact
- Root cause analysis per bottleneck with supporting evidence
- Improvement scenarios with projected revenue impact
- Prioritized action plan with quick wins and strategic projects
- Measurement framework to track improvements

## Agents Used

- **marketing-strategist** — Funnel architecture, lead quality analysis, strategic recommendations
- **analytics-analyst** — Conversion data analysis, benchmarking, impact modeling
- **cro-specialist** — Conversion bottleneck diagnosis, A/B test recommendations, form and checkout optimization, statistical significance testing

---

## Supporting file: skills/context-engine/compliance-rules.md

# Compliance Rules Reference

This file is the canonical compliance ruleset for the Digital Marketing Pro plugin. All marketing modules MUST check outputs against these rules before delivery. Rules are structured for programmatic consumption by the context engine.

---

## Section 1: Geographic Privacy Laws

### 1.1 EU/EEA — General Data Protection Regulation (GDPR)

| Field | Detail |
|---|---|
| **Region** | European Union / European Economic Area (27 EU member states + Iceland, Liechtenstein, Norway) |
| **Law** | General Data Protection Regulation (GDPR) |
| **Year Enacted** | 2016 (enforced May 25, 2018) |
| **Consent Model** | Opt-in. Explicit, informed, freely given, specific, and unambiguous consent required before processing personal data. Consent must be as easy to withdraw as to give. Legitimate interest may apply in narrow B2B contexts but requires a documented balancing test. |
| **Email Rules** | Prior opt-in required for all marketing emails. Soft opt-in exception: existing customers may be emailed about similar products/services if given an easy opt-out at collection and in every message. Every email must include sender identity, physical address, and a functional unsubscribe mechanism honored within 30 days. |
| **Cookie/Tracking Rules** | Prior consent required for all non-essential cookies and trackers (ePrivacy Directive). Cookie banners must allow granular choice (accept/reject by category). Pre-ticked boxes are invalid. Analytics cookies require consent unless strictly necessary. Server-side tracking of personal data still requires a lawful basis. |
| **Penalty Range** | Up to EUR 20 million or 4% of global annual turnover, whichever is higher. Supervisory authorities may also issue warnings, bans on processing, and orders to erase data. |
| **Key Marketing Impact** | Double opt-in is industry standard. All lead forms need clear consent checkboxes (not bundled). Data Processing Agreements required with every martech vendor. Privacy policy must disclose all data recipients. Cross-border data transfers require adequacy decisions, SCCs, or BCRs. Right to erasure means suppression lists must be maintained. Profiling for ad targeting requires explicit consent or legitimate interest with opt-out. |

### 1.1b EU/EEA — AI Act Article 50 (Generative AI Disclosure)

| Field | Detail |
|---|---|
| **Region** | European Union / European Economic Area |
| **Law** | Regulation (EU) 2024/1689 — Artificial Intelligence Act, Article 50 (Transparency obligations for providers and deployers of certain AI systems) |
| **Applicable** | **2 August 2026** (transparency obligations); general-purpose AI obligations applied 2 Aug 2025; high-risk system obligations 2 Aug 2027 |