attribution

Files (4)

• SKILL.md
• framework-notes.md · references/
• check-output.py · scripts/
• output-template.md · templates/

SKILL.md (first lines)

# Attribution

## Overview

Attribution answers the existential marketing question: which of our activities actually produce revenue? The core principle is that single-touch attribution lies. First-touch attribution over-credits awareness channels. Last-touch attribution over-credits bottom-of-funnel conversion channels. Both lead to systematically bad investment decisions — over-funding channels that appear in the credited position and starving channels that create the conditions for conversion.

The non-obvious rule: the "best" attribution model depends on your GTM motion. Product-led growth companies should weight product-qualified signals higher. Sales-led companies should weight sales engagement higher. Channel-led companies should weight partner influence. There is no universal attribution model — only the model that matches how your customers actually buy.

This skill produces: a Multi-Touch Attribution Model Report comparing 4-6 attribution models on revenue credit allocation, channel ROI calculations with cost and revenue attribution, a UTM governance framework with taxonomy and enforcement rules, a source-of-truth reporting structure, and optimization recommendations for budget reallocation.

## When to Use

- User says "attribution" or "attribution model" → activate this skill
- User asks "which channel generates the most revenue" → use this skill
- User says "marketing ROI" or "campaign ROI" → attribution is required
- User mentions "UTM tracking" or "UTM hygiene" or "UTM parameters" → use UTM governance module
- User asks "how do I measure multi-touch attribution" → implement a model
- User says "source of truth reporting" or "marketing and sales disagree on numbers" → use this skill
- Trigger phrases: attribution modeling, multi-touch, first-touch, last-touch, channel attribution, campaign ROI, marketing ROI, UTM parameters, tracking governance

Do NOT use for:
- Campaign-level analytics (open rates, reply rates, meeting rates) → use campaign-analytics
- Pipeline management and forecasting → use pipeline-management
- A/B testing methodology → use a-b-testing
- CRM data architecture → use crm-integration
- Real-time channel monitoring and alerting → use proactive-alerts

## Authoritative Foundations

This skill draws from the following established methodologies:

- **Bizible (Marketo/Marketo Measure) — Multi-Touch Attribution** — The most widely deployed B2B multi-touch attribution system. Bizible's model maps every marketing and sales touch across the customer journey, weighting touches based on position (FT, LC, even, U-shaped, W-shaped, custom). Acquired by Adobe/Marketo, it's the enterprise standard.

- **Full Circle Insights (Salesforce-native)** — Attribution built inside the CRM rather than appended to it. The implicit criticism of marketing-platform-first attribution is that it misses sales touches. Full Circle captures both marketing and sales activity within the CRM.

- **Google Analytics — Attribution Models** — The most accessible attribution implementation, now with data-driven attribution as the default in GA4. Google's shift from rules-based to machine-learning-based attribution reflects the industry trend toward algorithmic models.

- **DreamData — B2B Attribution** — Account-based attribution for companies where multiple stakeholders influence a deal. Critical distinction: person-level attribution credits the individual who converted; account-level attribution distributes credit across the buying group.

## Prerequisites

- CRM data with opportunity records including: create date, close date, deal amount, primary campaign source (HubSpot, Salesforce, or Attio)
- Marketing platform data with touch history: email opens, clicks, form fills, content downloads, webinar attendance, ad clicks (Marketo, HubSpot, Pardot, or GA4)
- Sales activity data: calls, emails, meetings logged on opportunities (CRM activity history)
- UTM-tagged URLs across all marketing channels (website, ads, email, social, partner)
- Cost data by channel: total spend per channel per period for ROI calculation
- Recommended: 12+ months of touchpoint data for stable attribution modeling
- Recommended upstream skills: crm-integration (for CRM data architecture), campaign-analytics (for campaign-level metrics)

## Step-by-Step Process

### Phase 1: Intake

Gather required information from the user. Ask all questions at once. Do not proceed until all answers are received.

Required intake questions:

1. **GTM motion**: What is your primary GTM motion? (Product-led growth, sales-led, channel/partner-led, marketing-led, hybrid?)
2. **Average sales cycle**: How long from first touch to closed-won? (30 days, 90 days, 180 days, 12+ months?) This determines the lookback window.
3. **Buying group size**: How many people typically influence a purchase? (Single decision-maker, 3-5 person committee, 6+ enterprise buying group?) Determines person-level vs account-level attribution.
4. **Channel mix**: What channels are active? (Outbound email, inbound/content, paid ads, events, partners, referrals, social, direct, product-led?)
5. **Data sources**: Where are touchpoints tracked? (CRM, marketing automation, product analytics, ad platforms, webinar platform?)
6. **Current attribution**: What attribution model, if any, is currently in use? What metrics does marketing currently report? What does sales report?
7. **UTM status**: Are UTMs consistently applied? Is there a UTM taxonomy documented? Who enforces it?
8. **Budget data**: Can you provide spend data by channel for the analysis period?

### Phase 2: UTM Governance and Hygiene Audit

UTM parameters are the foundation of attribution accuracy. Bad UTMs = bad attribution.

1. **UTM taxonomy design** — enforce the standard 5 parameters:
   - `utm_source`: The platform/site sending traffic (google, linkedin, hubspot, marketo, outreach). Must be a controlled value from an approved list.
   - `utm_medium`: The marketing medium (cpc, organic_social, email, display, referral, partner, event). Must be a controlled value.
   - `utm_campaign`: The specific campaign name. Use a consistent naming convention: `[quarter]-[channel]-[audience]-[offer]-[variant]`. Example: `q1-2024-email-enterprise-compliance-toolkit-v2`.
   - `utm_content`: What was clicked (cta-text, banner-blue, subject-line-test-a). Used for A/B testing within campaigns.
   - `utm_term`: Search keywords (only for paid search). Optional.

2. **UTM hygiene audit** — scan all URLs for common errors:
   - Missing `utm_source` (most common error — without it, traffic is "direct")
   - Inconsistent source naming: "linkedin," "LinkedIn," "linkedin.com," "LinkedIn Ads" are 4 different sources.
   - Using `utm_medium=cpc` for non-paid traffic
   - Spaces in UTM values (should use hyphens or underscores, never spaces)
   - Case sensitivity: UTM values are case-sensitive. "Google" ≠ "google."
   - Campaign parameter used as catch-all (same utm_campaign across multiple channels)
   - Missing utm_campaign (leaves traffic unassigned to any campaign for ROI calculation)
   - URL shorteners stripping UTM parameters (bit.ly, ow.ly strip by default — configure to preserve)
   - Internal links tagged with UTM parameters (overwrites real attribution data)

3. **UTM governance rules** — document and enforce:
   - All outbound links from marketing must have at minimum: utm_source, utm_medium, utm_campaign.
   - Source values must come from pre-approved list (requires request to add new source).
   - Medium values must come from 10 standard categories.
   - Campaign naming convention is mandatory and validated at URL creation.
   - Marketing automation platforms must auto-append UTMs (configure at the platform level).
   - Sales-provided links should use a different tracking parameter (or UTM with sales-specific source) to distinguish sales vs marketing influence.

4. **UTM data quality score** — calculate for the analysis period:
   - % of revenue-attributed opportunities with complete UTM data: target >90%
   - % of website sessions with utm_source: target >80%
   - % of campaign spend assigned to specific campaigns via UTM: target >95%
   - If scores are below targets, attribution modeling will be unreliable. Fix UTM hygiene first.

### Phase 3: Touchpoint Data Assembly

Build the unified touchpoint timeline:

1. **Define the touchpoint taxonomy** — categorize every interaction:
   - **Marketing touches**: Email click, content download, webinar attendance, ad click, website visit, form fill, social engagement, event booth visit.
   - **Sales touches**: Sales email, sales call, meeting held, demo delivered, proposal sent, LinkedIn connection/inmail.
   - **Product touches**: Signup, activation event, invite team member, upgrade feature usage, PQL trigger.
   - **Partner touches**: Partner referral, co-marketing event, marketplace listing click.

2. **Build touchpoint timelines** for each opportunity:
   - For every closed-won and closed-lost opportunity, assemble all touchpoints from first interaction to close date.
   - Each touchpoint records: timestamp, channel, touch type, campaign association, and whether it was marketing or sales initiated.
   - For account-level attribution: roll up all contacts under the account and create a merged timeline.

3. **Define the attribution window (lookback period)**:
   - Standard: 90 days for SMB (shorter sales cycles), 180 days for mid-market, 365 days for enterprise.
   - Custom window: if your average sales cycle is 120 days, use 120-day lookback.

From LeadMagic/gtm-skills, MIT.

More from LeadMagic/gtm-skills