Attribution deep dive

Skill metrikia-io/metrikia-claude-plugin/skills/attribution-deep-dive

Deep analysis of multi-touch attribution - customer journeys, channel contribution, and conversion path optimizationFrom its SKILL.md

Install

npx -y skills add metrikia-io/metrikia-claude-plugin --skill attribution-deep-dive

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 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.

SKILL.md

2.5 KB, as published. Nobody here has run it

Attribution Deep Dive

Analyze multi-touch attribution to understand the true value of each marketing channel.

Process

Get recent conversions
- Call list_leads with status "converted" to find recent conversions
- Call list_deals with status "won" for revenue data
Journey analysis
- For 5-10 converted leads, call get_attribution_journey to map full journeys
- Identify common patterns: first touch channels, assist channels, closing channels
Channel contribution
- Call get_budget_advice for attribution-enriched insights
- Compare last-touch vs multi-touch attribution to find undervalued channels
Ask Diana
- Call ask_diana: "Based on multi-touch attribution, which channels are undervalued by last-click and deserve more budget?"

Output Format

Journey Patterns

Common conversion paths (e.g., "Facebook Ad -> Google Search -> Direct -> Conversion")

Channel Contribution

Table: Channel | First Touch % | Assist % | Last Touch % | True Value (MTA)

Undervalued Channels

Channels that get little last-click credit but contribute heavily to assists

Optimization Opportunities

Specific actions to improve the conversion path

Process Flow

digraph attribution_deep_dive {
    rankdir=TB;
    "Fetch converted leads" -> "Fetch won deals";
    "Fetch won deals" -> "Map 5-10 journeys";
    "Map 5-10 journeys" -> "Identify patterns";
    "Identify patterns" -> "Get budget advice (MTA)";
    "Get budget advice (MTA)" -> "Ask Diana undervalued channels";
    "Ask Diana undervalued channels" -> "Compile attribution report";
}

Red Flags

Channel shows 0% last-touch but >15% assist -> severely undervalued, investigate
Average journey >7 touchpoints -> long consideration cycle, adjust attribution window
Single-touch conversions dominating -> either tracking gap or very direct funnel
Large gap between platform-reported and MTA conversions -> deduplication needed

Error Handling

If MCP server returns connection error -> Check that the plugin is still authorized in Metrikia Settings (sign in again if needed)
If "tenant not found" -> the session may have the wrong scope authorized. Need mcp:read minimum
If rate limited (429) -> Wait 60 seconds, reduce batch sizes
If empty results -> Verify date range and check if data sources are synced via get_sync_status