PluginBench
Skill
Pass
Audit score 90

ads-attribution

agricidaniel/claude-ads

Audit cross-platform ad attribution, conversion definitions, and reporting windows to reconcile GA4, MMPs, and platform discrepancies.

What is ads-attribution?

Systematically inventories attribution sources (browser, server, platform, analytics, MMP, offline) and reconciles comparable events to identify measurement gaps and quality issues. Use this when you need to validate conversion counts across Meta, Google, AppsFlyer, Adjust, Branch, Singular, or other platforms, or when reporting windows and definitions don't align.

  • Inventory all attribution sources with their identity, counting, deduplication, and privacy rules
  • Reconcile comparable events and explain differences caused by eligibility, consent, modeled data, conversion lag, or scope
  • Separate measurement quality from platform-reported performance
  • Identify incompatible reporting windows, conversion definitions, and attribution models
  • Detect cross-platform discrepancies and missing evidence
  • Generate a measurement improvement plan through a normalized JSON contract

How to install ads-attribution

npx skills add https://github.com/agricidaniel/claude-ads --skill ads-attribution
Claude Code
Cursor
Windsurf
Cline

How to use ads-attribution

  1. 1.Read the main ads contract and normalized account snapshots for your platforms
  2. 2.Declare the business conversion definition, value, data window, timezone, currency, and decision context
  3. 3.Inventory every attribution source (browser, server, platform, analytics, MMP, offline, app) with its rules
  4. 4.Reconcile comparable events and document differences by cause (eligibility, consent, modeled data, lag, thresholds, scope)
  5. 5.Report findings, contradictions, confidence gaps, and missing evidence through the JSON contract
  6. 6.Do not assume one platform is ground truth or add incompatible reports together until normalized

Use cases

Good for
  • Reconcile Meta seven-day and Google thirty-day conversion windows to find true comparable totals
  • Audit why AppsFlyer, Adjust, and Branch report different conversion counts for the same app install
  • Validate offline conversion uploads against platform-reported online conversions
  • Investigate GA4 attribution model differences when platform performance claims don't match measured events
  • Review AdServices and AdAttributionKit privacy-preserving attribution against traditional MMP data
Who it's for
  • Performance marketing managers and attribution analysts
  • Paid media strategists reconciling platform reports
  • Analytics engineers auditing conversion pipelines
  • Marketing operations teams validating data quality across platforms

ads-attribution FAQ

Can I add Meta and Google conversion totals together?

Only if they share the same conversion event definition, attribution window, click/view scope, counting method, deduplication identity, timezone, currency, and attribution model. If Meta uses seven-day and Google uses thirty-day windows, reconcile the windows first and report values side by side until comparable.

What should I do if platforms report different conversion counts for the same event?

Inventory each source's eligibility rules, view-through rules, consent requirements, modeled data treatment, conversion lag, and thresholds. Reconcile these differences to explain the gap; do not assume one platform is ground truth.

How do I handle offline conversions in attribution audits?

Include offline sources in your inventory with their identity, counting, and deduplication rules. Reconcile offline events against online platform data using the same conversion definition and window to identify measurement gaps.

What is the comparability gate?

A requirement that sources must share the same conversion definition, attribution window, counting method, and other parameters before aggregating. Until then, report values side by side with their definitions instead of computing a total.

Should I recommend an attribution model without context?

No. Do not recommend an attribution model without understanding the operator's decision context and business goals. Report findings and let the operator decide based on their strategy.

Full instructions (SKILL.md)

Source of truth, from agricidaniel/claude-ads.


name: ads-attribution description: "Audit cross-platform attribution, conversion definitions, reporting windows, GA4, AdServices and AdAttributionKit, MMPs, browser and server events, offline conversions, and platform reconciliation. Use for attribution audit, attribution models, conversion windows, requests to add or total Meta and Google conversions, incompatible reporting-window aggregation, GA4 attribution, MMP review, AppsFlyer, Adjust, Branch, Singular, or cross-platform discrepancies."

Attribution Audit

  1. Read the main ads contract and normalized account snapshots.
  2. Declare the business conversion, value, data window, timezone, currency, and decision the attribution analysis must support.
  3. Inventory every browser, server, platform, analytics, MMP, offline, and app attribution source with its identity, counting, deduplication, and privacy rules.
  4. Reconcile comparable events and explain differences caused by eligibility, view-through rules, consent, modeled data, conversion lag, thresholds, or scope.
  5. Separate measurement quality from platform-reported performance.
  6. Return findings, contradictions, confidence, missing evidence, and a measurement improvement plan through the common JSON contract.

Do not assume one platform is ground truth, add incompatible reports together, or recommend an attribution model without the operator's decision context.

Comparability gate

Reject aggregation until the sources share, or are explicitly normalized to, the same conversion event and value definition, attribution window, click/view scope, counting method, deduplication identity, timezone, currency, attribution model, and modeled-data treatment. Until then, report the values side by side with their definitions; do not compute a total.

Example: Meta seven-day conversions and Google thirty-day conversions are incompatible. Refuse to add them, reconcile windows and definitions first, and only aggregate a newly comparable dataset.