Skip to content
SkillModel-led287 tokens in use

Ad Attribution Audit

Cross-platform attribution audit that inventories every conversion source and refuses to add numbers from incompatible reporting windows.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-attribution
/plugin marketplace add agricidaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Ad Attribution Audit costs

89tokens idle
287tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure15/25
  • Examples3/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

The attribution skill reviews how conversions are defined and counted across ad platforms, GA4, mobile measurement partners, server events and offline data. It lists every source with its identity, counting and deduplication rules, then reconciles comparable events and explains the gaps.

A comparability gate blocks totals until sources share the same event, window, scope and model. Until then it reports the values side by side with their definitions.

What You Get

  • An inventory of attribution sources with identity, counting and deduplication rules
  • Reconciliation notes that explain differences from view-through rules, consent, modeled data and conversion lag
  • Side-by-side reporting where totals are not valid
  • A measurement improvement plan in the common JSON contract

Common Use Cases

  • Explaining why Meta and Google report different conversion counts
  • Reviewing GA4 attribution against platform numbers
  • Checking an MMP setup with AppsFlyer, Adjust, Branch or Singular
  • Responding to a request to total conversions across platforms

What Makes It Unique

It has a written comparability gate. Aggregation is rejected until sources share the conversion event, value definition, window, click and view scope, counting method, deduplication identity, timezone, currency, model and modeled-data treatment. Its worked example refuses to add Meta seven-day and Google thirty-day conversions.

Under The Hood

This is a prompt-only skill with no scripts. It tells the agent to read the main ads contract and the normalized account snapshots, then compare the exports, analytics data and API results you provide. It does not treat any one platform as ground truth and does not recommend an attribution model without your decision context. It sends findings to the conductor in JSON and makes no account changes.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers