attribution has two halves. Interpretation helps judge which numbers to trust: platform claims, model comparisons, MMM, incrementality and holdout tests, and self-reported attribution for podcasts and dark social.
The build half helps you own your attribution: anonymous ids merged to a known person with identify, first-touch capture, and stitching conversions that finish on a third-party domain through metadata passthrough and webhooks.
What You Get
- A written answer that names the source of truth and what each source says
- A model comparison for long sales cycles
- A confidence and gaps section that shows where the data is weak
- A first-party design using identify and merge with guardrails
- A plan for writing source, confidence and basis onto CRM records
Common Use Cases
- Judging whether a channel really works when its dashboard over-claims
- Planning an incrementality or holdout test
- Crediting podcasts and dark social with self-reported attribution
- Stitching a booking made on a third-party scheduling page back to the visitor
What Makes It Unique
It pairs interpretation with a build track and sets guardrails for the build: only the anonymous id is passed to third-party links, and referrers such as checkout and login pages are excluded from first-touch data. References cover attribution models, business types, first-party tracking and measurement paradigms.
Under The Hood
The SKILL.md and four references are loaded as context. The skill ships no scripts and runs nothing itself. Its build guidance describes code you would add to your own site and webhook handler, using tools such as PostHog, GA4 or Segment; those need your own accounts.