Suganthan-Mohanadasan

Multi Signal Keyword Attribution — Development skill for Claude Code

Development community

Free, open BigQuery skill for the (not provided) gap.

How to install Multi Signal Keyword Attribution

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Suganthan-Mohanadasan/Multi-signal-keyword-attribution and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Multi Signal Keyword Attribution does

Free, open BigQuery skill for the (not provided) gap. Estimates which GSC queries drive GA4 conversions and revenue using a 3-signal join, intent weighting, and per-row confidence.

Alternatives in Development

  • Third-party Notices — THE FOLLOWING SETS FORTH ATTRIBUTION NOTICES FOR THIRD PARTY SOFTWARE THAT MAY BE CONTAINED IN PORTIONS OF THI 94.7k ★
  • Attribution — Bundled Skill Attribution 213 ★
  • Notebooklm — Query and manage Google NotebookLM notebooks with persistent auth, batch/multi queries, source sync, and struc 159 ★

README

Multi-Signal Keyword Attribution

A free, open skill for the "(not provided)" gap in Google Analytics. It estimates which of your visible Search Console queries are driving GA4 conversions and revenue, joining the two inside BigQuery with 3-signal narrowing, intent weighting, and a confidence score on every row.

**Full guide with setup walkthrough:** [suganthan.com/blog/not-provided-keywords-google-analytics/](https://suganthan.com/blog/not-provided-keywords-google-analytics/)

What it does

For each Google Search Console query that brought clicks to your site, this skill tells you how many GA4 sessions, conversions, and revenue that specific query is responsible for, and how confident you should be in the answer.

The methodology:

  1. Joins GSC and GA4 on 3 signals: normalised landing page, date, device.
  2. Distributes GA4 metrics within each (page, date, device) bucket by weighted click share.
  3. Weights by search intent: branded (3.0x), transactional (2.0x), commercial (1.5x), navigational (1.0x), informational (0.5x).
  4. Renormalises per page so the sum of attributed metrics matches GA4's actual page total.
  5. Scores confidence per row based on candidate count and click volume.

Example output

You get a sortable table of every query, the page it landed on, its intent, and the GA4 sessions, conversions, and revenue attributed to it, each with a confidence rating. Here is a condensed sample (synthetic SaaS site, 28-day window, numbers illustrative):

Query Page Intent Clicks Att. Conv Att. Revenue Confidence
projectflow pricing /pricing branded 168 28.4 $6,820 HIGH
projectflow / branded 412 41.6 $9,985 LOW
best project management software /comparison commercial 218 7.2 $1,180 MEDIUM
buy project management software /pricing transactional 45 5.1 $640 HIGH
what is a kanban board /blog/kanban-explained informational 412