Individual skill
non-serving-keyword-scanner
Scans your accounts for enabled Search keywords with zero impressions over a window (default 180 days) and writes one review tab to a Google Sheet — every row then gets a Pause/Keep/Investigate verdict per rules.md. Report-only, never pauses. Auto-invoke when user says 'scan non-serving keywords', 'find dead keywords', 'keyword cleanup report', or 'non-serving keyword scan'.
non-serving-keyword-scanner/SKILL.md
Source commit 90f0e419f2d820789d5e50eee1237ab9fd14dfc6
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 80
- Repository last updated
- Aug 25, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-agents Repository topic
- ai-skills Repository topic
- claude-code Repository topic
- google-ads Repository topic
- google-ads-api Repository topic
- ppc Repository topic
- ppc-automation Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
README.mddoc · 5,317 bytesSKILL.mdcore · 8,147 bytesSKILL.mdcore · 8,147 bytesSKILL.mdcore · 8,147 bytesaccounts.example.mddoc · 731 bytesdiagrams/README.mddoc · 584 bytesdiagrams/run-logic.mmdasset · 1,249 bytesdiagrams/run-logic.svgasset · 211,380 bytesdiagrams/theme.jsonasset · 1,400 bytesdiagrams/workflow-hero.mmdasset · 960 bytesdiagrams/workflow-hero.svgasset · 30,072 bytesexamples.mddoc · 4,415 bytesreferences/scan-contract.mddoc · 6,524 bytesrules.mddoc · 8,352 bytesscripts/non_serving_keyword_scan.pyruns · 16,047 bytes
Read excerpt
# Non-Serving Keyword Scanner
Finds the keywords nobody knows exist: enabled, eligible, and silent — zero
impressions across the whole scan window. Across a large portfolio these
accumulate into hundreds of rows of clutter and false coverage ("we're
covering that term" — except it never serves). One run scans every account
you point it at and produces a single review tab.
One operator owns the workflow end to end: run the scan → triage the tab
(`rules.md` — clusters before rows) → give every row a Pause / Keep /
Investigate verdict → route what needs routing. The scanner itself never
pauses anything; it is a hygiene instrument, not a savings instrument —
every flagged keyword spent $0.00 by definition.
