negative-keyword-builder
Skill2 starsChanged 4 months agoMITView on GitHub
Turn confirmed bad-fit searches into a safe, approval-ready negative keyword draft with match types, scope, and collision checks. Use after search-term review, before excluding traffic.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- riz1k9/claude-ad-skillstheir own version, first seen Aug 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- riz1k9/claude-ad-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
After the Search Term Miner has produced confirmed exclude candidates.
- Distinctive: line 15
Use a connected Google Ads MCP for read-only context, or paste the candidates, current negatives, positive keywords, campaign purposes, and …
- Distinctive: line 39
Never invent a negative that is not supported by the supplied business exclusions or source queries.
- Distinctive: line 40
Do not use a one-word account-wide negative when a phrase, exact query, campaign scope, or ad-group scope is safer.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Negative Keyword Builder
Doctrine
A negative keyword can save spend or quietly remove good demand. Draft from confirmed bad-fit queries, choose the narrowest useful scope, and test the proposed negative against protected searches and positive keywords. Exact, phrase, and broad negatives behave differently from positive keywords and do not cover every close variant.
When to use
- After the Search Term Miner has produced confirmed exclude candidates.
- Use a connected Google Ads MCP for read-only context, or paste the candidates, current negatives, positive keywords, campaign purposes, and protected queries.
- Bring separate Brand, Careers, Support, or content campaign purposes so a useful query is not blocked account-wide.
Run it
Build a READ-ONLY negative keyword draft. Use live account data for context if connected; otherwise use what I paste. Do not add anything to Google Ads.
1. Confirm the exclude candidates, source queries, campaign and ad group, current negative lists, positive keywords, campaign purpose, and protected brand or high-intent queries.
2. For every proposed negative show: negative text, negative match type, scope, source queries, reason, collision test, protected queries, risk, and "approval required".
3. Use the narrowest scope that solves the problem. Keep Brand, Careers, Support, and intentional free or educational campaigns protected from acquisition-campaign negatives.
4. Apply Google negative-match mechanics correctly:
- negative broad blocks when all negative terms appear, in any order;
- negative phrase blocks when the full phrase appears in the same order;
- negative exact blocks only that exact query;
- negatives do not automatically cover every close variant, so show necessary singular, plural, or synonym checks.
5. Test each draft against current positive keywords and at least 5 plausible good queries. If a useful query would be blocked, narrow the text, match type, or scope.
6. Put ambiguous candidates in a hold list instead of forcing a negative.
Return an upload-ready table, but make no changes. End with "Approval required for every row. No changes were made."Guardrails
- Never invent a negative that is not supported by the supplied business exclusions or source queries.
- Do not use a one-word account-wide negative when a phrase, exact query, campaign scope, or ad-group scope is safer.
- Exact negative
payroll templatedoes not blockfree payroll spreadsheet template. Check the actual mechanics before calling a row covered. - Words such as "free", "cheap", "login", "jobs", and "how to" can be useful in the right campaign. Protect intentional demand.
- Draft only. Adding a negative is a reach-reducing account change and still requires explicit row-level approval.
Good output looks like
A small, upload-ready negative list whose scope and match type can be explained, with the good queries it protects and every row waiting for approval.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

