google-ads-guardrails
Skill15 starsChanged 38 days agoMITView on GitHub
Guardrails for Google Ads recommendations and mutations. Hard rules on what NOT to recommend, prohibited phrasing, data-quality requirements. Used internally for any Google Ads optimization or change recommendation.
In this repository61 other files it gives its agents.
- access-and-permissionsSkill
- accounts-and-connectionsSkill
- ad-brief-generatorSkill
- affiliate-marketingSkill
- analyse-creativeSkill
- automate-with-agentsSkill
- brief-creativeSkill
- build-reportsSkill
- clean-wasted-spendSkill
- competitor-ad-intelligenceSkill
- creative-psychology-hooksSkill
- creative-researchSkill
- diagnose-performanceSkill
- email-marketingSkill
- ga4-source-of-truthSkill
- get-startedSkill
- gomarble-skills-creative-strategistsSkill
- gomarble-skills-ecommerce-brandsSkill
- gomarble-skills-google-ads-auditSkill
- gomarble-skills-meta-ads-auditSkill
- gomarble-skills-saas-companiesSkill
- google-ads-create-master-skillSkill
- google-ads-depth-of-analysisSkill
- google-ads-keywordplannerSkill
- google-ads-pmax-evaluationSkill
- google-ads-pmax-scalingSkill
- google-ads-search-analysisSkill
- google-ads-search-executionSkill
- google-ads-shoppingSkill
- google-ads-tool-fundamentalsSkill
- google-impression-shareSkill
- google-pmax-pulseSkill
- google-search-auditSkill
- google-search-term-auditSkill
- launch-campaignsSkill
- linkedin-adsSkill
- manage-campaignsSkill
- meta-ads-auditSkill
- meta-agent-operationsSkill
- meta-create-master-skillSkill
- meta-creative-analysisSkill
- meta-creative-fatigue-detectionSkill
- meta-creative-strategySkill
- meta-custom-event-interpretationSkill
- meta-daily-optimizationSkill
- meta-depth-of-analysisSkill
- meta-guardrailsSkill
- meta-performance-analysisSkill
- meta-tool-fundamentalsSkill
- microsoft-adsSkill
- organic-socialSkill
- own-creative-diagnosisSkill
- research-competitorsSkill
- search-console-master-skillSkill
- shift-budgetSkill
- shopify-order-disciplineSkill
- tiktok-adsSkill
- tiktok-create-master-skillSkill
- winning-ads-engineSkill
- winning-ads-orchestratorSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 11 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
If a recommendation does not map to one of these controls, it is not actionable.
- Distinctive: line 40
Ecommerce: Use ROAS, conversion value, cost per purchase.
- Distinctive: line 41
Lead gen: Use CPA, cost per lead. Never use ROAS unless offline revenue is imported.
- Distinctive: line 42
Unclear: ASK the user. Do not assume.
- Distinctive: line 47
Never scale if: CPA > target, ROAS < target, or query/search term hygiene not done
- Distinctive: line 48
Never scale based on: Impression Share alone, CPC alone, or early data (< 7 days)
- Distinctive: line 53
Do not stack changes (budget + bids + structure simultaneously)
- Distinctive: line 54
Do not judge performance on: < 30 conversions (Search), < 50 conversions (PMax/Shopping)
- Distinctive: line 55
Avoid changes that reset learning unless absolutely required
- Very specific: line 69
Before any scale/pause/restructure suggestion, check:
- Distinctive: line 70
Search term quality (Q4/Q5 presence)
- Distinctive: line 77
If diagnostics are incomplete → say insufficient data, do not recommend.
≈ “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
Google Ads Guardrails
READ BEFORE GENERATING ANY RECOMMENDATION.
Budget Reallocation Prohibition
You CANNOT allocate, shift, increase, reduce, or "optimize" budget for: keywords, search terms, match types, devices (unless bid adjustments in Search), locations (unless bid adjustments or exclusions), audiences (unless bid modifiers), asset groups (PMax has no asset-group budgets).
Before writing ANY recommendation, ask: Does this imply moving money between keywords, queries, products, devices, audiences, or asset groups? If YES → rewrite using valid controls below.
Valid Budget Controls
| Campaign Type | Valid Controls |
| Search / Shopping | Campaign daily budget, bid strategy targets (tCPA/tROAS/max CPC), pause/enable campaigns or ad groups |
| Performance Max | Campaign daily budget, bid strategy targets (tCPA/tROAS), pause asset groups or campaign |
If a recommendation does not map to one of these controls, it is not actionable.
Mandatory Rewrites
❌ "Shift budget from keyword A to keyword B" ✅ "Pause keyword A. Increase campaign daily budget by 10–20% to allow keyword B more eligible demand."
❌ "Allocate more to [breakdown: placement/device/demographic/product/asset group]" ✅ "Create a new campaign targeting [dimension] with its own budget, OR use bid adjustments/exclusions."
Rule: Any recommendation implying budget movement between sub-campaign entities must be rewritten to use campaign budget, bid targets, pause/enable, or structural separation.
Metric Selection
First infer conversion type:
- Ecommerce: Use ROAS, conversion value, cost per purchase. Never use CPA alone for revenue decisions.
- Lead gen: Use CPA, cost per lead. Never use ROAS unless offline revenue is imported.
- Unclear: ASK the user. Do not assume.
Scaling Limits
- Max budget increase: 20% at a time
- Never scale if: CPA > target, ROAS < target, or query/search term hygiene not done
- Never scale based on: Impression Share alone, CPC alone, or early data (< 7 days)
- Frame scaling as: "Incremental test with downside risk"
Learning & Stability
- Do not stack changes (budget + bids + structure simultaneously)
- Do not judge performance on: < 30 conversions (Search), < 50 conversions (PMax/Shopping)
- Avoid changes that reset learning unless absolutely required
Immediate STOP Triggers
Halt any recommendation that attempts:
- "Scale keywords / products / asset groups"
- "Reallocate spend between queries"
- "Optimize placements in PMax"
- "Increase bids and budget at the same time"
- "Scale > 20% in one step"
- "Fix low IS by increasing budget blindly"
Required Diagnostics Before Any Action
Before any scale/pause/restructure suggestion, check:
- Search term quality (Q4/Q5 presence)
- CPA/ROAS vs target
- IS Lost (Rank vs Budget breakdown)
- CPC trend direction
- Conversion volume sufficiency
- Bidding strategy compatibility
If diagnostics are incomplete → say insufficient data, do not recommend.
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.

