google-ads-write
Skill38 starsChanged 8 months agoApache-2.0View on GitHub
Safe Google Ads write operations using the Confirm-Execute-Postcheck (CEP) protocol. Activate when the user wants to pause campaigns, change bids, update budgets, add keywords, create ads, or make any modification to their Google Ads account. Every mutation requires explicit user confirmation before execution.
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 19
Before any write operation, present exactly what will change:
- Distinctive: line 36
Only after the user explicitly confirms (says "confirm", "yes", "go ahead", "do it", "approved"):
- Distinctive: line 43
Verify the change took effect by querying the updated entity
- Distinctive: line 124
After any write operation, note:
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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 Write Operations
You manage write operations to Google Ads accounts. Every mutation follows the CEP protocol — no exceptions.
CEP Protocol (Confirm → Execute → Post-check)
Step 1: Confirm
Before any write operation, present exactly what will change:
## Proposed Change
**Action**: [what will happen]
**Account**: [customer ID]
**Target**: [campaign/ad group/keyword name and ID]
**Before**: [current state]
**After**: [new state]
**Risk Level**: [Low/Medium/High]
Type CONFIRM to proceed.Step 2: Execute
Only after the user explicitly confirms (says "confirm", "yes", "go ahead", "do it", "approved"):
- Execute the mutation via the Google Ads API
- Log the operation with timestamp, action, parameters, and pre-state snapshot
Step 3: Post-check
After execution:
- Verify the change took effect by querying the updated entity
- Report the result with before/after comparison
- Note any follow-up actions needed
Supported Write Operations
Campaign Status
Action: update_campaign_status
Params: campaign_id, status (ENABLED | PAUSED)
Risk: Medium — affects all ads in the campaignBudget Update
Action: update_budget
Params: budget_id, amount_micros (new daily budget in micros)
Risk: Medium — affects daily spend rate
Always show: current budget, new budget, monthly estimate (daily × 30.4)Keyword Bid
Action: update_ad_group_bid / update_keyword_bid
Params: ad_group_id or criterion_id, cpc_bid_micros
Risk: Low-Medium — affects auction position
Always show: current bid, new bid, estimated position impactNegative Keywords
Action: create_negative_keyword
Params: campaign_id, keyword text, match_type (BROAD | PHRASE | EXACT)
Risk: Low — blocks unwanted traffic
Batch: up to 50 keywords per call
Always show: list of keywords being added, match type, affected campaignCreate RSA (Responsive Search Ad)
Action: create_ad
Params: ad_group_id, headlines (3-15, max 30 chars each),
descriptions (2-4, max 90 chars each), final_url
Risk: Low — new ads are created PAUSED for review
Validation: check character limits before submitting
Always show: headline/description preview with character countsCreate Campaign
Action: create_campaign
Params: name, channel_type, daily_budget, bidding_strategy, network_settings
Risk: High — creates new spend capacity
Always create PAUSED so user can review before enablingApply Recommendation
Action: apply_recommendation (from Google's optimization suggestions)
Risk: Varies — always show what the recommendation will changeSafety Rules
- Never skip confirmation — even if the user says "just do it all"
- Never combine destructive operations — pause and delete are separate confirmations
- Always show before/after — the user must see what will change
- Create ads PAUSED — never create an ad in ENABLED state
- Batch limit — max 50 operations per batch, with itemized preview
- No raw GAQL mutations — use structured mutation operations only
- Log everything — every write operation is recorded for audit trail
Rollback Awareness
After any write operation, note:
- What was changed
- What the previous state was
- How to reverse it (e.g., "To undo: pause campaign X again" or "To undo: set bid back to $2.50")
In this repository4 other files it gives its agents.
- google-ads-analysisSkill
- google-ads-auditSkill
- google-ads-mathSkill
- google-ads-mcpSkill
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.

