pre-launch-check
Skill4 starsChanged 31 days agoMITView on GitHub
Check one Google Ads campaign before it goes live and return a pass/fix table. Use when the user asks "is this campaign ready to launch?", "check the new Demand Gen before I enable it", "can I turn this on?", or right after a campaign was built PAUSED.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- egenil/sitelemetry-claude-plugintheir own version, first seen Sep 28, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- egenil/sitelemetry-claude-plugin★ 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 repository13 other files it gives its agents.
- ads-auditSkill
- campaign-architectSkill
- consent-auditSkill
- demand-gen-launchSkill
- event-auditSkill
- gtm-buildSkill
- monthly-reportSkill
- performance-insightsSkill
- search-launchSkill
- setupSkill
- tracking-auditSkill
- tracking-planSkill
- weekly-checkSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Check one paused campaign against everything that commonly wastes the first weeks of spend.
- Very specific: line 23
Call account_profile (currency, writes).
- Very specific: line 30
Channels: Search: campaign.network_settings.target_search_network and target_content_network (partners and Display expansion usually off …
- Very specific: line 60
If every row passes: "Ready to launch." Then offer to enable it with ads_set_status (level campaign, status ENABLED): call it without …
- Distinctive: line 65
Never enable a campaign with a failed check unless the user explicitly accepts that specific risk.
- Very specific: line 66
Never apply ads_set_status without first showing the preview and getting a yes.
- Very specific: line 67
If the profile is read-only (no write tools), tell the user to run npx google-marketing-agent accounts set <alias> writes true and restart …
≈ “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
Pre-launch check
Check one paused campaign against everything that commonly wastes the first weeks of spend. Offer to launch only when everything passes.
When to use
A campaign exists (usually PAUSED, as every campaign created by this package is) and the user wants to enable it.
Inputs
account: profile alias.- The campaign: ID or name. If only a name is given, find the ID with
get_campaign_performanceorrun_gaql_query(SELECT campaign.id, campaign.name, campaign.status FROM campaign WHERE campaign.name LIKE '%<name>%').
Steps
Call account_profile (currency, writes). Then run each check with run_gaql_query unless another tool is named.
- Goal.
SELECT campaign_conversion_goal.category, campaign_conversion_goal.origin, campaign_conversion_goal.biddable FROM campaign_conversion_goal WHERE campaign.id = <id>andSELECT conversion_goal_campaign_config.goal_config_level, conversion_goal_campaign_config.custom_conversion_goal FROM conversion_goal_campaign_config WHERE campaign.id = <id>. Pass when it bids on the conversion the user cares about and that action is recording (guide("measurement")). - Bidding and budget.
SELECT campaign.bidding_strategy_type, campaign.target_cpa.target_cpa_micros, campaign.maximize_conversions.target_cpa_micros, campaign_budget.amount_micros FROM campaign WHERE campaign.id = <id>. Flag a target CPA far below what the account has achieved, or a daily budget below one target CPA. - Channels. Search:
campaign.network_settings.target_search_networkandtarget_content_network(partners and Display expansion usually off for lead-gen). Demand Gen: channel controls perguide("demand-gen"). - Locations and languages.
campaign.geo_target_type_setting.positive_geo_target_typemust bePRESENCE. Location and language criteria (negative = truerows are exclusions, not targets):SELECT campaign_criterion.type, campaign_criterion.negative, campaign_criterion.location.geo_target_constant, campaign_criterion.language.language_constant FROM campaign_criterion WHERE campaign.id = <id> AND campaign_criterion.type IN ('LOCATION', 'LANGUAGE'). Demand Gen keeps them on the ad group:SELECT ad_group.name, ad_group_criterion.type, ad_group_criterion.negative, ad_group_criterion.location.geo_target_constant, ad_group_criterion.language.language_constant FROM ad_group_criterion WHERE campaign.id = <id> AND ad_group_criterion.type IN ('LOCATION', 'LANGUAGE'). - Audience (Demand Gen).
SELECT ad_group.name, ad_group_criterion.type, ad_group_criterion.audience.audience, ad_group_criterion.user_list.user_list FROM ad_group_criterion WHERE campaign.id = <id> AND ad_group_criterion.type IN ('AUDIENCE', 'USER_LIST', 'CUSTOM_AUDIENCE'). An ad group with no audience signal is a blocker when the campaign targets business buyers, a warning otherwise (it relies on optimized targeting alone). - Ads and assets.
SELECT ad_group.name, ad_group_ad.ad.type, ad_group_ad.ad_strength, ad_group_ad.policy_summary.approval_status, ad_group_ad.policy_summary.review_status, ad_group_ad.policy_summary.policy_topic_entries, ad_group_ad.ad.final_urls FROM ad_group_ad WHERE campaign.id = <id>and assets at campaign and account level (campaign_asset.field_type,customer_asset.field_type). Search: ad strength Good or better, sitelinks and callouts present. Demand Gen: the image formats inguide("demand-gen"). - Policy and review.
DISAPPROVEDis a fail andAPPROVED_LIMITEDa warning; explain thepolicy_topic_entrieswithguide("policy"). Ads still under review (review_statusnotREVIEWED) are a warning: they may not serve on day one. - Final URLs. List the distinct final URLs and ask the user to confirm they load and match the ad.
Output
# Pre-launch: <campaign name> (<id>)
| Check | Result | Fix |
|---|---|---|
| Goal | ✓ / ✗ | ... |
...If every row passes: "Ready to launch." Then offer to enable it with ads_set_status (level campaign, status
ENABLED): call it without confirm to show the preview, and apply only after the user says yes.
Never
- Never enable a campaign with a failed check unless the user explicitly accepts that specific risk.
- Never apply
ads_set_statuswithout first showing the preview and getting a yes. - If the profile is read-only (no write tools), tell the user to run
npx google-marketing-agent accounts set <alias> writes trueand restart their MCP client. Never edit config files.
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.

