Google ads workflow
Skill itallstartedwithaidea/MiniAgent/skills/google-ads-workflow
The Cowork Agent for Everything — trainable advertising AI + 14 platform MCP servers + agent skills. Based on minimind (42k stars). Train from zero in 2 hours.
npx -y skills add itallstartedwithaidea/MiniAgent --skill google-ads-workflowAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use for complete, end-to-end advertising workflows that span multiple skills — full account audits with action plans, campaign launches with verification, optimization cycles, or any multi-step advertising process. Trigger when the task requires analysis AND changes AND verification, or when the user wants a complete workflow rather than a single answer.
SKILL.md
3.2 KB, as published. Nobody here has run it
Google Ads Workflow — Skill Composition
This meta-skill chains MiniAgent's specialized skills into complete workflows.
REQUIRED BACKGROUND
You MUST understand all 5 core skills before using this skill:
google-ads-analysis— data analysis and GAQLgoogle-ads-audit— systematic 7-dimension evaluationgoogle-ads-write— safe write operations (CEP protocol)google-ads-math— PPC calculationsgoogle-ads-mcp— API connectivity
Workflow 1: Complete Account Audit
Step 1: [google-ads-analysis] Pull account-level metrics
Step 2: [google-ads-audit] Run 7-dimension audit framework
Step 3: [google-ads-math] Calculate opportunity cost of issues found
Step 4: OUTPUT → docs/miniagent/audits/YYYY-MM-DD-<account>-audit.md
Step 5: OUTPUT → docs/miniagent/plans/YYYY-MM-DD-<account>-optimization.md
Workflow 2: Campaign Optimization Cycle
Step 1: [google-ads-analysis] Identify underperforming campaigns
Step 2: [google-ads-analysis] Pull search terms for wasted spend
Step 3: [google-ads-math] Calculate impact of proposed changes
Step 4: [google-ads-write] CEP: Add negative keywords
Step 5: [google-ads-write] CEP: Adjust budgets
Step 6: [google-ads-analysis] Postcheck — verify changes
Step 7: OUTPUT → optimization summary with before/after metrics
Workflow 3: New Campaign Launch Checklist
Step 1: [google-ads-math] Calculate target CPA/ROAS from business goals
Step 2: [google-ads-analysis] Competitive landscape via auction insights
Step 3: CHECKLIST:
□ Campaign structure defined (brand/non-brand/competitor)
□ Keyword lists built with proper match types
□ Negative keyword lists created (universal + industry-specific)
□ Ad copy written (3 headlines, 2 descriptions minimum)
□ Extensions configured (sitelinks, callouts, structured snippets)
□ Conversion tracking verified
□ Budget set with daily/monthly caps
□ Bid strategy selected with rationale
□ Geographic targeting configured
□ Device adjustments set
Step 4: [google-ads-write] CEP: Implement campaign
Step 5: [google-ads-analysis] Day-1 verification check
Workflow 4: Weekly Reporting
Step 1: [google-ads-analysis] Pull last 7 days vs prior 7 days
Step 2: [google-ads-math] Calculate WoW changes for all key metrics
Step 3: [google-ads-analysis] Identify top 3 wins and top 3 concerns
Step 4: OUTPUT → formatted report with:
- Executive summary (3 sentences)
- Key metrics table (WoW comparison)
- Top performers
- Attention items
- Recommended actions for next week
Context Isolation Rule
When chaining skills, each step should pass only the RELEVANT context to the next step. Do not carry the entire conversation history into write operations — pass only the specific campaign/ad group/keyword context needed for that change.
Gives 0 of the 12 instructions most automation workflows skills give
Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-06
- write conventional commit messagesin 36 of 745, across 35 files
- delete branches after mergein 30 of 745, across 21 files
- make atomic commitsin 25 of 745, across 15 files
- write minimal code to pass testsin 22 of 745, across 10 files
- run tests before committingin 21 of 745, across 13 files
- re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
- use try-catch for error handlingin 20 of 745, across 6 files
- write tests before implementationin 20 of 745, across 8 files
- configure branch protection rulesin 19 of 745, across 5 files
- explain the why in commit messagesin 19 of 745, across 9 files
- refactor code while tests remain greenin 19 of 745, across 6 files
- Interact with elements using refsin 19 of 745, across 11 files
Said here and by no other author read
- understand all core skills before use
- pull account-level metrics for audits
- run the seven-dimension audit framework
- calculate the opportunity cost of issues
- identify underperforming campaigns for optimization
- verify changes using a postcheck
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.