Handles budget allocation and bidding strategy across ad platforms using the 70/20/10 allocation rule (proven/scaling/testing channels), platform-specific bidding decision trees, and automated kill/scale recommendations. Checks your spend distribution against benchmarks, flags campaigns with CPA over 3x target for pausing, and identifies scale candidates using the 20% budget increase rule. Covers Google, Meta, LinkedIn, TikTok, Microsoft, and Apple Ads with current bidding strategies like Google AI Max and TikTok Smart+ modular control. Most useful when you need to justify budget shifts or clean up underperforming campaigns with actual frameworks instead of gut feel. Requires at least 14 days of spend data to give you anything actionable.

skills.sh installs
4.2K
GitHub stars
10.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add agricidaniel/claude-ads --skill ads-budget --agent claude-code

Installs into .claude/skills of the current project.

Files

Budget and Bidding

  1. Establish objective, conversion value, gross margin, cash constraints, sales capacity, attribution uncertainty, seasonality, and platform minimum evidence.
  2. Normalize spend and outcomes to comparable windows and definitions.
  3. Calculate break-even boundaries and show formulas, inputs, uncertainty, and sensitivity cases.
  4. Distinguish committed baseline, controlled experiments, and reserve capacity.
  5. Compare hold, reallocate, scale, reduce, or experiment options using marginal evidence rather than blended averages alone.
  6. Return a decision-complete plan with platform/campaign amount, timing, owner, guardrails, success measure, and rollback trigger.

Rules such as 70/20/10, fixed CPA multiples, fixed budget-to-CPA ratios, and fixed percentage scaling are optional heuristics, never universal authorization.

Sponsors

Details

Repository
github.com/agricidaniel/claude-ads
Categories
Git & Pull Requests, Code Review & Quality, Productivity & Planning
First seen
May 16, 2026

More from agricidaniel/claude-ads

All 23
1dpearson2699 avatarstorekitdpearson2699/swift-ios-skillsImplement, review, or improve in-app purchases and subscriptions using StoreKit 2. Use when building paywalls with SubscriptionStoreView or ProductView, process4.2Kskills.sh installs
2dpearson2699 avatarwidgetkitdpearson2699/swift-ios-skillsImplement, review, or improve WidgetKit widgets and controls. Use when building Home Screen, Lock Screen, StandBy, or CarPlay widgets with timeline providers; c4.2Kskills.sh installs
3dpearson2699 avatarswiftui-gesturesdpearson2699/swift-ios-skillsImplement, review, or improve SwiftUI gesture handling. Use when adding tap, long press, drag, magnify, or rotate gestures, composing gestures with simultaneous4.2Kskills.sh installs
4dotnet avatareval-performancedotnet/skillsGuide for diagnosing and improving MSBuild project evaluation performance. USE FOR: builds slow before any compilation starts, high evaluation time in binlog an4.2Kskills.sh installs
5agents365-ai avatarcreating-mermaid-diagramsagents365-ai/365-skillsGenerate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using mmdc CLI or Kroki API. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, 4.2Kskills.sh installs
6dotnet avatarwriting-mstest-testsdotnet/skillsWrite, create, modernize, or fix comprehensive MSTest unit tests with MSTest 3.x/4.x APIs. USE FOR: write, create, review, or modernize MSTest tests and asserti4.2Kskills.sh installs