Ads Budget
Review cross-platform ad spend, bidding fit, and kill/scale lists using 70/20/10 and ROAS/CPA guardrails.
Overview
ads-budget is an agent skill for the Grow phase that evaluates cross-platform ad spend, bidding strategies, and kill/scale readiness using 70/20/10 and validated performance gates.
Install
npx skills add https://github.com/agricidaniel/claude-ads --skill ads-budgetWhat is this skill?
- 70/20/10 budget split across proven, scaling, and test channels
- 3x Kill Rule and 20% scaling rule for pause vs scale decisions
- Requires ≥14 days of spend data before kill/scale evaluation
- Kill candidates need ≥20 clicks or ≥$100 spend before pause recommendations
- Pulls frameworks from budget-allocation, bidding-strategies, benchmarks, and scoring references
- 70/20/10 rule for proven, scaling, and test channel spend
- 3x Kill Rule and 20% scaling rule in recommendations
- Requires ≥14 days spend data; kill candidates need ≥20 clicks or ≥$100 spend
Adoption & trust: 814 installs on skills.sh; 5.8k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your ad budget is spread across platforms without a clear rule for what to kill, what to scale, or how bidding should match funnel stage.
Who is it for?
Solo marketers with two weeks or more of multi-platform spend who want structured ROAS/CPA decisions before increasing budget.
Skip if: Brand-new accounts with almost no spend history, or organic-only growth with zero paid campaigns to analyze.
When should I use this skill?
User mentions budget allocation, bidding strategy, ad spend, ROAS target, media budget, or scaling across active ad platforms.
What do I get? / Deliverables
You get allocation recommendations, bidding strategy fit, and explicit kill and scale lists backed by minimum data thresholds.
- Budget allocation assessment against 70/20/10
- Bidding strategy recommendations with kill list and scale list
- Health-oriented scoring notes tied to benchmark references
Recommended Skills
Journey fit
How it compares
Use as a budget-and-bidding reviewer inside the claude-ads reference stack, not as a creative generator or landing-page builder.
Common Questions / FAQ
Who is ads-budget for?
Indie builders and solo founders actively spending on paid ads who need allocation, bidding, and kill/scale lists grounded in reference frameworks.
When should I use ads-budget?
Use it in Grow when reviewing monthly media budget, ROAS targets, bidding strategy changes, or decisions to pause underperformers and scale winners.
Is ads-budget safe to install?
It reads campaign references and performance summaries you provide; check the Security Audits panel on this Prism page and avoid pasting live API secrets into prompts.
SKILL.md
READMESKILL.md - Ads Budget
<!-- Updated: 2026-04-13 | v1.5 --> # Budget Allocation & Bidding Strategy ## Process 1. Collect budget and performance data across all active platforms 2. Read `ads/references/budget-allocation.md` for allocation framework 3. Read `ads/references/bidding-strategies.md` for strategy decision trees 4. Read `ads/references/benchmarks.md` for CPC/CPA benchmarks 5. Read `ads/references/scoring-system.md` for health score algorithm 6. **Validate**: confirm spend data covers ≥14 days before evaluating kill/scale decisions 7. Evaluate budget allocation, bidding strategy, and scaling readiness 8. **Validate**: verify kill list candidates have sufficient data (≥20 clicks or ≥$100 spend) before recommending pause 9. Generate recommendations with kill list and scale list ## Budget Allocation Framework ### 70/20/10 Rule - **70%** on proven channels (consistent ROAS/CPA targets met) - **20%** on scaling channels (showing promise, need more data) - **10%** on testing channels (new platforms, audiences, creatives) ### Platform Selection Matrix | Business Type | Primary | Secondary | Testing | |---------------|---------|-----------|---------| | SaaS B2B | Google Search, LinkedIn | Meta, YouTube | TikTok, Microsoft | | E-commerce | Google Shopping, Meta | TikTok, YouTube | Microsoft, LinkedIn | | Local Service | Google Search, Google LSA | Meta | Microsoft, YouTube | | B2B Enterprise | LinkedIn, Google Search | Meta | Microsoft, TikTok | | Info Products | Meta, YouTube | Google Search | TikTok | | Mobile App | Meta, Google UAC | TikTok | Apple Ads | | Real Estate | Google Search, Meta | YouTube | Microsoft | | Healthcare | Google Search | Meta | Microsoft, YouTube | | Finance | Google Search, Meta | LinkedIn | Microsoft | | Agency (clients) | Varies by client | N/A | N/A | ### Budget Sufficiency Rules | Platform | Minimum Daily | Learning Phase Budget | |----------|--------------|----------------------| | Google Search | $20/day | Sufficient for 15+ conv/month | | Google PMax | $50/day | Sufficient for algorithm optimization | | Meta | $20/day per ad set | ≥5x target CPA per ad set | | LinkedIn | $50/day Sponsored Content | 15+ conversions/month | | TikTok | $50/day campaign, $20/day ad group | ≥50x target CPA per ad group | | Microsoft | No strict minimum | Sufficient for stable delivery | ## Bidding Strategy Evaluation ### Google Ads Bidding Decision Tree ``` Start ├─ <30 conversions/month? │ └─ Use Maximize Clicks (cap CPC at benchmark) │ └─ When >30 conv/month → Maximize Conversions ├─ 30-50 conversions/month? │ └─ Use Maximize Conversions │ └─ When stable CPA → Target CPA ├─ >50 conversions/month? │ └─ Use Target CPA │ └─ When revenue tracking → Target ROAS └─ Revenue tracking active + >50 conv/month? └─ Use Target ROAS ``` ### Meta Ads Bidding - **Lowest Cost (default)**: best for volume, may have CPA variance - **Cost Cap**: sets CPA ceiling, may reduce volume - **Bid Cap**: maximum bid per auction, most control - **ROAS Goal**: target return on ad spend - **CBO vs ABO**: CBO for proven campaigns, ABO for testing ### LinkedIn Bidding - **Cost Per Send (CPS)**: for Message Ads - **Manual CPC**: recommended starting point for cost control - **Cost Cap**: efficiency at scale with predictable CPA - **Maximum Delivery**: highest volume, most expensive. Use only for scale with established data - **Target Cost**: for predictable CPA ### TikTok Bidding - **Lowest Cost**: maximize conversions within budget (volume) - **Cost Cap**: set maximum CPA