skills-ws/skills/paid-ads/references/budget-allocation-frameworks.md

87 agent skills for AI coding assistants — marketing, growth, web3, dev, design & operations. Built for OpenClaw, Claude Code, Cursor, and Codex.

## Contents

- Budget Allocation Frameworks
- The 70/20/10 Rule
- Channel Budget Split by Funnel Stage
- Monthly Budget Minimums (to gather signal)

## Budget Allocation Frameworks

### The 70/20/10 Rule

- **70%** → Proven channels and campaigns with positive ROAS
- **20%** → Scaling what's working — new audiences, expanded geo, new ad formats
- **10%** → Experiments — new channels, creative concepts, audience tests

### Channel Budget Split by Funnel Stage

```
AWARENESS (20-30% of budget)
├── YouTube / Meta Video / Display
├── Goal: Impressions, reach, video views
└── KPI: CPM, VTR, brand lift

CONSIDERATION (30-40% of budget)
├── Meta engagement, Google Display remarketing, LinkedIn
├── Goal: Clicks, engagement, lead gen
└── KPI: CPC, CTR, CPL

CONVERSION (30-50% of budget)
├── Google Search, Shopping, Meta conversion campaigns
├── Goal: Purchases, signups, demos
└── KPI: CPA, ROAS, conversion rate
```

### Monthly Budget Minimums (to gather signal)

These are **rules of thumb (as of Jun 2026)**, not platform mandates — the real floor is *enough conversions to exit learning*. Derive it: `min monthly spend ≈ target_CPA × 50 conversions` per ad set/campaign (Meta needs ~50 optimization events/ad set/week; Google smart bidding wants ~30+ conv/30 days). High-CPA verticals need far more than the table.

| Channel | Minimum Monthly | Recommended |
|---------|----------------|-------------|
| Google Search | $1,500 | $3,000-$10,000 |
| Meta Ads | $1,000 | $3,000-$15,000 |
| LinkedIn Ads | $3,000 | $5,000-$15,000 |
| X (Twitter) Ads | $1,000 | $2,000-$5,000 |

Below these thresholds you won't gather enough data for meaningful optimization.

---