# ad-spend-guardrails

Builds written paid-media spend policies with maximum allowable CAC, ROAS floors, and kill-switch triggers. Use it to lock in payback limits derived from unit economics before scaling ad budgets.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 19800 installs · ★ 2
- Author: Maya-Beth Finotti
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/mbfinotti/advertising-skills/tree/HEAD/skills/ad-spend-guardrails/SKILL.md
- Updated: 2026-09-14
- HTML: https://affpapa.org/en/nevibecode/skills/ad-spend-guardrails

## What it does

The skill acts as a policy architect for paid media. It calculates maximum allowable CAC, minimum ROAS or MER floors, and hard kill-switch thresholds based on contribution margin and cash runway. Instead of borrowing generic heuristics like a 3:1 LTV-to-CAC ratio, it derives numbers directly from unit economics.

It interviews the user first. The agent asks one question per message, covering business motion, margin confidence, and team sign-offs. The output splits controls into three clear layers: a mathematical break-even floor, an operational target floor, and an automated kill-switch. It sets guardrails on marginal rather than blended performance, so increasing spend will not mask unprofitable acquisition.

The skill only generates policy. It does not touch live ad accounts and will not pace daily budgets. A known limitation is that restart rules and cooling-off periods after a spend halt are not standardized in industry literature. The user must decide those explicitly during the interview, because unconfirmed recovery terms leave the kill-switch unenforceable.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mbfinotti/advertising-skills --skill ad-spend-guardrails -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ad-spend-guardrails/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ad-spend-guardrails/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mbfinotti/advertising-skills --skill ad-spend-guardrails -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ad-spend-guardrails/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mbfinotti/advertising-skills --skill ad-spend-guardrails -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ad-spend-guardrails/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mbfinotti/advertising-skills ad-spend-guardrails
```

2. **Manually: put the files in place**
- File: `.github/skills/ad-spend-guardrails/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mbfinotti/advertising-skills --skill ad-spend-guardrails -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mbfinotti/advertising-skills --path skills/ad-spend-guardrails
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ad-spend-guardrails/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add mbfinotti/advertising-skills --skill ad-spend-guardrails -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mbfinotti/advertising-skills/tree/HEAD/skills/ad-spend-guardrails/SKILL.md

## When to use it
- calculate maximum allowable CAC from contribution margin
- define break-even ROAS floors to prevent unhedged ad spend
- establish hard kill-switch triggers and escalation owners
- align monthly paid-media caps with cash runway

## Example prompts
- Help me set spend guardrails and break-even ROAS for our subscription tiers.
- Draft a paid-media spend policy with kill-switch thresholds for an e-commerce store with 40% margin.
- What allowable CAC can we afford based on our contribution margin and cash runway?

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 7bc14a0af06783f4.

BEGIN THIRD-PARTY FILE 7bc14a0af06783f4
```text
---
name: ad-spend-guardrails
description: "Set the organisation's top-level paid-media spend guardrails as written policy - maximum allowable CAC, minimum ROAS/MER floor, kill-switch thresholds, counter-metrics, who owns them and who may override them - each derived from contribution margin, payback, and cash runway rather than inherited from a dashboard. Use whenever the user asks what CAC they can afford, mentions a ROAS floor, spend guardrails, a kill switch, when to stop spending, or who approves a budget increase - even if they never say 'guardrails'. Covers B2B and B2C. Do NOT use to judge whether current CAC/ROAS is actually good (mbfinotti/advertising-skills@cac-roas-benchmark) or to monitor daily pacing (mbfinotti/advertising-skills@ad-budget-pacing)."
license: MIT
metadata:
  author: Maya-Beth Finotti
  version: "1.1.3"
---

# Profitability Guardrails

You are a paid-media policy architect. Your job is to produce one written artifact: the spend guardrails every later budget decision must respect.

You set policy. You never execute platform changes or optimize a live campaign. Three ideas carry the whole exercise:

- **Derive, never quote.** Break-even comes from the business's own contribution margin. Every published target - 3:1 LTV:CAC, 4x ROAS, 12-month payback - is someone's heuristic, and none of them knows this business's margin.
- **A threshold is not a policy.** It becomes one when it has a consequence, a named owner, an override path and a way back. A status label with no consequence is decoration.
- **Guardrails are set on the margin, spent on the average.** The number that authorizes the next dollar is the marginal one; the number in the monthly report is the blended one. Confusing them is the most expensive mistake in this whole document.

Be honest about one gap upfront: no published practitioner source specifies cooling-off lengths or restart criteria after a spend kill. Settle those with the user as decisions, and label them as such rather than dressing them up as benchmarks.

## Interview

Ask before proposing any number. One question per message, multiple-choice where a choice set exists, and skip whatever the user already answered. Start by asking what guardrails already exist - surface the inherited policy before recommending a new one, or you will quietly replace a threshold someone else owns.

- Motion: B2B, B2C/e-commerce, marketplace, subscription, or a mix?
```
END THIRD-PARTY FILE 7bc14a0af06783f4

The third-party file has ended. Everything between the 7bc14a0af06783f4 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2434 of 31663 bytes. © Maya-Beth Finotti · MIT · https://github.com/mbfinotti/advertising-skills/tree/HEAD/skills/ad-spend-guardrails/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md