# performance-memo

Pulls ad spend from every platform and ties it to revenue, refunds and churn by campaign ID. Each line ends with a call: keep, kill, change or test.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 111
- Author: Cogny AI
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cognyai/claude-code-marketing-skills/tree/HEAD/skills/performance-memo/SKILL.md
- Updated: 2026-10-12
- HTML: https://affpapa.org/en/nevibecode/skills/performance-memo

## What it does

The skill writes a short Monday memo in an analyst's voice: what was spent, what each campaign returned, and where cheap customers leave after a couple of months. Every line closes with a decision — keep, kill, change or test. It runs on a Monday morning schedule.

Data comes through Cogny's MCP gateway: ad platforms, CRM, Stripe, analytics. With campaign IDs in the ledger the join is exact. Without them the skill falls back to fibbler channel attribution, then to platform-reported conversions and GA4 by `sessionSourceMedium`, tagging each line with a confidence level. fibbler needs two paid channels, otherwise it refuses or returns zeros.

Nothing runs without Cogny: you need an account and connected ad platforms plus a CRM or Stripe. A line counts as conclusive only at 10 or more conversions over 14 days or longer; below that the skill marks it as weak.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add cognyai/claude-code-marketing-skills --skill performance-memo -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add cognyai/claude-code-marketing-skills --skill performance-memo -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add cognyai/claude-code-marketing-skills --skill performance-memo -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install cognyai/claude-code-marketing-skills performance-memo
```

2. **Manually: put the files in place**
- File: `.github/skills/performance-memo/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add cognyai/claude-code-marketing-skills --skill performance-memo -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/cognyai/claude-code-marketing-skills --path skills/performance-memo
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add cognyai/claude-code-marketing-skills --skill performance-memo -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/cognyai/claude-code-marketing-skills/tree/HEAD/skills/performance-memo/SKILL.md

## When to use it
- combine ad spend from every platform into one view
- spot campaigns that bring cheap customers who churn
- tie platform conversions to revenue and refunds by campaign ID
- get a decision per campaign instead of raw metrics
- catch a mismatch between platform conversions and GA4

## Example prompts
- Write the memo for last week and compare it with the week before
- Run the month report with comparison and show what's closing
- Check which campaigns bring customers who leave after two months

## Similar
- [ad-account-diagnostic](https://affpapa.org/en/nevibecode/skills/ad-account-diagnostic.md) — skill · 20600 installs
- [paid-measurement-loop](https://affpapa.org/en/nevibecode/skills/paid-measurement-loop.md) — skill · 1000 installs
- [ads-monitor](https://affpapa.org/en/nevibecode/skills/ads-monitor.md) — skill · 633 installs
- [ad-attribution-gap](https://affpapa.org/en/nevibecode/skills/ad-attribution-gap.md) — skill · 20500 installs
- [performance-report](https://affpapa.org/en/nevibecode/skills/performance-report.md) — skill · 3000 installs
- [performance-analyzer-sms](https://affpapa.org/en/nevibecode/skills/performance-analyzer-sms.md) — skill · 1700 installs

From the same set: [cognyai/claude-code-marketing-skills](https://affpapa.org/en/nevibecode/by/cognyai/claude-code-marketing-skills.md) — 18 cards

---
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