Takes your raw campaign performance data and writes the executive summary paragraph that goes at the top of the report. The plain English explanation of what happened, why it happened, and what's being done about it. The part every client actually reads. Platform: Google and Meta.
git clone https://github.com/irinabuht12-oss/marketing-skills.git--- name: client-report-narratives description: Takes your raw campaign performance data and writes the executive summary paragraph that goes at the top of the report. The plain English explanation of what happened, why it happened, and what's being done about it. The part every client actually reads. Platform: Google and Meta. metadata: platform: Google and Meta --- # 5/ Client Report Narratives — Google + Meta ## What it does Takes your raw campaign performance data and writes the executive summary paragraph that goes at the top of the report. The plain English explanation of what happened, why it happened, and what's being done about it. The part every client actually reads. ## How it works Feed Claude the key metrics for the period — spend, conversions, CPA, ROAS, CTR, impression share, and any notable changes. It identifies the most important trends, connects them to likely causes, and writes a clear narrative that a non-technical stakeholder can understand without asking follow-up questions. ## Practical example You paste in last month's data: $45K spend, 1,180 leads at $38 CPA (down from $44), ROAS 4.2x. Claude writes: "March delivered 1,180 leads at $38 CPA, a 14% improvement over February. The primary driver was the new UGC creative set launched mid-month which outperformed static images by 2.3x on Meta prospecting. Google Search held steady at $29 CPA with branded terms contributing 34% of volume. One area to watch — Meta retargeting CPA increased 18% as the audience pool shrinks, recommending a lookalike refresh for April." ## What you get back - Executive summary paragraph ready to paste into your report - Key wins highlighted with specific numbers - Problem areas flagged with context, not just red numbers - Forward-looking recommendations tied to the data - Written in a tone that matches client communication, not ad platform jargon ## When to use it - Weekly and monthly client reporting - Internal stakeholder updates where you need to explain performance fast - QBR prep when you need narratives for multiple accounts - Any time you're staring at a spreadsheet and need to turn it into words ## Data access (Ryze MCP) This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly: - claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → `https://connector.get-ryze.ai/mcp` - Claude Code: `claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp` - Cursor: Settings → MCP → add the same URL Setup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
["Gather your raw campaign data from [Google Ads/Meta Ads Manager] for the [specified period]. Export metrics like impressions, clicks, CTR, conversions, spend, and CPA.","Identify 2-3 key performance drivers (e.g., audience segments, creative types, or dayparting) and any anomalies (e.g., unexpected drops or spikes).","Paste the prompt template into your AI tool and replace [PLACEHOLDERS] with your data and context. For platforms with multiple accounts/campaigns, focus on the top-performing or most representative set.","Review the AI’s output for accuracy. Adjust tone to match your client’s preferences (e.g., more technical for data-heavy clients or simpler for non-marketers).","Copy the final summary into your report template. Use the AI’s suggestions for corrective actions as talking points in your follow-up meeting."]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/irinabuht12-oss/marketing-skills/tree/main/skills/client-report-narrativesCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Write a concise executive summary for the client report covering [PLATFORM] campaign performance for [MONTH/YEAR]. Highlight key metrics like [IMPRESSIONS], [CLICKS], [CTR], [CONVERSIONS], and [SPEND]. Explain the top 2-3 performance drivers in plain English, noting any anomalies or trends. Include 1-2 sentences on corrective actions or optimizations already implemented. Keep it under 150 words.
For our Meta ad campaigns in July 2024, we delivered 1.2M impressions, 18,450 clicks (CTR 1.53%), and 427 conversions at a $38.20 cost per acquisition—all beating Q2 benchmarks by 12%. The standout performer was our retargeting audience (Audience B), which drove 68% of conversions despite representing only 35% of spend, thanks to our recent creative refresh. We also saw a 22% drop in performance on Tuesday/Wednesday midday slots, which we’ve addressed by pausing underperforming placements. Moving forward, we’ll reallocate 15% of budget to high-performing creative variants and implement dayparting adjustments to capture weekend momentum. Overall, ROAS improved to 3.4x (up from 2.9x last month) while maintaining CAC within target range.
skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan