mcpbeat Sign in

Analyzing Marketing Campaign Agent Skill

Analyze weekly marketing campaign performance data across channels. Use when analyzing multi-channel digital marketing data to calculate funnel metrics (CTR, CVR) and compare to benchmarks, compute cost and revenue efficiency metrics (ROAS, CPA, Net Profit), or get budget reallocation recommendations based on performance rules.

773 tokens
context cost
SKILL.md, read when the skill is used
2
files
plus reference files
0
copies elsewhere
how many repositories repackaged it
1 335
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/https-deeplearning-ai/sc-agent-skills-files --skill analyzing-marketing-campaign

The instruction itself

7 sections, as written by the author

Marketing Campaign Analysis

Automated analysis of multi-channel marketing campaign data.

Input Requirements

Expects campaign data in CSV format with these columns:

  • date: Campaign date
  • campaign_name: Campaign identifier
  • channel: Marketing channel
  • segment: Customer segment
  • impressions: Ad impressions (empty for Email channel)
  • clicks: Number of clicks
  • conversions: Number of conversions
  • spend: Marketing spend in dollars
  • revenue: Revenue generated in dollars
  • orders: Number of orders

Data Quality Check

  • Check for missing values and empty cells (Email channel won't have impressions)
  • Verify no negative values in numeric columns
  • Flag anomalies (e.g., conversions without clicks)

Funnel Analysis

Calculate per channel:

  • Click Through Rate (CTR) = clicks / impressions × 100
  • Conversion Rate (CVR) = conversions / clicks × 100

Compare to user-provided benchmarks, report difference in percentage points and provide brief interpretation for each channel. If benchmarks are not provided, use these historical values:

| Channel | CTR | CVR |

|---------|-----|-----|

| Facebook_Ads | 2.5% | 3.8% |

| Google_Ads | 5.0% | 4.5% |

| TikTok_Ads | 2.0% | 0.9% |

| Email | 15.0% | 2.1% |

Efficiency Analysis

Calculate per channel:

  • Return On Ad Spend (ROAS) = revenue / spend
  • Cost Per Acquisition (CPA) = spend / conversions
  • Net Profit = revenue - Total Costs
  • Total Costs = spend + (orders × Shipping Cost) + (revenue × Product Cost %)
  • Unless user specifies different values, use:
  • Shipping Cost: $8 per order
  • Product Cost: 35% of revenue

Compare to user-provided targets. If not provided, use these defaults:

  • Target ROAS: 4.0x minimum
  • Max CPA: $50

Output Format

Present results as tables with status indicators:

Funnel Analysis Table:

| Channel | CTR Actual | CTR Benchmark | CTR Diff | CVR Actual | CVR Benchmark | CVR Diff |

Efficiency Analysis Table:

| Channel | ROAS | Status | CPA | Status | Net Profit | Status |

Status indicators:

  • ROAS: "[OK] Above" if >= target, "[X] Below" if < target
  • CPA: "[OK] Below" if <= max, "[X] Above" if > max
  • Net Profit: "[OK] Positive" if > 0, "[X] Negative" if <= 0

Follow each table with brief channel-by-channel interpretation highlighting key insights and recommended actions.

Budget Reallocation

If user asks about budget reallocation, read references/budget_reallocation_rules.md for the complete decision framework including eligibility rules, performance-based actions, and constraints.

Other skills for the same job

different authors, same section of the catalogue
Internal Comms
by anthropics
vendor ×16

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

377 tokens
Competitive Ads Extractor
by frostant
×10

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

2k tokens
Lead Research Assistant
by frostant
×8

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

1.6k tokens
Developer Growth Analysis
by frostant
×6

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

3.9k tokens
Google Official SEO Guide
by ZhanlinCui
×4

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

4.2k tokens
Web Performance SEO
by ZhanlinCui
×4

Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.

670 tokens
App Store Optimization
by alirezarezvani
×3

Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store

4.1k tokens scripts
Imagegen Frontend Web
by mxyhi
×3

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

9.2k tokens

How to use it

Copy the folder

Take https-deeplearning-ai/analyzing-marketing-campaign from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.