Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plans, creates, and optimizes digital marketing campaigns including content strategy, social media, email marketing, SEO, and AI visibility (GEO). Generates UTM parameters and tracking URLs. Helps develop go-to-market strategies, campaign messaging, content calendars, and performance measurement frameworks. Use when asked to "create a marketing campaign", "plan content strategy", "build email sequences", "set up UTM tracking", "analyze marketing metrics", "launch a product", "optimize for SEO",
.claude/skills/nicepkg-running-marketing-campaigns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 200% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 60% | 0% |
Plan, execute, and measure digital marketing campaigns across content, social, email, and analytics.
Source: where traffic originates (google, facebook, newsletter)
Medium: how it arrives (cpc, email, social, organic)
Campaign: initiative name (spring-sale-2025, product-launch)
Format: lowercase, hyphens, no spaces
Input: "Spring Sale 2025" → Output: "spring-sale-2025"
Input: "Q1 Launch Campaign" → Output: "q1-launch-campaign"
Example: ?utm_source=linkedin&utm_medium=social&utm_campaign=q1-launchEssential fields: Title, Target keyword, Funnel stage (TOFU/MOFU/BOFU), Format, Owner, Publish date, Distribution channels.
Primary metrics by channel:
| Need | Reference | When to Load | |------|-----------|--------------| | Plan content strategy | content-strategy.md | Topic clusters, calendars, funnel mapping, repurposing | | Execute social media | social-media.md | Platform tactics, posting times, engagement benchmarks | | Build email campaigns | email-marketing.md | Sequences, subject lines, segmentation, deliverability | | Track campaigns | utm-tracking.md | UTM formatting, naming conventions, GA4 alignment | | Measure performance | analytics-measurement.md | KPIs, GA4 setup, attribution, ROI calculations | | Launch products | gtm-tools.md | GTM frameworks, positioning, tool selection | | Define brand voice | brand-guidelines.md | Voice dimensions, tone, messaging framework, terminology | | Optimize for search | seo-optimization.md | Technical SEO, on-page, content SEO, link building, E-E-A-T | | Optimize for AI | geo-optimization.md | GEO, LLMO, AEO, AI Overviews, chatbot visibility |
Python utilities for campaign automation:
| Script | Purpose | Usage | |--------|---------|-------| | utm_tools.py | UTM generation, validation, batch processing, QR codes | python utm_tools.py generate --source facebook --medium paid-social --campaign q1-launch | | brand_checker.py | Brand voice compliance, readability scoring, banned words | python brand_checker.py check --file copy.txt |
Generate and validate UTMs:
bash# Generate UTM parameters python scripts/utm_tools.py generate -s facebook -m paid-social -c spring-2025 # Build complete tracking URL python scripts/utm_tools.py build -u https://example.com -s email -m newsletter -c q1-launch # Validate existing URL python scripts/utm_tools.py validate -u "https://example.com?utm_source=email&utm_medium=cpc" # Batch process from CSV python scripts/utm_tools.py batch -f campaigns.csv -u https://example.com -o tracking.csv # Check GA4 channel mapping python scripts/utm_tools.py ga4-check -s facebook -m paid-social
Check brand compliance:
bash# Full compliance check python scripts/brand_checker.py check --file marketing_copy.txt # Check readability score python scripts/brand_checker.py readability --text "Your marketing copy here" # Find banned words python scripts/brand_checker.py banned --file email_draft.txt # Full audit with JSON output python scripts/brand_checker.py full-audit --file campaign.txt --output report.json
What does the user need?
Creating or planning content?
├─ Yes → content-strategy.md
│ • Topic clusters, pillar pages
│ • Content calendars (annual/quarterly/weekly)
│ • TOFU/MOFU/BOFU mapping
│ • Repurposing workflows
└─ No ↓
Platform-specific social guidance?
├─ Yes → social-media.md
│ • Instagram, LinkedIn, TikTok, X, Facebook
│ • Posting cadence and timing
│ • Algorithm priorities
│ • Engagement benchmarks
└─ No ↓
Email campaigns or sequences?
├─ Yes → email-marketing.md
│ • Welcome, drip, re-engagement sequences
│ • Subject line optimization
│ • Segmentation strategies
│ • Deliverability requirements
└─ No ↓
UTM parameters or tracking URLs?
├─ Yes → utm-tracking.md + scripts/utm_tools.py
│ • Parameter formatting rules
│ • Naming conventions
│ • GA4 channel alignment
│ • Dynamic parameters for ads
│ • Batch URL generation
└─ No ↓
Analytics, metrics, or reporting?
├─ Yes → analytics-measurement.md
│ • KPIs by channel
│ • GA4 configuration checklist
│ • Attribution models
│ • ROI formulas
└─ No ↓
Product launch or go-to-market?
├─ Yes → gtm-tools.md
│ • SOSTAC, RACE, AARRR frameworks
│ • Launch campaign structure
│ • Positioning methodology
│ • Marketing tool selection
└─ No ↓
Brand voice, tone, or messaging?
├─ Yes → brand-guidelines.md + scripts/brand_checker.py
│ • Voice dimension matrix
│ • This-but-not-that chart
│ • Messaging framework
│ • Terminology standards
│ • Compliance checking
└─ No ↓
SEO or search engine optimization?
├─ Yes → seo-optimization.md
│ • Technical SEO (crawling, indexing, speed)
│ • On-page SEO (titles, headers, content)
│ • Content SEO (E-E-A-T, topic clusters)
│ • Link building strategies
│ • Core Web Vitals
└─ No ↓
AI visibility, GEO, or chatbot optimization?
├─ Yes → geo-optimization.md
│ • Generative Engine Optimization (GEO)
│ • LLMO (Large Language Model Optimization)
│ • AEO (Answer Engine Optimization)
│ • ChatGPT, Perplexity, AI Overviews visibility
│ • Content structure for AI citation
└─ No → Clarify the specific marketing needFor requests spanning multiple domains, load references in priority order:
| Request Type | Primary | Secondary | Supporting | |--------------|---------|-----------|------------| | Product launch | gtm-tools.md | brand-guidelines.md, content-strategy.md | email-marketing.md, social-media.md | | Campaign tracking | utm-tracking.md | analytics-measurement.md | — | | Quarterly plan | content-strategy.md | social-media.md, email-marketing.md | analytics-measurement.md | | Performance optimization | analytics-measurement.md | (channel-specific) | — | | Brand voice | brand-guidelines.md | brand_checker.py | — | | Search rankings | seo-optimization.md | content-strategy.md | analytics-measurement.md | | AI visibility | geo-optimization.md | seo-optimization.md | content-strategy.md | | Full strategy | seo-optimization.md, geo-optimization.md | content-strategy.md, social-media.md | email-marketing.md, analytics-measurement.md |
Before launching any campaign, verify:
Beginner signals: Asks "what is," "how do I," "why should I," unfamiliar terminology, requests explanations. → Provide concept context before tactics. Explain frameworks. Offer templates.
Experienced signals: Uses correct terminology, asks for benchmarks, requests templates, mentions specific tools. → Skip fundamentals. Provide benchmarks, templates, advanced tactics directly.
In scope:
Out of scope (suggest alternatives):
Clarify before proceeding:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,488 | 13,392 | +79% | 1 | 1 | 0% | 1,261 | 3,783 | +200% | 0 | 0 | — |
case-02 | fail→pass | 21,182 | 19,191 | -9% | 1 | 1 | 0% | 3,402 | 5,511 | +62% | 0 | 0 | — |
case-03 | pass→pass | 9,345 | 6,911 | -26% | 1 | 1 | 0% | 1,339 | 3,542 | +165% | 0 | 0 | — |
case-04 | fail→pass | 13,422 | 9,389 | -30% | 1 | 1 | 0% | 2,125 | 3,845 | +81% | 0 | 0 | — |
case-05 | fail→pass | 21,507 | 6,378 | -70% | 1 | 1 | 0% | 3,815 | 3,482 | -9% | 0 | 0 | — |
case-06 | fail→pass | 10,934 | 3,432 | -69% | 1 | 1 | 0% | 1,940 | 3,097 | +60% | 0 | 0 | — |
case-07 | fail→pass | 9,679 | 2,831 | -71% | 1 | 1 | 0% | 1,734 | 3,039 | +75% | 0 | 0 | — |
case-08 | fail→pass | 8,415 | 3,150 | -63% | 1 | 1 | 0% | 1,221 | 3,060 | +151% | 0 | 0 | — |
case-09 | fail→pass | 7,369 | 3,314 | -55% | 1 | 1 | 0% | 1,236 | 3,061 | +148% | 0 | 0 | — |
case-10 | fail→pass | 6,039 | 2,366 | -61% | 1 | 1 | 0% | 1,120 | 2,904 | +159% | 0 | 0 | — |
case-11 | fail→pass | 13,673 | 5,168 | -62% | 1 | 1 | 0% | 2,205 | 3,545 | +61% | 0 | 0 | — |
case-12 | fail→pass | 19,121 | 24,662 | +29% | 1 | 1 | 0% | 2,885 | 3,231 | +12% | 0 | 0 | — |
case-13 | fail→pass | 19,153 | 5,823 | -70% | 1 | 1 | 0% | 2,902 | 3,563 | +23% | 0 | 0 | — |
case-14 | fail→pass | 12,361 | 7,843 | -37% | 1 | 1 | 0% | 2,024 | 3,768 | +86% | 0 | 0 | — |
case-15 | fail→pass | 13,296 | 6,873 | -48% | 1 | 1 | 0% | 2,234 | 3,639 | +63% | 0 | 0 | — |
case-16 | fail→pass | 11,611 | 7,907 | -32% | 1 | 1 | 0% | 1,780 | 3,682 | +107% | 0 | 0 | — |
case-17 | pass→pass | 14,056 | 12,115 | -14% | 1 | 1 | 0% | 2,190 | 4,419 | +102% | 0 | 0 | — |
case-18 | pass→pass | 15,912 | 9,338 | -41% | 1 | 1 | 0% | 2,384 | 3,998 | +68% | 0 | 0 | — |
case-19 | fail→pass | 8,935 | 2,679 | -70% | 1 | 1 | 0% | 1,343 | 2,935 | +119% | 0 | 0 | — |
case-20 | fail→pass | 10,935 | 5,106 | -53% | 1 | 1 | 0% | 1,741 | 3,359 | +93% | 0 | 0 | — |
case-21 | fail→pass | 13,583 | 4,172 | -69% | 1 | 1 | 0% | 2,311 | 3,151 | +36% | 0 | 0 | — |
case-22 | fail→pass | 14,878 | 4,678 | -69% | 1 | 1 | 0% | 2,278 | 3,382 | +48% | 0 | 0 | — |
case-23 | pass→pass | 6,852 | 3,109 | -55% | 1 | 1 | 0% | 990 | 2,951 | +198% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +83 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.