social-media-analyzer
npx machina-cli add skill alirezarezvani/claude-code-skill-factory/social-media-analyzer --openclawSocial Media Campaign Analyzer
This skill provides comprehensive analysis of social media campaign performance, helping marketing agencies deliver actionable insights to clients.
Capabilities
- Multi-Platform Analysis: Track performance across Facebook, Instagram, Twitter, LinkedIn, TikTok
- Engagement Metrics: Calculate engagement rate, reach, impressions, click-through rate
- ROI Analysis: Measure cost per engagement, cost per click, return on ad spend
- Audience Insights: Analyze demographics, peak engagement times, content performance
- Trend Detection: Identify high-performing content types and posting patterns
- Competitive Benchmarking: Compare performance against industry standards
Input Requirements
Campaign data including:
- Platform metrics: Likes, comments, shares, saves, clicks
- Reach data: Impressions, unique reach, follower growth
- Cost data: Ad spend, campaign budget (for ROI calculations)
- Content details: Post type (image, video, carousel), posting time, hashtags
- Time period: Date range for analysis
Formats accepted:
- JSON with structured campaign data
- CSV exports from social media platforms
- Text descriptions of key metrics
Output Formats
Results include:
- Performance dashboard: Key metrics with trends
- Engagement analysis: Best and worst performing posts
- ROI breakdown: Cost efficiency metrics
- Audience insights: Demographics and behavior patterns
- Recommendations: Data-driven suggestions for optimization
- Visual reports: Charts and graphs (Excel/PDF format)
How to Use
"Analyze this Facebook campaign data and calculate engagement metrics" "What's the ROI on this Instagram ad campaign with $500 spend and 2,000 clicks?" "Compare performance across all social platforms for the last month"
Scripts
calculate_metrics.py: Core calculation engine for all social media metricsanalyze_performance.py: Performance analysis and recommendation generation
Best Practices
- Ensure data completeness before analysis (missing metrics affect accuracy)
- Compare metrics within same time periods for fair comparisons
- Consider platform-specific benchmarks (Instagram engagement differs from LinkedIn)
- Account for organic vs. paid metrics separately
- Track metrics over time to identify trends
- Include context (seasonality, campaigns, events) when interpreting results
Limitations
- Requires accurate data from social media platforms
- Industry benchmarks are general guidelines and vary by niche
- Historical data doesn't guarantee future performance
- Organic reach calculations may vary by platform algorithm changes
- Cannot access data directly from platforms (requires manual export or API integration)
- Some platforms limit data availability (e.g., TikTok analytics for business accounts only)
Source
git clone https://github.com/alirezarezvani/claude-code-skill-factory/blob/dev/generated-skills/social-media-analyzer/SKILL.mdView on GitHub Overview
The Social Media Campaign Analyzer provides comprehensive analysis of social media campaign performance across platforms. It surfaces engagement, reach, ROI, and audience insights to inform data-driven marketing decisions, with trend detection and competitive benchmarking.
How This Skill Works
The tool ingests campaign data in JSON, CSV, or text, including platform metrics, reach data, cost data, content details, and a date range. It uses core scripts calculate_metrics.py and analyze_performance.py to compute engagement rates, ROI, audience patterns, and trends, then outputs a performance dashboard, engagement analysis, ROI breakdown, audience insights, and visual reports (Excel/PDF).
When to Use It
- Analyze this Facebook campaign data and calculate engagement metrics
- What's the ROI on this Instagram ad campaign with $500 spend and 2,000 clicks?
- Compare performance across all social platforms for the last month
- Benchmark client campaigns against industry standards
- Identify high-performing content types and posting patterns
Quick Start
- Step 1: Prepare campaign data in JSON or CSV with platform metrics, reach, cost, content details, and date range.
- Step 2: Run calculate_metrics.py and analyze_performance.py to generate metrics and recommendations.
- Step 3: Review the Performance dashboard and export visual reports (Excel/PDF).
Best Practices
- Ensure data completeness before analysis (missing metrics affect accuracy)
- Compare metrics within same time periods for fair comparisons
- Consider platform-specific benchmarks (Instagram engagement differs from LinkedIn)
- Account for organic vs. paid metrics separately
- Track metrics over time to identify trends
Example Use Cases
- An agency compares Facebook, Instagram, and TikTok campaigns over the last month to optimize ad spend.
- A client ROI calculation with $500 ad spend and 2,000 clicks on Instagram to measure ROAS.
- The tool surfaces the top-performing post types (video, carousel) across campaigns.
- Benchmark client campaigns against industry standards to set performance targets.
- Exportable visual reports (Excel/PDF) with charts for quarterly reviews.
