contentscoring
🥈SilverA Python-based content scoring model for marketing teams that analyzes performance of videos, blogs, and non-gated content to surface what works and what doesn't.
400Updated 3mo ago
Intermediate30min to implementmarketing
Saves ~30 min per use
Quick InstallView Source
git clone https://github.com/rh-marketingops/contentscoring.gitWorks with:
Claude
Overview
About This Skill
The contentscoring skill provides business logic for calculating and maintaining marketing content scores. Built by Red Hat's marketing operations team, it was designed to analyze the performance of videos, blogs, and non-gated content assets. The model surfaces insights about which content performs well or poorly, helping marketing teams prioritize creation and assessment efforts. It is intentionally designed as an analytical guide rather than a prescriptive tool, summarizing performance signals and prompting deeper investigation into the reasoning behind a specific piece's results. Marketing operations analysts and content strategists benefit most from this skill.
How to Use
["Gather your content data: Export performance metrics (views, engagement, conversions) from your analytics tools (e.g., Google Analytics, HubSpot, or YouTube Studio) for the time period you want to analyze.","Run the Content Score Model: Use the Python-based scoring script (or a tool like Google Colab) to input your data. The model will calculate a CSM score for each piece of content based on predefined criteria.","Identify patterns: Look for trends in the top and bottom performers. Note common themes in high-scoring content (e.g., topic, format, length) and weaknesses in low-scoring content (e.g., poor SEO, weak hooks).","Generate actionable insights: Use the AI’s recommendations to refine your content strategy. For example, if video thumbnails correlate with higher CSM scores, A/B test different thumbnail designs for future videos.","Iterate and track: Apply the insights to new content and monitor its performance over time. Re-run the scoring model quarterly to track progress and adjust your strategy based on evolving trends."]
Use Cases
Score blog post performance to identify high- and low-performing content
Evaluate video content effectiveness using consistent scoring logic
Assess non-gated content assets to guide future content creation priorities
Maintain a running content performance score across a marketing content library
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/rh-marketingops/contentscoringRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Analyze the performance of our [CONTENT_TYPE] content (videos, blogs, or non-gated posts) published between [START_DATE] and [END_DATE]. Focus on metrics like [ENGAGEMENT_METRIC] (e.g., views, shares, comments), [CONVERSION_METRIC] (e.g., click-through rate, time on page), and [SEO_METRIC] (e.g., keyword rankings, backlinks). Rank the top 5 performing pieces and the bottom 5 underperforming pieces. For the top performers, suggest how to replicate their success in future content. For the underperformers, recommend specific improvements like topic refinement, format adjustments, or promotion strategies. Use the [CONTENT_SCORE] model to validate your findings.
Example Output
Here’s the content performance analysis for our blog and video library from January 1 to March 31, 2024, based on the Content Score Model (CSM) metrics. The top-performing blog post was *'10 AI Tools to Boost Your Marketing Productivity in 2024'*, which achieved a CSM score of 92/100. This post garnered 12,450 unique views, a 15% click-through rate (CTR) from organic search, and an average session duration of 8 minutes and 32 seconds. Its success was driven by a data-driven angle, actionable takeaways, and a strong SEO strategy targeting long-tail keywords like *'best AI tools for marketers'*. The second-highest performer, *'How to Create a High-Converting LinkedIn Ad in 2024'* (CSM: 88), saw a 22% increase in shares compared to the previous quarter, likely due to its viral-worthy hooks and step-by-step format. The lowest-performing content included *'The History of Email Marketing'* (CSM: 45), which had a high bounce rate (68%) and minimal social engagement. The post lacked modern relevance and failed to address current pain points. Another underperformer, *'5 Ways to Use Chatbots in E-commerce'* (CSM: 52), had a low CTR (3.1%) despite decent views (5,200), suggesting the topic was either oversaturated or poorly targeted. To replicate the success of the top performers, we recommend focusing on content that combines trending topics with data-backed insights, as seen in the AI tools post. For underperformers, consider repurposing them into shorter formats (e.g., infographics or Twitter threads) or updating them with fresh data and case studies. The Content Score Model also flagged that our video content on *'How to Build a Sales Funnel'* (CSM: 60) could benefit from a more engaging thumbnail and a stronger call-to-action in the first 30 seconds to reduce drop-off rates.
Apply to these tools
Browse all toolsCompatible MCP servers
Browse all MCP serversFind the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan