content-analysis

Extract sentiment, topics, keywords, and insights from text content.

Updated Mar 30, 2026

Search Tags:#llm #insights #nlp #text #analyze #sentiment #topics

Ready to run

npx skills add https://github.com/Patkik/Multi-tenant-SaaS-Catering-V2 --skill content-analysis-patkik

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: content-analysis
Source: https://github.com/Patkik/Multi-tenant-SaaS-Catering-V2/tree/main/.agents/skills/content-analysis
Command: npx skills add https://github.com/Patkik/Multi-tenant-SaaS-Catering-V2 --skill content-analysis-patkik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, nltk, scikit-learn, matplotlib, seaborn, plotly, wordcloud, requests, and includes scripts (resource) components.

What problem does it solve?

Analyzing large volumes of text for sentiment, topics, keywords, and strategic insights can be time-consuming and error-prone when done manually. This skill automates the process using both traditional NLP methods and LLM-powered analysis to deliver consistent, actionable results.

Core Features & Use Cases

Combines traditional NLP with LLM-enhanced analysis to extract sentiment, topics, keywords, and insights from diverse content.
Supports multiple content types (social posts, articles, reviews, video captions, and customer feedback) and multiple languages.
Use cases include brand monitoring, content optimization, market research, and product feedback analysis, enabling rapid decision making.

Quick Start

Process a sample dataset to return sentiment, topics, and actionable insights.

Frequently Asked Questions about content-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I analyze text content for sentiment and topics automatically?▼

To analyze text content for sentiment and topics automatically, this skill uses Python scripts blending traditional NLP and LLM-assisted analysis to extract keywords, sentiment, topics, and insights from diverse sources like social media posts and articles.

Can I use NLP and LLM integration for customer feedback analysis?▼

Yes, you can use NLP and LLM integration for customer feedback analysis. The skill applies modular preprocessing and content classification to process reviews, extracting actionable insights to enable rapid decision making.

Does this text analysis approach support social media posts and articles?▼

Yes, this text analysis approach supports social media posts and articles. It processes diverse content types, including video captions and customer feedback, across multiple languages to deliver consistent results.

What is the best way to extract keywords and visualize insights from reviews?▼

The best way to extract keywords and visualize insights from reviews is using the built-in Python scripts. The skill leverages scikit-learn for topic modeling and matplotlib, seaborn, and plotly to generate visualizations from the extracted data.

Do I need pandas and nltk installed to run content classification scripts?▼

Yes, you need pandas and nltk installed. These are required dependencies for the modular preprocessing and traditional NLP tasks, alongside numpy and scikit-learn, to execute the content classification scripts successfully.

What are the limitations of combining traditional NLP with LLM for text insights?▼

Combining traditional NLP with LLM for text insights means the skill requires multiple Python dependencies like pandas, numpy, and scikit-learn. It functions as an intermediate-level script-based tool rather than a standalone application.