analyze

Analyze customer feedback sentiment, themes, and trends with regex-based extraction.

8|2|Updated Feb 9, 2026

Search Tags:#feedback #insights #themes #trends #analyze #customer #sentiment

Ready to run

npx skills add https://github.com/mikeparcewski/wicked-garden --skill analyze-mikeparcewski

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: analyze
Source: https://github.com/mikeparcewski/wicked-garden/tree/main/skills/product/analyze
Command: npx skills add https://github.com/mikeparcewski/wicked-garden --skill analyze-mikeparcewski

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze sentiment, extract themes, and detect trends from customer feedback to inform product decisions and improve customer understanding.

Core Features & Use Cases

Sentiment analysis to classify feedback as positive, negative, neutral, or mixed, with intensity scoring.
Theme extraction to cluster feedback into actionable topics and priorities.
Trend detection to identify emerging or declining signals over time and across segments.
Prioritization assistance by scoring themes based on frequency, severity, and urgency.

Quick Start

Analyze recent feedback to reveal sentiment, themes, and trends.

Frequently Asked Questions about analyze

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

FAQPage Schema

How do I analyze customer feedback to identify sentiment and themes?▼

Analyze customer feedback by applying regex-based keyword extraction and co-occurrence clustering to classify sentiment and group responses into actionable themes. This process scores feedback intensity to prioritize product decisions based on aggregated support emails and survey responses.

Can I detect trends in customer sentiment over time from survey responses?▼

Yes, you can detect trends in customer sentiment over time by analyzing targeted segments and timeframes within your feedback corpus. The process identifies emerging or declining signals to help inform product decisions and improve customer understanding.

What is the best way to extract actionable themes from support emails?▼

Extract actionable themes from support emails by using co-occurrence clustering to group related feedback topics. The approach scores themes based on frequency, severity, and urgency to deliver prioritized insights for product decisions.

Does this sentiment analysis approach work with mixed positive and negative review data?▼

Yes, this sentiment analysis approach works with mixed review data by classifying feedback as positive, negative, neutral, or mixed with intensity scoring. It applies lightweight text processing to the full corpus to extract themes and trends.

How do I prioritize product decisions based on negative customer feedback?▼

Prioritize product decisions by scoring negative customer feedback themes based on frequency, severity, and urgency. The scoring mechanism processes aggregated feedback to highlight the most critical issues requiring immediate attention.

What are the limitations of regex-based keyword extraction for customer feedback analysis?▼

Regex-based keyword extraction for customer feedback analysis relies on lightweight text processing, which may miss nuanced linguistic context or complex sarcasm. It works best for straightforward sentiment classification and theme clustering rather than deep semantic understanding.