Sentiment Analysis

This is a structured framework for turning messy feedback data into segmented insights with sentiment scores, JTBD analysis, and concrete recommendations. You feed it CSVs, PDFs, or survey dumps, and it identifies user segments, assigns sentiment scores on a -1 to +1 scale, and pulls out pain points versus wins for each group. The output is thorough, maybe more thorough than you need for a quick pulse check, but that's the point. It's built for when you have hundreds or thousands of feedback entries and need to see patterns across different user types rather than reading everything yourself. Works best when you actually have rich feedback data to analyze, not just a handful of comments.

Install to Claude Code

npx -y skills add phuryn/pm-skills --skill sentiment-analysis --agent claude-code