pm-feedback

Categorize feedback, analyze sentiment, and rank issues into Markdown reports.

46|8|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/konglong87/superPM --skill pm-feedback-konglong87
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pm-feedback
Source: https://github.com/konglong87/superPM/tree/main/skills/03-growth-iteration/pm-feedback
Command: npx skills add https://github.com/konglong87/superPM --skill pm-feedback-konglong87

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns messy user feedback and comments into an actionable analysis, so you can understand satisfaction, identify key issues, and prioritize improvements instead of guessing.

Core Features & Use Cases

  • Multi-dimensional feedback analysis: categorizes feedback, analyzes sentiment, assesses priority (P0–P3), and clusters problems into core issue groups.
  • Parallel subagent execution: runs the four analysis dimensions concurrently to produce a faster, more complete report.
  • Decision-ready output: generates a consolidated improvement report and recommends next skills for prioritization, iteration planning, and documentation updates.

Use case example: You collect 200 app reviews and support messages after a feature release, then use this Skill to determine which issues drive negative sentiment, how urgent they are, and what to fix first.

Quick Start

Provide your user feedback data (paste content or point to a file), and ask the Skill to generate the user feedback analysis report with prioritized improvement actions.

Frequently Asked Questions about pm-feedback

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

FAQPage Schema
How do I analyze user feedback and prioritize product improvements?

To analyze user feedback and prioritize improvements, you provide raw comments and reviews to generate categorized insights, sentiment results, and priority-ranked issues. The system categorizes feedback, analyzes sentiment, assesses priority from P0 to P3, and clusters problems into core groups for actionable iteration planning.

What is the best way to turn app reviews into a structured Markdown report?

The best way to turn app reviews into a structured Markdown report is by running parallel subagent processing on the raw text. This concurrently executes categorization, sentiment analysis, priority assessment, and problem clustering to output consolidated improvement reports under specified documentation directories.

Can I process customer support messages and post-release reviews together for sentiment analysis?

Yes, you can process customer support messages and post-release reviews together for sentiment analysis. The system applies multi-dimensional feedback analysis across multiple feedback sources to help product teams perform customer support triage and feedback-driven iteration planning.

How do I cluster user feedback problems into core issue groups for iteration planning?

You cluster user feedback problems into core issue groups by feeding raw text into a feedback analysis workflow. It automatically identifies related problem themes and groups them, allowing you to determine which issues drive negative sentiment and what to fix first.

Does user feedback analysis work without specifying a specific file format for the input data?

Yes, user feedback analysis works without a specific file format because you can directly paste content or point to a file. The system uses AskUserQuestion-driven data intake to collect the necessary text for generating prioritized improvement actions.