Feedback Analyzer Skill for ChatGPT: Cluster Comments and Keep Evidence
Label customer comments by topic and sentiment, link each group to input evidence, and record the sample size. Use the clusters to decide what merits follow-up.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download skills/feedback-analyzer/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for feedback-analyzer together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that feedback-analyzer appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
Classify four fictional comments: A found search fast, B could not find filters, C had to scroll to see filters, and D requested dark mode. Include evidence IDs for each theme.What to check
Filter visibility groups B and C. A is positive search feedback and D is a theme request. The four-comment limit is visible before readers draw any prevalence conclusions.
Original SKILL.md on GitHub · Updated
Frequently asked question
How do I count a comment about both search and filters?
Use multiple labels where they add value and preserve the input ID. Say that theme counts overlap and report a separate unique-comment total.