respond-to-eval

The Skill processes course evaluations by parsing free-text and numeric feedback from a CSV file, clustering comments into themes based on sentiment and frequency, and generating a structured teaching improvement plan with targeted actions.

Student feedback analysis groups comments into themes by evaluating frequency and sentiment, then classifying each thematic cluster into categories like 'Keep', 'Change', 'Investigate', or 'Out-of-scope' to guide teaching improvements.

Yes, the course evaluation analysis supports processing both free-text and numeric feedback, enabling comprehensive assessment of student responses to produce a structured teaching improvement plan.

Yes, you need Python libraries for file parsing and text processing to run course evaluation clustering, as the script relies on these dependencies to analyze feedback and generate the improvement plan.

The best way to turn end-of-semester course evaluations into actionable changes is to use an automation script that categorizes feedback into thematic clusters and outputs a structured plan classifying items as 'Keep', 'Change', or 'Investigate'.

Course evaluations should be in a CSV format for automated teaching improvement analysis, as demonstrated by the quick start command which processes a file named course-evaluation.csv to parse student feedback.