"It wasn't scary" is bad news, "it wasn't confusing" is good: sorting tester comments

Counting words in tester comments goes wrong at "not". The same little word turns a compliment into a complaint depending on what you wanted the player to feel. This entry sorts comments into problems and praise by looking at the feeling you aimed for.

Why this works

A word has no value by itself. Whether it is praise or complaint depends on the feeling you wanted and on whether a small word like not turns it around. So the sorting must start from what you intended, one short clause at a time.

When not to use it

It fails on irony, long winding sentences and comments in other languages. If you have fewer than a few dozen comments, just read them all yourself. The sorting is only a way to decide which pile to read first.

In the full entry

• What to build, step by step
• Starting values and the reason for each
• 4 common mistakes and the fix
• 34 lines of example code with 5 checks that pass
• How your AI shows you that it works

Say this to your AI

Use the Spielerando entry ""It wasn't scary" is bad news, "it wasn't confusing" is good: sorting tester comments" (read_entry comment-says-not-scary-is-that-bad) in my game. Build it step by step, and show me how you checked that it works.

Or skip this and connect the MCP: your AI then finds all of this by itself.Connect the MCP