3 ready prompts
Written for the moment this actually comes up.
Execute — do the immediate task
+Show me every reference to the class DataValidator across the codebase and list the file path and…
Execute — do the immediate task
+Show me every reference to the class DataValidator across the codebase and list the file path and line number for each occurrence. Prioritize references inside tests and the files under src/services, and open test/validator.test.js after gathering the list.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I ask QA to review changes, make approving this refactor easy: surface whether DataValidator…
Improve — make it easier to accept
+Before I ask QA to review changes, make approving this refactor easy: surface whether DataValidator is subclassed anywhere, highlight calls that pass plain objects instead of validated models, and flag references inside configuration files or scripts that might run outside the test harness.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+I searched for DataValidator and found many usages, some passing raw objects, some constructing…
Decide — diagnose the stuck moment
+I ran a quick search for DataValidator and got dozens of hits with different call patterns.
I searched for DataValidator and found many usages, some passing raw objects, some constructing with different options. I can't tell which callers assume prior validation and which expect the validator to run. Who should I talk to and what's the safest next step to avoid silently changing runtime behavior when I modify the validator?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Next to this one
Other code editor work people do in Visual Studio Code.
Every task here came from the work, not from a feature list — which is why the prompts name what you want done and never the button that does it. The tool changes; the work does not.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.