Find names that make sense without the docs.
What it does
Compares candidate names by testing whether three models infer their intended meaning from a short scenario.
When to use it
Use when choosing among names for a field, enum value, table or glossary word.
How to use it
Give it candidate terms to compare; it returns the test scenario and a scored comparison naming a winner, tie or weak winner.
What you provide
- candidate terms
Uses
Good to know
- starts one helper agent per item, so the count depends on the work
Latest review
What you need · 1
Requires the claude CLI supporting the model, effort and strict MCP configuration flags used by the probe.
Access · 3
This skill
Claude
Write
Sends naming scenarios to Claude
~/.claude/CLAUDE.md
Read
Loads global Claude instructions
temporary directories
Write
Saves raw model responses