hallucinating-labels
Installation
SKILL.md
hallucinating-labels
Ask a cheap model to write a plausible label for the item. Snap that label onto the real vocabulary with an embedder. The model never sees the label set.
Doug Turnbull's pattern (softwaredoug.com, 2026-08-10), with the two prompt and boundary corrections that measurement produced.
Check the boundary first
If the whole vocabulary fits in a prompt, do not use this skill. Ship the label list and ask for a constrained choice. Measured on WANDS (860 labels, 468 queries, one gold label each, gemini-3.5-flash-lite):
| approach | acc@1 | acc@3 | input tokens/item |
|---|---|---|---|
| structured output, all 860 labels shipped | 0.701 | 0.744 | 5,265 |
| this skill | 0.564 | 0.690 | 6 |
| embed the item directly, no model | 0.417 | 0.564 | 0 |