Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/acu-nugget-recall
Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers.
Passed 21 of 23 test cases with the skill, and 11 of 23 without it.
and 14 more in the full report
12 fixed10 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are starting an ACU recall run for paper arxiv:2201.11903 ('Chain-of-Thought Prompting Elicits Reasoning in Large Language Models'). Which directory should be created to hold all intermediate unit and matching JSON files?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies creating the acu-nugget-recall/ directory. | Missed | Passed |
The instructions your model reads when the skill loads.
target_summary; never generate the scored summary inside this
tactic.acu-nugget-recall/.target_summary in one call.03-recall-aggregate.json.Write 01-atomic-unit-writing.json, 02-atomic-unit-matching.json, and
03-recall-aggregate.json. Record the summary source. Report every unmatched
unit, not just the score. For a single-summary Nugget run, carry the method's
weak per-topic reliability caveat alongside the number.
test cases passed, vs 11 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.