Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/argumentative-zoning
Tactic: Label every sentence of one paper with its rhetorical role using Argumentative Zoning.
Passed 2 of 9 test cases with the skill, and 2 of 9 without it.
1 fixed4 passed either way15 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Perform argumentative zoning on paper 'arxiv:2310.05555'. To save space, segment the manuscript into paragraph units rather than sentences.
| Checked | Without skill | With skill |
|---|---|---|
| Segments text using sentence granularity. | Missed | Passed |
| Stores line, start, end offset metadata for units. | Missed | Passed |
The instructions your model reads when the skill loads.
not_found.{line, start, end} offsets. Write 01-unit-segmentation.json.label_set: argumentative-zoning,
hierarchy_toggle: false, and output_type: single_label. Write
02-unit-classification.json.Use exactly AIM, BACKGROUND, OWN, CONTRAST, BASIS, TEXTUAL, and OTHER. Every sentence receives one label; use OTHER rather than skipping an uncertain unit. Narrow scopes are valid but not distributionally comparable to a full-text run.
Report scope, sentence count, zone counts, empty zones, and both paths.
test cases passed, vs 2 / 9 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.