Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/argument-synthesis
Strategy for synthesizing argument positions — aggregate evidence, resolve contradictions, produce synthesis reports identifying which claims survive scrutiny.
Passed 17 of 22 test cases with the skill, and 7 of 22 without it.
and 12 more in the full report
13 fixed4 passed either way2 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
During the self-check probe after reaching budget on the space exploration subsidy debate, we discovered missing nuances regarding non-contested claims. How many additional iterations are permitted to resolve these gaps?
| Checked | Without skill | With skill |
|---|---|---|
| The response limits additional iterations to a maximum of 2. | Missed | Passed |
The instructions your model reads when the skill loads.
Synthesize coherent positions from the argument graph. Aggregates evidence across claims, resolves contradictions where possible, and produces synthesis reports that identify which claims survive scrutiny and which are undermined.
| Metric | Small | Medium | Large |
|---|---|---|---|
| Claims synthesized | 10 | 25 | 50 |
| Contradictions resolved | 2 | 6 | 12 |
| Synthesis reports | 1 | 3 | 5 |
| Metric | Target | Current | % |
|---|---|---|---|
| Claims synthesized | — | — | — |
| Contradictions resolved | — | — | — |
| Synthesis reports | — | — | — |
Cannot exit until 80% of budget targets met.
After budget gate passes, self-check:
Max 2 extra iterations if gaps found.
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.