Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/disagreement-mapping
Map disagreement structure by collecting judgments, clustering opinions, extracting arguments per cluster, and visualizing fault lines.
Passed 19 of 22 test cases with the skill, and 16 of 22 without it.
and 2 more in the full report
4 fixed15 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a medical association poll regarding universal baseline coverage, 120 physicians responded. Group 1 (30 doctors) supports it based on public health outcomes; Group 2 (30 doctors) supports it to eliminate administrative billing overhead; Group 3 (40 doctors) opposes it citing federal budget deficit risks; Group 4 (20 doctors) opposes it citing concerns over government intervention in clinical care decisions. Construct the opinion topology map.
| Checked | Without skill | With skill |
|---|---|---|
| The output forms 4 distinct opinion clusters based on underlying reasoning. | Passed | Passed |
| The output includes explicit cluster sizes for all identified groups. | Passed | Passed |
| The output categorizes fault lines by dispute type. | Missed | Passed |
The instructions your model reads when the skill loads.
Map the structure of disagreement rather than forcing convergence. Collect diverse judgments, identify natural clusters of opinion, extract the core arguments supporting each cluster, and produce a visual map of the disagreement topology.
judgment-collection to gather positions and reasoning from all perspectivescluster-analysis to identify natural groupings of similar positionsargument-extraction for each cluster to surface core argumentsdisagreement-visualization to produce the disagreement map| SOP | Role in Tactic |
|---|---|
| judgment-collection | Gather positions with reasoning from all perspectives |
| cluster-analysis | Identify natural opinion clusters and characterize them |
| argument-extraction | Extract and steel-man core arguments for each cluster |
| disagreement-visualization | Produce structured map of clusters, arguments, and fault lines |
Optional, no fixed order; the final leaf is always a sop.
test cases passed, vs 16 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.