Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/consensus-classification
Classify items as consensus or dissensus at a given threshold.
Passed 19 of 21 test cases with the skill, and 5 of 21 without it.
and 31 more in the full report
15 fixed5 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have 5 pediatric oncology treatment indications evaluated by a panel of 10 specialists with scores from 0.0 to 1.0 (Threshold: 0.80). Indication A: 0.95, Indication B: 0.82, Indication C: 0.78, Indication D: 0.60, Indication E: 0.80. Format the result as JSON arrays. Most analysts summarize these as a bulleted report with Markdown headings, but we need raw JSON array outputs.
| Checked | Without skill | With skill |
|---|---|---|
| Indication E is classified in consensus_items[] for meeting the 0.80 threshold. | Missed | Passed |
| Indication C is classified in dissensus_items[] for falling below the 0.80 threshold. | Missed | Passed |
| The response uses explicit consensus_items[] and dissensus_items[] JSON array keys. | Missed | Passed |
The instructions your model reads when the skill loads.
Classify each item (question, indication, or topic) as having reached consensus or remaining in dissensus at the specified threshold. Produces two clean lists with supporting evidence.
Spawn a subagent that takes judgments and a threshold value, then classifies each item and provides the evidence for classification.
Output MUST contain: consensus_items[] and dissensus_items[] arrays. Every item in the input must appear in exactly one list. Each item must include its score and classification rationale.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
test cases passed, vs 5 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.