yogsoth-ai Domain Level Judgment
Signalling answers → domain-level judgments via each tool's own lookup rules. QUADAS-2's dual-axis output (risk-of-bias + applicability-concern per domain) terminates here — no further rollup exists for it. RoB2/ROBINS-I continue to worst-case-lookup.
Execution
Subagent — spawned via spawn-agent skill.
Why This SOP Exists (coverage-audit S4)
The original graph connected signalling-question-answering directly to an overall-judgment node, with no place for the first-level domain rollup RoB2/ROBINS-I/QUADAS-2 all define algorithmically before any overall verdict — and no place at all for QUADAS-2's terminal dual-axis output, since QUADAS-2 never reaches a "worst case across domains" step the way RoB2/ROBINS-I do.
Available SOPs
| SOP | When to use |
|---|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. |