Fold raw signalling-question answers into domain-level judgments for RoB2, ROBINS-I, or QUADAS-2, per each tool's own lookup rules — the first of two aggregation levels these tools define. QUADAS-2 is dual-axis (risk-of-bias AND applicability-concern per domain, D1-D3) and terminates here with no further rollup; RoB2/ROBINS-I continue on to worst-case-lookup for an overall verdict. Use this after signalling-question-answering has produced the raw answers.
SkillScore74Maintained
Automatic
◆Clinical / Healthcare pack
Last verified 9/7/2026
What it changes
Passed 16 of 22 test cases with the skill, and 14 of 22 without it.
Without skill65%
With skill74%
Checks it passed that the model alone missed
Identifies spawn-agent as the skill used to spawn the execution subagent
Explains that QUADAS-2 produces terminal dual-axis domain judgments without an overall summary score
2 fixed15 passed either way6 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+11%
Agent turns
0%
Response time
-3%
Model gemini-3.6-flashMeasured 9/7/2026v117 of 23 cases passed with skill · 22 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
When delegating domain judgment calculations to a subagent according to our workflow standards, which specific tool skill is invoked to spawn that subagent?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies spawn-agent as the skill used to spawn the execution subagent
Missed
Passed
case-19 · gemini-3.6-flash · 9/7/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md21 linessingle file
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.