Judge a three-way SUPPORTS/REFUTES/NOINFO label for an atomic claim, based only on its selected rationale sentences (SciFact's final classification step). Use this after rationale-selection has produced the evidence sentences — this is the terminal step of the SciFact chain, producing the complete (claim, abstract, label, rationale) tuple.
SkillScore61Maintained
Automatic
◆AI Engineer pack
Last verified 9/8/2026
What it changes
Passed 13 of 21 test cases with the skill, and 8 of 21 without it.
Without skill39%
With skill61%
Checks it passed that the model alone missed
Assigns the label NOINFO.
Assigns the label REFUTES.
Dispatches a subagent via spawn-agent.
and 2 more in the full report
5 fixed9 passed either way9 still failing0 broke
Pass-rate lift
+22 pp
Tokens
+16%
Agent turns
0%
Response time
+2%
Model gemini-3.6-flashMeasured 9/8/2026v114 of 23 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
Claim: 'Daptomycin remains effective against enterococcal biofilm formation at low doses.' Rationale: 'Low-dose daptomycin failed to reduce biofilm mass in enterococcal isolates, showing complete loss of efficacy.' Predict the SciFact label.
What was checked, without and with the skill
Checked
Without skill
With skill
Assigns the label REFUTES.
Missed
Passed
case-20 · gemini-3.6-flash · 9/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md17 linessingle file
Claim Label Prediction
Three-way SUPPORTS/REFUTES/NOINFO label, grounded only in the selected rationale sentences — terminal step of the SciFact 3-chain.
Execution
Subagent — spawned via spawn-agent skill.
Available SOPs
SOP
When to use
spawn-agent
Spawn a customized CC subagent with full MCP tool access.