Profile a medical-imaging dataset before any modelling decision is made — the acquisition grid, voxel spacing and orientation spread, the intensity domain, which label values are actually present, how much of the volume the target occupies, and how large the target is in millilitres — then gate that profile against the researcher's declared plan. Catches, at the point where it is still cheap, the dataset facts that otherwise surface after a training run: a "test set" that carries no ground truth
SkillScore84Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆AI Engineer pack
Last verified 8/24/2026
What it changes
Passed 18 of 22 test cases with the skill, and 11 of 22 without it.
Without skill52%
With skill84%
Checks it passed that the model alone missed
Identifies the LABEL_MISSING audit verdict
Identifies the ORIENTATION_MIXED audit verdict
Identifies the TEST_SET_UNLABELLED audit verdict
and 7 more in the full report
9 fixed12 passed either way3 still failing1 broke
Pass-rate lift
+32 pp
Tokens
+61%
Agent turns
0%
Response time
-56%
Model gemini-3.6-flashMeasured 8/24/2026v1 · latest is v221 of 25 cases passed with skill · 22 comparable
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/3/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
During automated verification, a scan volume has grid dimensions 512x512x120 while its matching segmentation label volume has dimensions 512x512x110. Which audit verdict flags this error?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies the LABEL_SHAPE_MISMATCH audit verdict
Missed
Passed
case-13 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md3 linessingle file
/profile-imaging was renamed to /imaging-data in v6.0; this redirect is removed in v7.
Run /imaging-data now, passing the same arguments the user gave /profile-imaging.
Start at /imaging-data Phases 1–3 (profile the dataset, gate the profile, record the decisions).