Design or audit the clinical-validation study for an engineer-built medical-imaging model (segmentation, classification, or detection) before the validation report or manuscript is written. Covers patient-level split disjointness and the data-leakage taxonomy, tuning-on-test, internal versus genuine external validation, comparator design, single-run versus multi-seed variance, task-correct metric selection, test-set sizing, and CLAIM 2024 / TRIPOD+AI / STARD-AI reporting fit. Ships a determinist
SkillScore91Maintained
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 20 of 22 test cases with the skill, and 12 of 22 without it.
Without skill57%
With skill91%
Checks it passed that the model alone missed
Classifies the validation tier.
Directs multimodal LLM evaluation to mllm-eval.
Assesses test-set sizing or events-per-class requirements.
and 12 more in the full report
8 fixed13 passed either way2 still failing0 broke
Pass-rate lift
+35 pp
Tokens
+68%
Agent turns
0%
Response time
-20%
Model gemini-3.6-flashMeasured 8/24/2026v2 · latest is v321 of 23 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 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
We completed our validation study design and need to run DeLong tests to compare AUROCs and generate bootstrap confidence intervals and calibration curves for our final table. Which skill or step owns statistical calculation execution?
What was checked, without and with the skill
Checked
Without skill
With skill
Routes statistical calculation execution to analyze-stats.
Missed
Passed
case-18 · 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
/model-validation was renamed to /model-assessment in v6.0; this redirect is removed in v7.
Run /model-assessment now, passing the same arguments the user gave /model-validation.
Start at /model-assessment Part A, Phases 1–7 (validation design and the split-leakage gate).