Vet the concrete third-party model a study will be built on — this repository, this revision, this checkpoint — not the architecture family. Records a model dossier (source and version pin, licence and the file it was read from, intended use, pretrained-weight provenance, model task vs study task, reported validation, what the model was developed on, your evaluation arms) and gates it deterministically. Catches what a licence check and a citation count cannot: an evaluation arm sitting on the be
SkillScore77Maintained
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 15 of 19 test cases with the skill, and 5 of 19 without it.
Without skill27%
With skill77%
Checks it passed that the model alone missed
Identifies the audit verdict NO_VERSION_PIN
Identifies the audit verdict LICENCE_UNSTATED
Identifies the audit verdict HARDWARE_UNVERIFIED
and 15 more in the full report
12 fixed5 passed either way4 still failing1 broke
Pass-rate lift
+50 pp
Tokens
+44%
Agent turns
0%
Response time
-57%
Model gemini-3.6-flashMeasured 8/24/2026v1 · latest is v217 of 22 cases passed with skill · 19 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 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
We are integrating a pre-trained weights checkpoint `bone-density-eval.pth` whose source repository gives no documentation regarding what dataset was used to pretrain the weights. What major verdict does the provenance script produce when `weights.pretrained` is true but training corpus details are absent?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies the audit verdict WEIGHTS_PROVENANCE_UNKNOWN
Missed
Passed
Refrains from guessing training datasets when none are documented
Passed
Passed
case-16 · 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-sourcing was renamed to /model-selection in v6.0; this redirect is removed in v7.
Run /model-selection now, passing the same arguments the user gave /model-sourcing.
Start at /model-selection Phases 4–6 (write and gate the model dossier for the concrete repository or checkpoint).
General-purpose research orchestrator. Routes ambiguous or multi-step requests to the right skill(s) from the medsci-skills bundle. Use when the user describes a research goal without naming a specific skill, or when a task spans multiple skills.