Individual skill
mllm-eval
Use when designing or auditing how an LLM or multimodal LLM is evaluated on a clinical task (report generation, VQA, text extraction). Covers reference standard, clinical-efficacy metrics beyond BLEU/ROUGE, hallucination, contamination and prompt sensitivity. Imaging models are /model-assessment.
skills/mllm-eval/SKILL.md
Source commit cc462bc2069064b557c2fea12a1f83ed1fe67f66
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 376
- Repository last updated
- Nov 10, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- biostatistics Repository topic
- claude-code Repository topic
- claude-skills Repository topic
- clinical-research Repository topic
- diagnostic-accuracy Repository topic
- literature-review Repository topic
- manuscript Repository topic
- medical-ai Repository topic
- medical-research Repository topic
- meta-analysis Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 7,865 bytesSKILL.mdcore · 7,865 bytesSKILL.mdcore · 7,865 bytesreferences/eval_manifest_schema.mddoc · 4,175 bytesreferences/evaluation_axes.mddoc · 12,352 bytesscripts/check_mllm_eval_completeness.pyruns · 25,392 bytesscripts/mllm_eval_completeness_challenge/fixture/manifest_bad.jsonasset · 354 bytesscripts/mllm_eval_completeness_challenge/fixture/manifest_good.jsonasset · 791 bytesscripts/mllm_eval_completeness_challenge/fixture/plan_bad.mddoc · 202 bytesscripts/mllm_eval_completeness_challenge/fixture/plan_good.mddoc · 795 bytesscripts/mllm_eval_completeness_challenge/problem.mddoc · 2,078 bytesscripts/mllm_eval_completeness_challenge/verify.shruns · 2,568 bytesskill.ymlasset · 3,506 bytestemplates/eval_manifest.jsonasset · 791 bytestests/test_mllm_eval_completeness.shruns · 12,785 bytes
Read excerpt
# MLLM-Eval Skill
## Purpose
This skill makes an **LLM / MLLM clinical evaluation defensible**: a real adjudicated reference standard,
faithfulness measured not assumed, clinical-efficacy metrics beyond n-gram overlap, a pretraining-
contamination check, prompt-sensitivity disclosed, and a reader study where text is generated. It is
**model-agnostic** — every check applies to a closed API and to open weights — and **read-only** (an
advisory design/audit skill): it audits the evaluation design and **specifies and routes** the
clinical-efficacy metrics (RadGraph-F1 / CheXbert-F1 via their published extractors) rather than running
the model or computing the metrics itself.
It is the LLM/MLLM **evaluation-design counterpart** in the lane — an auditor that hands the specified
metrics to their extractors and `/analyze-stats`, parallel to how `/model-assessment` audits an imaging