mllm-eval SKILL.md skillA
mllm-eval from aperivue/medsci-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add aperivue/medsci-skills/mllm-eval@git:20261004.2b37f5bPins git:20261004.2b37f5b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- aperivue/medsci-skills
- Path
skills/mllm-eval/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261004.2b37f5b, committed Oct 4, 2026
- First version recorded
- Jun 28, 2026
- Size
- 7,865 bytes
- Repository stars
- 366
- License
- MIT
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 model's design and computes its metrics. The reviewer-side audit of a finished manuscript uses the `mllm_evaluation.md` (ME0–ME8) probe via `/self-review` and `/peer-review`; this skill is the author-side harness design. It routes the reader study to …
Read the whole file at its exact version.
How to install
mdr add aperivue/medsci-skills/mllm-eval@sha256:148f033be25b3d68The line at the top of this page pins the label git:20261004.2b37f5b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_wstovtcieg3rpkzu)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Jun 28, 2026 and Oct 4, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261004.2b37f5b latest | 2026-10-04 | 2b37f5b | 7,865 B | A | view · diff |
| git:20261003.5e119f6 | 2026-10-03 | 5e119f6 | 7,703 B | A | view · diff |
| git:20261003.e424819 | 2026-10-03 | e424819 | 7,492 B | A | view · diff |
| git:20261003.a4b19a8 | 2026-10-03 | a4b19a8 | 6,987 B | A | view · diff |
| git:20260930.c8ed96c | 2026-09-30 | c8ed96c | 6,438 B | A | view · diff |
| git:20260629.657d615 | 2026-06-29 | 657d615 | 6,720 B | A | view · diff |
| git:20260628.530cf75 | 2026-06-28 | 530cf75 | 6,288 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7865 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
aperivue/medsci-skills · 366 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wstovtcieg3rpkzu GET https://markdownregistry.com/api/v1/resolve?ref=aperivue/medsci-skills/mllm-eval GET https://markdownregistry.com/api/v1/blob/148f033be25b3d68a8936f9c485e07d522ed1499ee65a5d7d66709e96dd4172d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.