medsci-skills Plugin marketplaceA

medsci-skills from aperivue/medsci-skills is a Claude Code plugin marketplace: the list of plugins Claude Code can add from that repo and install by name.

Add it to Claude Code
claude plugin marketplace add aperivue/medsci-skills

Then install any of its 9 plugins by name: the list and each line are below.

Audit grade
A, 14 of 14 checks passed
Kind
Plugin marketplace
Repository
aperivue/medsci-skills
Path
.claude-plugin/marketplace.json
Versions recorded
5
Latest version
git:20260930.c8ed96c, committed Sep 30, 2026
First version recorded
Jul 22, 2026
Size
9,506 bytes
Repository stars
390
License
MIT

Physician-built Claude Code skills for clinical manuscript preparation, with deterministic integrity gates — reporting-guideline and risk-of-bias compliance, reference/citation verification, and numerical-consistency checks — plus literature search, study design, statistics, publication-ready figur… (9 plugins: medsci-literature, medsci-data, medsci-modeling and more).

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.

Plugins in medsci-skills

9 plugins listed in this marketplace file at its latest saved version. Add the marketplace first with the line above.

medsci-literature
Literature search with anti-hallucination citation verification, full-text retrieval, Zotero/Obsidian sync, and reference-integrity audits.
From this repository, ./
claude plugin install medsci-literature@medsci-skills
medsci-data
Study design and validity review, literature-grounded variable operationalization, sample-size planning, data cleaning, de-identification, codebook generation, and dataset versioning.
From this repository, ./
claude plugin install medsci-data@medsci-skills
medsci-modeling
Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never…
From this repository, ./
claude plugin install medsci-modeling@medsci-skills
medsci-analysis
Reproducible statistical analysis, publication-ready figures, batch/cross-national/replication analysis, and meta-analysis synthesis.
From this repository, ./
claude plugin install medsci-analysis@medsci-skills
medsci-writing
IMRAD manuscript and IRB-protocol drafting, AI-pattern removal, AI-search optimization, and reviewer-response letters.
From this repository, ./
claude plugin install medsci-writing@medsci-skills
medsci-review
Pre-submission self-review, peer-review drafting, and reporting-guideline compliance audits against EQUATOR checklists.
From this repository, ./
claude plugin install medsci-review@medsci-skills
medsci-submission
Submission packaging, journal recommendation and profiling, institutional form filling (ICMJE COI, IRB), and grant proposals.
From this repository, ./
claude plugin install medsci-submission@medsci-skills
medsci-project
Research orchestration, project intake and management, research-gap and meta-analysis topic discovery, and author-strategy analysis.
From this repository, ./
claude plugin install medsci-project@medsci-skills
medsci-presentation
Academic presentation and PPTX building, PDF/document rendering, environment setup, skill publishing, and offering your changes back to the project.
From this repository, ./
claude plugin install medsci-presentation@medsci-skills

What the file says

{
  "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  "name": "medsci-skills",
  "description": "Physician-built Claude Code skills for clinical manuscript preparation, with deterministic integrity gates — reporting-guideline and risk-of-bias compliance, reference/citation verification, and numerical-consistency checks — plus literature search, study design, statistics, publication-ready figures, IMRAD drafting, journal selection, peer review, and revision. Submission-grade, not a generic skill catalog.",
  "owner": {
    "name": "Aperivue"
  },
  "plugins": [
    {
      "name": "medsci-literature",
      "displayName": "MedSci Literature & References",
      "description": "Literature search with anti-hallucination citation verification, full-text retrieval, Zotero/Obsidian sync, and reference-integrity audits.",
      "author": {
        "name": "Aperivue",
        "url": "https://github.com/Aperivue"
      },
      "homepage": "https://github.com/Aperivue/medsci-skills#skills",
      "repository": "https://github.com/Aperivue/medsci-skills",
      "keywords": [
        "medical-research",
        "clinical-research",
        "literature-search",
…

Read the whole file at its exact version.

How to install

Install it, pinned
mdr add aperivue/medsci-skills/.claude-plugin/marketplace.json@git:20260930.c8ed96c

Pins git:20260930.c8ed96c in mdr.lock.

The exact contents, by fingerprint
mdr add aperivue/medsci-skills/.claude-plugin/marketplace.json@sha256:6a91ac124f5eec27

The mdr line above pins the label git:20260930.c8ed96c, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_c3xjdm5w6g6tvwdv.svg)](https://markdownregistry.com/a/art_c3xjdm5w6g6tvwdv)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in aperivue/medsci-skills/.claude-plugin/marketplace.json since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of marketplace.json from somewhere else? Ask it: where did my marketplace.json come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Jul 22, 2026 and Sep 30, 2026, about one every 18 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260930.c8ed96c latest2026-09-30 c8ed96c 9,506 BA view · diff
git:20260930.e4f475f2026-09-30 e4f475f 5,362 BA view · diff
git:20260811.90d1e232026-08-11 90d1e23 5,256 BA view · diff
git:20260724.3fd14062026-07-24 3fd1406 5,215 BA view · diff
git:20260722.91bf5d12026-07-22 91bf5d1 5,180 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (9506 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

GitHub

aperivue/medsci-skills · 390 stars · license MIT · pushed 2026-11-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_c3xjdm5w6g6tvwdv
GET https://markdownregistry.com/api/v1/resolve?ref=aperivue/medsci-skills/.claude-plugin/marketplace.json
GET https://markdownregistry.com/api/v1/blob/6a91ac124f5eec27408ec53b02db548f65e8ee97e10542230c7fb490b19e70c6

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: which agent file does what.

More from aperivue/medsci-skills

AGENTS.md AGENTS.md file
aperivue/medsci-skills · AGENTS.md
git:20260930.fd8f1e2 · audit A · 390 stars
CLAUDE.md CLAUDE.md file
aperivue/medsci-skills · CLAUDE.md
git:20261016.e6f0589 · audit A · 390 stars
academic-aio SKILL.md skill
aperivue/medsci-skills · skills/academic-aio/SKILL.md · Use when a medical AI paper should be found and cited by AI search engines and RAG tools. Optimizes the title…
git:20261003.182e0ff · audit A · 390 stars
add-journal SKILL.md skill
aperivue/medsci-skills · skills/add-journal/SKILL.md · Use when a target journal has no profile yet. Reads the journal's author guidelines and writes a detailed /write-paper…
git:20260930.c8ed96c · audit A · 390 stars
analyze-stats SKILL.md skill
aperivue/medsci-skills · skills/analyze-stats/SKILL.md · Use when data needs statistical analysis. Runs reproducible Python/R code for Table 1, diagnostic accuracy, agreement…
git:20261004.a78d7a4 · audit A · 390 stars
architecture-zoo SKILL.md skill
aperivue/medsci-skills · skills/architecture-zoo/SKILL.md · Renamed to /model-selection in v6 (removed in v7).
git:20260930.e4f475f · audit A · 390 stars
author-strategy SKILL.md skill
aperivue/medsci-skills · skills/author-strategy/SKILL.md · Use when analyzing a researcher's publication record from PubMed. Fetches an author's papers, classifies study types…
git:20261002.a99bcb0 · audit A · 390 stars
batch-cohort SKILL.md skill
aperivue/medsci-skills · skills/batch-cohort/SKILL.md · Use when one validated cohort analysis must be repeated across many exposure/outcome pairs. Generates one R/Python…
git:20261004.5b44a65 · audit A · 390 stars
calc-sample-size SKILL.md skill
aperivue/medsci-skills · skills/calc-sample-size/SKILL.md · Use when planning how many patients or cases a study needs before data collection (power analysis, IRB justification)…
git:20260930.c8ed96c · audit A · 390 stars
check-reporting SKILL.md skill
aperivue/medsci-skills · skills/check-reporting/SKILL.md · Use when auditing a manuscript item by item against a reporting guideline or risk-of-bias tool. Covers 49 reporting…
git:20261004.5cd6db2 · audit A · 390 stars
clean-data SKILL.md skill
aperivue/medsci-skills · skills/clean-data/SKILL.md · Use when a clinical CSV/Excel dataset needs profiling and cleaning before analysis (missing values, outliers…
git:20260930.c8ed96c · audit A · 390 stars
contribute SKILL.md skill
aperivue/medsci-skills · skills/contribute/SKILL.md · Use when sending local changes back to the project (an added journal profile, a fixed checklist item, an adapted skill)…
git:20261002.0985a27 · audit A · 390 stars

Every file in aperivue/medsci-skills

Browse by kind, by grade A, or by owner.