Miller-Jensen lab skills: Python, R, single-cell secretion, flow cytometry, live-cell imaging, stochastic gene expression, and domain primers.
Python implementation rules for Miller-Jensen lab analysis code — uv environments, ruff, portable paths, and notebook-vs-script discipline. TRIGGER when editing .py files, writing analysis scripts, structuring a Python project, or refactoring notebook code into reusable modules in a Miller-Jensen lab repository.
Search the scientific literature for the Miller-Jensen lab using public REST APIs (PubMed/OpenAlex/Crossref/Europe PMC/bioRxiv/Semantic Scholar/arXiv/Unpaywall) and optionally Ai2 Asta. TRIGGER when the user asks to find papers on a topic, do a quick literature lookup, locate a DOI or PMID, get the latest preprints, or ground a claim in real published work. For a reproducible local corpus snapshot, see [local-lit-search](../local-lit-search/SKILL.md).
Build and query a local SQLite FTS5 corpus of the scientific literature for a Miller-Jensen lab project — interview-driven PubMed pulls, Semantic Scholar citation enrichment, PMC full-text fetch with download safeguards, and grounded `[PMID:…]` citations. TRIGGER when the user asks to build a literature corpus, write a manuscript intro that needs stable citations, do a paper-replication lit review, or get reproducible answers across sessions on a specific research question. For ad-hoc / single-query lookups, prefer [literature-search](../literature-search/SKILL.md).
Agent behavior for git and GitHub in Miller-Jensen lab work — when to branch, what to commit, what to ignore, when to push back on big files, and how to handle the lab org `miller-jensen-lab`. TRIGGER when working in a git repository whose origin is under `miller-jensen-lab/*` OR a lab member's personal account doing lab-related work, when running `git`, `gh`, or any commit/branch/PR/repo-creation flow on lab code.
Use the Zotero local HTTP API (and Zotero Web API where needed) to search the user's reference library, add references by DOI, export BibTeX or CSL-formatted bibliographies, and manage collections and tags from within an analysis or manuscript repository. TRIGGER when the user mentions Zotero, citations, references, BibTeX, `.bib` files, DOIs in the context of citing a paper, or a manuscript draft asking for "the right paper for this claim."
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin marketplace of skills for the Miller-Jensen lab at Yale. Once installed, Claude Code loads the right skill on demand when you ask it to do something lab-shaped — write an analysis script, fit a bursting model, gate a flow file, refactor a notebook, etc.
Two pillars:
For generic bioinformatics skills (single-cell QC, scVI, 10x Genomics, Nextflow, PubMed/bioRxiv search), install Anthropic's life-sciences marketplace alongside this one. We deliberately don't duplicate those skills.
/plugin marketplace add anthropics/life-sciences
This marketplace focuses on what's specific to the lab's work — single-cell secretion, stochastic gene-expression models, live-cell reporter imaging, cell-cell communication inference, flow cytometry, smFISH — plus general Python/R hygiene tuned for analysis (not web apps or CLI tools).
You need Claude Code installed. Inside Claude Code:
/plugin marketplace add miller-jensen-lab/claude-code-marketplace
/plugin install mjlab@miller-jensen-lab
Update later with /plugin marketplace update miller-jensen-lab.
Per-project install, GUI install paths (VS Code, Cursor, JetBrains), and verification — see the Yale SOM HPC marketplace README for the full menu; the steps are identical.
mjlab pluginGeneral programming — Python, R, and analysis hygiene tuned for lab work.
| Skill | Purpose |
|---|---|
overview | Mental model, two-pillar manifesto, pointers into other skills. |
programming-and-coding | Cross-language coding philosophy (KISS, small functions, smoke tests). |
coding-in-python | uv, ruff, pytest, pathlib, notebook-vs-module discipline. |
coding-in-r | renv, tidyverse, lintr/styler, testthat, Bioconductor staples. |
tabular-data | Polars/DuckDB/Parquet defaults; when to leave pandas. |
notebooks | When to use a notebook, when to refactor, headless execution. |
plotting | Publication-quality ggplot2 / matplotlib defaults; colorblind-safe palettes. |
starting-a-new-project | Reproducible project layout (data/, src/, notebooks/, results/). |
reproducible-envs | uv and renv lockfiles, pinning, restore-from-scratch checks. |
code-review | Self-review checklist before opening a PR. |
code-overview | How to read into an unfamiliar lab repo quickly. |
using-git-and-github | Agent judgment for branches, commits, repo naming, big-file pushback, and the lab org. |
zotero | Use the Zotero local API to search, cite, and export bibliographies; manuscript citekey workflow. |
literature-search | Live-oracle search across PubMed/OpenAlex/Crossref/Europe PMC/bioRxiv/Semantic Scholar/arXiv/Unpaywall + Ai2 Asta. |
local-lit-search | Build a reproducible local SQLite FTS5 corpus from PubMed/PMC; answer questions with grounded [PMID:…] citations. |
web-scrape | curl with curl_chrome, playwright-cli for JS-heavy sites, GEO/SRA APIs. |
Lab-specific analyses — gap-filling skills, mostly first-of-kind as Claude Code skills.
| Skill | Purpose |
|---|---|
cell-cell-communication | CellChat / NicheNet / CellPhoneDB; ligand-receptor scoring. |
single-cell-secretion | Microfluidic multiplex cytokine analysis; polyfunctionality scoring. |
flow-cytometry | FCS handling, compensation, biexponential transforms, reproducible gating. |
live-cell-imaging | Reporter time-lapse, single-cell tracking, fold-change detection. |
smfish | Spot detection, per-cell transcript counts, fitting to bursting models. |
stochastic-gene-expression | Telegraph model, Gillespie/CME simulation, MLE on mRNA distributions. |
bio-data-hygiene | Sample sheets as source of truth, GEO/SRA submission prep, naming. |
bio-stats | Multiple testing, batch effects, mixed models for repeated-measures data. |
Domain primers — onboarding maps for an agent that needs to come up to speed.
| Skill | Purpose |
|---|---|
macrophage-immunology | M1/M2 axes, TLR/TNF/IFN signaling, TAMs, network-motif framing. |
hiv-latency | Reservoir biology, reactivation strategies, reporter systems. |
transcriptional-bursting | Telegraph model intuition, burst size vs. frequency, key papers. |
systems-immunology | Heterogeneity, single-cell methods, cell-cell communication. |
npx claudepluginhub miller-jensen-lab/claude-code-marketplace --plugin mjlabUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.