Frederik Schulz

Codex-native implementation harness agent for plan-driven execution with docs/plans tracking, MEMORY.md feedback, iterative verification, and resumable task loops.

Expert data visualization specialist for publication-quality figures, dashboards, and reproducible analysis notebooks.

Expert literature discovery and citation metadata agent for peer-reviewed papers, preprints, DOI lookup, and evidence-grounded search triage.

Expert computational biologist for omics workflows (QC, assembly, annotation, phylogenomics, MAG recovery, viral analysis, and JGI data access).

Expert scientific writer and editor for publication-quality manuscripts, revision strategy, peer review, and reproducible methods documentation.

Add "Open in molab" badge(s) linking to marimo notebooks. Works with READMEs, docs, websites, or any markdown/HTML target.

Browser automation via agent-browser CLI for web navigation, form filling, screenshots, scraping, login flows, and UI testing.

Critically review, score, compare, and rank one or more AI scientist outputs for biology, bioinformatics, computational life science, or adjacent research tasks. Trigger when the user asks to evaluate notebooks, code, figures, analyses, manuscripts, software, or final reports produced by AI scientists; compare multiple AI scientists on the same task; judge publication readiness; or audit rigor, reproducibility, novelty, and task completion. Do not use this skill to perform the original research task itself unless the user is explicitly asking for a reviewer-style audit of already produced outputs.

Generate anywidget components for marimo notebooks.

Search arXiv preprints through the official arXiv API and turn arXiv IDs into local Markdown summaries. Use when you need CS, math, physics, or quantitative biology preprints, especially recent submissions that may not yet appear in peer-reviewed literature indexes.

Create publication-quality matplotlib/seaborn charts with readable axes, tight layout, and curated palettes.

Functional annotation and taxonomy inference from sequence homology.

Assemble genomes/metagenomes and produce assembly QC artifacts.

Perform metagenomic binning, refinement, and QC with completeness/contamination checks.

Initialize a bioinformatics project scaffold with reproducible environments, schemas, and data cataloging. Use for new projects or repo setup.

Call genes and annotate basic features for prokaryotes, viruses, and eukaryotes.

Evaluate scientific rigor, methods, biases, and evidence quality for claims, papers, and study designs.

Build marker gene alignments and phylogenetic trees.

Design and scaffold bioinformatics pipelines using Prefect+Dask for local/distributed execution or Nextflow for HPC schedulers.

Cluster proteins into orthogroups and derive pangenome matrices.

Ingest, QC, and map reads with reproducible outputs. Use for raw read processing and coverage stats.

Search bioRxiv preprints through the official bioRxiv API and locally filter titles, abstracts, and authors for keyword queries. Use when you need recent biology preprints, bioRxiv-native metadata, date-range scans, DOI lookups, or author shortlists that may not yet appear in peer-reviewed literature indexes.

Aggregate results, train ML models, and produce reports with validated references.

Structure prediction and structure-based annotation.

Detect, classify, and QC viral contigs.

Generate reproducible Methods documentation from workflow run artifacts (Nextflow/Snakemake/CWL), including exact commands, versions, parameters, QC gates, and outputs.

Run a Codex-native planning and implementation loop with docs/plans progress tracking, MEMORY.md failure memory, per-task git worktrees, and iterative verification until tasks pass or need human intervention. Use when you want Mycelium-like orchestration for Codex without the Mycelium stack.

Query the Crossref REST API for DOI validation, title search, citation metadata, and bibliography audits. Use when you need DOI lookup, title-to-DOI matching, or reference metadata cleanup.

Fetch current API and SDK documentation with the chub CLI. Use when writing or reviewing code against fast-changing APIs, especially when the user asks for the latest or current docs.

Implement a research paper in a marimo notebook fully automatically without extra user input.

Queries JGI Lakehouse (Dremio) for genomics metadata from GOLD, IMG, Mycocosm, Phytozome. Downloads genome files from JGI filesystem using IMG taxon OIDs. Use when working with JGI data, GOLD projects, IMG annotations, or downloading genomes.

Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).

Run a multi-agent scientific manuscript review with parallel specialist reviewers, disagreement checks, and an editor meta-review. Use when reviewing a manuscript, preprint, revision, or rebuttal in Codex or Claude Code.

Write a marimo notebook in a Python file in the right format.

Create/refactor reproducible analysis notebooks with Marimo (preferred) or Jupyter (minimal support). Use for interactive, narrative-first analyses.

Build production-ready Plotly Dash dashboards with consistent theming, clear layouts, and performant callbacks.

Search the PMC Open Access literature with polars-dovmed. Author structured JSON queries directly, then use the hosted API when an API key is available or fall back to local dovmed scan over PMC, bioRxiv, or both parquet corpora.

Structured, decision-ready review framework for AI/ML, computational biology, and bioscience proposals. Use when evaluating grant, project, or funding proposals.

Assess paper and journal impact using OpenAlex citation counts, optional Altmetric data, and curated journal impact-factor references. Use when comparing papers, journals, or literature shortlists by reach and influence.

Draft, review, and iteratively revise scientific manuscripts with a provider-agnostic multi-agent workflow for Codex and Claude Code. Use for new manuscripts, section rewrites, rebuttals, response letters, or manuscript QA when claims must stay grounded in supplied artifacts.

Track and reconcile taxonomy updates across NCBI, GTDB, ICTV, and community eukaryote frameworks with versioned provenance.