Menu
Skills in this repository
SkillsMP has collected 420 skills from eightmm/codex-science. Open a skill to review its source and details.
eightmm/codex-scienceShowing 40 of 420 collected skills.
Synthesize population, clinical, functional, regulatory, expression, and cohort evidence for a genomic variant. Use for research interpretation of rsIDs or genomic alleles, not patient-specific diagnosis or treatment.
Inspect and use the local computer as a reproducible scientific workbench across shell, Python, R, Julia, Jupyter, containers, CPUs, and GPUs. Use when a scientific task needs local files, code execution, package or environment setup, data conversion,…
Run reproducible scientific workloads through an existing SSH host, Slurm/HPC cluster, cloud GPU provider, or remote object storage. Use for remote execution, job submission and monitoring, checkpointed long runs, GPU allocation, data staging, result…
Retrieve an AlphaFold predicted structure from the AlphaFold Database for a given UniProt accession and analyze its confidence (pLDDT), intrinsically disordered regions, and rigid domain boundaries (PAE). Use when the user has a UniProt ID and wants…
Analyze how a single non-coding genetic variant affects gene expression, chromatin accessibility, histone marks, transcription factors, and splicing using the AlphaGenome API. Use when the user gives a variant in chr:pos:ref/alt form and asks about regulatory…
Search arXiv preprints for a topic, author, or concept and triage the results. Use when the user wants recent primary literature, preprints, or methods papers in physics, math, CS, quantitative biology, or statistics. Uses the plugin's built-in read-only…
Fetch bioRxiv and medRxiv preprint metadata by DOI, or browse a narrow date range with a category, for life-science and medical preprints. Use when you already have a DOI or an approximate date plus category — not for open-ended keyword discovery. Public API,…
Predict 3D biomolecular structures and binding affinity with the open-source Boltz model — proteins, complexes, nucleic acids, and protein-ligand systems from sequence. Use when the user wants a predicted structure or affinity from sequence (not an…
Query the ChEMBL database for bioactive molecules, drug targets, bioactivity measurements (IC50/Ki/EC50), approved drugs, and mechanisms. Use when the user asks about compounds, targets, potency values, or drug mechanisms. Public REST API, no credential…
Search ClinicalTrials.gov (API v2) for trials by condition, intervention, status, phase, location, or sponsor; fetch a trial by NCT ID; check eligibility; and count trials. Use for trial discovery, pipeline/portfolio analysis, or patient-matching context.…
Look up clinical significance and pathogenicity classifications (Pathogenic, Benign, VUS) and supporting evidence for human genomic variants in NCBI ClinVar. Use for variant clinical interpretation or benchmark controls. Public NCBI API, no credential needed.
Look up and map short human variants (SNPs, indels) in NCBI dbSNP: resolve between rsIDs, GRCh38 coordinates, and HGVS, and get variant type, gene, clinical significance, and allele frequencies. Public NCBI API, no credential needed.
Query the ENCODE Registry of candidate cis-Regulatory Elements (cCREs) via the SCREEN GraphQL API, and ENCODE experiments/files via the ENCODE Portal REST API, across human cell types. Public APIs, no credential needed.
Resolve gene/transcript/protein IDs, fetch genomic or protein sequences, retrieve gene structure (exons), and predict variant consequences (VEP) via the Ensembl REST API. Use as an ID translator, sequence source, and variant-effect tool. Public API, no…
Search Europe PMC for life-science literature and retrieve abstracts, citations, and open-access full text (XML/plain text) by PMCID. Use when the user wants broad biomedical literature discovery or open-access full text. Public API, no credential needed.
Find structurally similar proteins by submitting a 3D coordinate file (.pdb, .cif, or .mmcif) to the Foldseek web API and search databases such as PDB, AlphaFold, CATH, and MGnify. Use ONLY when the user provides a physical structure file and wants structural…
Query gnomAD for variant allele frequency/rarity, gene constraint metrics (pLI, LOEUF), variants in a region or gene, and structural variants. Use to assess variant rarity or loss-of-function intolerance. Not for individual patient genomes or somatic cancer…
Retrieve quantitative RNA expression and variant eQTL data from GTEx across 54 non-diseased tissue sites. Use for tissue expression profiles or eQTL lookups. Public API, no credential needed.
Retrieve protein expression levels and spatial/subcellular localisation from the Human Protein Atlas (HPA). Use for tissue/cell expression and localisation of a human protein. Public API, no credential needed.
Identify protein domains, families, and sites; find proteins sharing a domain/family; explore species distribution; and get domain architectures via InterPro (integrating Pfam, CDD, and more). Public API, no credential needed.
Retrieve transcription-factor binding profiles (PFMs/PWMs) from JASPAR, resolve gene symbols to JASPAR matrix IDs, and get TF metadata in multiple formats (MEME, TRANSFAC, PFM, JASPAR). Public API, no credential needed.
Retrieve protein and nucleotide sequences from NCBI via E-utilities: by accession, CDS translation, gene+organism search, locus lookup, PubMed-linked sequences, or patent proteins. Use to fetch biological sequences. Public NCBI API, no credential needed.
Search EMBL-EBI Ontology Lookup Service (OLS) for biomedical ontology terms, definitions, and hierarchies across 250+ ontologies (GO, DOID, HP, UBERON, CL). Use for term search, term details, or navigating parents/children/ancestors. Public API, no credential…
Query the OpenAlex scholarly graph for works, authors, institutions, sources, topics, and funders; resolve DOIs; and aggregate bibliometrics (citation counts, works). Use for academic discovery, author/institution lookup, or bibliometric summaries across all…
Query the openFDA API for drugs, devices, foods, and more: adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, and NDC lookups. Use for FDA safety/regulatory data. Public API, no credential needed.
Query the Open Targets Platform for target-disease associations, tractability/safety, genetic/omics evidence, and known drugs, for therapeutic target identification. Public GraphQL API, no credential needed.
Search and retrieve experimentally-determined 3D biomolecular structures from the RCSB Protein Data Bank by sequence, structure, ligand, or attribute, and fetch entry metadata or coordinate files. Use when the user wants experimental structures (X-ray,…
Restore, attribute, date, and contextualize ancient inscriptions with DeepMind's Aeneas (Latin) and Ithaca (Ancient Greek) models. Use for epigraphic text restoration, geographic attribution, or dating of ancient texts.
Align multiple protein sequences with EBI Clustal Omega to assess similarity and residue/domain conservation (up to 4000 sequences, 4 MB). Not for homolog search, non-protein sequences, structural alignment, or a single sequence. Public EBI API, no credential…
Find homologous protein sequences with MMseqs2 (fast, default) or BLAST (comprehensive fallback) from a sequence or FASTA. Use to find sequence homologs or infer function by sequence similarity — not by structural similarity. Public APIs, no credential needed.
Query PubChem by name, CID, or SMILES; retrieve properties; run similarity/substructure searches; and get bioactivity. Use for cheminformatics on a specific chemical, drug, or molecule. Public PUG-REST API, no credential needed.
Search PubMed biomedical literature for a topic, gene, drug, disease, or clinical question and retrieve article details. Use when the user wants peer-reviewed biomedical or clinical references. Uses the plugin's built-in read-only PubMed MCP tool for…
Visualize, analyze, and render protein/molecular structures with PyMOL: images, structural alignment/superposition, distance/contact measurement, binding-site highlighting, and coloring by B-factor/pLDDT. Not for docking, MD, or sequence-only analysis. Local…
Query QuickGO and the Evidence & Conclusion Ontology (ECO): map genes to GO biological processes, molecular functions, and cellular components; find genes for a GO term; and explore the GO hierarchy. Public API, no credential needed.
Query Reactome Content and Analysis Services: pathway enrichment of a gene list, identifier mapping, reaction participants, pathway hierarchy, and knowledgebase search. Use for pathway analysis and enrichment. Public API, no credential needed.
Query STRING for protein-protein interactions, interaction confidence/evidence, interaction partners, and functional enrichment. Use for PPI networks and enrichment of a protein set. Public API, no credential needed.
Fetch evolutionary conservation scores (phyloP, phastCons) and transcription-factor binding sites (ENCODE, JASPAR, ReMap) from the UCSC Genome Browser. Use to assess whether variants/regions are conserved or TF-bound. Public API, no credential needed.
Query UniBind for experimentally validated transcription-factor binding sites: retrieve TF-DNA datasets, download binding-site coordinates (BED/FASTA), and list datasets by species, cell line, or TF. Public API, no credential needed.
Search UniProtKB for proteins by name, gene, organism, or keyword and retrieve accessions plus functional annotation. Use when the user wants protein metadata, function, sequence, or identifier mapping. Uses the plugin's built-in read-only UniProt MCP tool…
Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.