{ "schemaVersion": 1, "generatedAt": "2026-08-26T17:42:15.484Z", "site": "https://heurekaskills.com", "source": { "repo": "heurekalabsco/heurekaskills", "ref": "main", "commit": "6bc57243f56e10da0507a49e08a5e90d4b3f3cd4" }, "count": 41, "skills": [ { "slug": "alphafold", "name": "alphafold", "description": "Retrieve predicted protein structures from the AlphaFold database by UniProt accession, and read their confidence metrics correctly — per-residue pLDDT, the PAE matrix for multi-domain proteins, and AlphaMissense variant annotations.", "category": "data", "version": "1.3.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "protein-structure", "alphafold", "uniprot", "plddt", "pae" ], "covers": [ "protein structure", "structure prediction", "alphafold", "uniprot", "plddt", "pae", "alphamissense", "missense variants", "variant effect", "cif", "pdb", "proteome", "human", "all organisms" ], "papers": [ "PMID:34265844", "PMID:34791371", "PMID:37733863" ], "access": [ "open" ], "updatedAt": "2026-08-19T12:35:21-04:00", "fileCount": 1, "checksum": "sha256:4e904447d193762372eb3bc771da62bf208f6e0bfeedddffbc730a932592e7b1", "signals": { "installs_total": 2, "installs_user": 2, "installs_agent": 0, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 2, "trending_rank": 2 }, "url": "https://heurekaskills.com/alphafold/", "manifest": "https://heurekaskills.com/alphafold/skill.json" }, { "slug": "anndata", "name": "anndata", "description": "Work with AnnData annotated matrices and .h5ad files — layers, obs/var metadata, sparse backing, on-disk access, and format conversion. The data-format layer under the single-cell ecosystem.", "category": "utility", "version": "1.3.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "h5ad", "single-cell", "data-format", "scverse" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 6, "checksum": "sha256:b9508d5efdf0220703db6131829f0a709732ea69e5f4310a85efcb3fafdd8901", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 1, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 7 }, "url": "https://heurekaskills.com/anndata/", "manifest": "https://heurekaskills.com/anndata/skill.json" }, { "slug": "autodock-vina", "name": "autodock-vina", "description": "Molecular docking with AutoDock Vina — receptor and ligand preparation, grid box definition, pose prediction and scoring. Use to predict how a small molecule binds a protein, to redock a known complex for validation, or to screen a compound set.", "category": "models", "version": "1.2.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "molecular-docking", "autodock", "vina", "structure-based", "virtual-screening" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 3, "checksum": "sha256:cad9e61049edd279d8d8b72b7589071104d0696f1c0414d9829fcca926686db5", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 8 }, "url": "https://heurekaskills.com/autodock-vina/", "manifest": "https://heurekaskills.com/autodock-vina/skill.json" }, { "slug": "biopython", "name": "biopython", "description": "Molecular biology toolkit with Biopython — sequence manipulation, FASTA/GenBank/PDB parsing, phylogenetics, BLAST automation, and programmatic NCBI/PubMed access via Bio.Entrez.", "category": "utility", "version": "1.3.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "sequences", "fasta", "genbank", "entrez", "blast" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 8, "checksum": "sha256:f74feac751bf7da4ccf18bf976b94684a49311e27033b799a50c7f144cbabf5d", "signals": { "installs_total": 1, "installs_user": 1, "installs_agent": 0, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 3 }, "url": "https://heurekaskills.com/biopython/", "manifest": "https://heurekaskills.com/biopython/skill.json" }, { "slug": "biostudies", "name": "biostudies", "description": "Search and retrieve studies from EBI BioStudies, the archive holding the ArrayExpress collection of functional-genomics submissions whose E-MTAB accessions mostly never reach GEO. Resolve an accession, traverse the nested section tree that carries title, organism and protocols, and download processed files and MAGE-TAB sample tables.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "arrayexpress", "rna-seq", "transcriptomics", "public-data", "microarray" ], "covers": [ "arrayexpress", "biostudies", "E-MTAB", "E-GEOD", "E-MEXP", "S-BIAD", "S-BSST", "EMPIAR", "rna-seq", "scRNA-seq", "single cell", "microarray", "functional genomics", "transcriptomics", "gene expression", "differential expression", "MAGE-TAB", "SDRF", "h5ad", "ENA", "fastq", "EMBL-EBI", "bioimages", "cryo-EM", "heart", "lymphatic endothelial cells", "human", "mouse", "cardiac inflammation", "EFO" ], "papers": [ "PMID:33211879", "PMID:42167442", "PMID:29069414", "PMID:26700850", "PMID:30357387", "PMID:25361974", "PMID:12519949", "PMID:17087822" ], "access": [ "open" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 1, "checksum": "sha256:e6c16c3ae742c4ad412c00f8b3f660d282013a2c4c47298eba656d77b078b440", "signals": null, "url": "https://heurekaskills.com/biostudies/", "manifest": "https://heurekaskills.com/biostudies/skill.json" }, { "slug": "bixbench", "name": "bixbench", "description": "Access BixBench, a dataset of 205 open-ended bioinformatics questions paired with 59 data capsules taken from published papers' analysis notebooks. Load the index, browse questions by category and source paper, and pull a capsule's real data onto disk. A benchmark by origin, and a browsable corpus of worked analysis cases in its own right.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "benchmark", "bioinformatics", "agents", "evaluation" ], "covers": [ "bixbench", "benchmark", "agent evaluation", "bioinformatics", "rna-seq", "genomics", "differential expression", "whole genome sequencing", "phylogenetics", "transcriptomics", "epigenomics", "imaging", "jupyter notebook", "capsule", "futurehouse", "analysis cases" ], "papers": [ "doi:10.48550/arXiv.2503.00096" ], "access": [ "open" ], "updatedAt": "2026-08-23T07:03:09-04:00", "fileCount": 1, "checksum": "sha256:97d21abe84589b379756561f360820e8c2bafdfab2ecdc3414233e35a0043a21", "signals": null, "url": "https://heurekaskills.com/bixbench/", "manifest": "https://heurekaskills.com/bixbench/skill.json" }, { "slug": "boltz2-nim", "name": "boltz2-nim", "description": "Predict biomolecular structure and binding affinity with Boltz2 NIM — protein, protein-ligand, DNA and RNA complexes from SMILES or CCD ligands, returning mmCIF and pIC50 scores, via the hosted NVIDIA API or local Docker.", "category": "models", "version": "1.4.0", "author": "NVIDIA BioNeMo Agent Toolkit (adapted by Heureka Labs)", "license": "CC-BY-4.0 AND Apache-2.0", "tags": [ "protein-structure", "binding-affinity", "nim", "nvidia", "boltz2" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 6, "checksum": "sha256:f51e49c5e5cdfbd16d021d370ceff1b2d268c6422ec64f363b3d5b508746c183", "signals": { "installs_total": 1, "installs_user": 1, "installs_agent": 0, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 4 }, "url": "https://heurekaskills.com/boltz2-nim/", "manifest": "https://heurekaskills.com/boltz2-nim/skill.json" }, { "slug": "cellprofiler", "name": "cellprofiler", "description": "Run CellProfiler pipelines headlessly and edit them as text — the -c -r invocation, LoadData CSVs that carry per-image metadata, batch groups, illumination correction before measurement, and joining the exported per-object tables back to the images they came from.", "category": "analysis", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "microscopy", "image-analysis", "segmentation", "cellprofiler", "cell-counting" ], "updatedAt": "2026-08-26T08:08:07-04:00", "fileCount": 1, "checksum": "sha256:6c8ca9ccba2086ff89c984a839d4364f4b7c4fe711e13f540bd4904ff4cefa7d", "signals": null, "url": "https://heurekaskills.com/cellprofiler/", "manifest": "https://heurekaskills.com/cellprofiler/skill.json" }, { "slug": "cellxgene-census", "name": "cellxgene-census", "description": "Query the CZ CELLxGENE Census for versioned public single-cell and spatial transcriptomics data — cell metadata, expression slices, summary counts, source H5AD downloads, and embeddings across organisms, tissues, diseases, and cell types.", "category": "data", "version": "1.1.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "single-cell", "atlas", "transcriptomics", "spatial", "public-data" ], "covers": [ "single-cell", "scRNA-seq", "spatial transcriptomics", "gene expression", "cell atlas", "cell type", "human", "mouse", "marmoset", "macaque", "chimpanzee", "brain", "blood", "kidney", "lung", "liver", "heart", "neuron", "T cell", "B cell", "macrophage", "COVID-19", "Alzheimer disease", "Visium", "Slide-seqV2", "Smart-seq2", "h5ad", "anndata", "embeddings", "TileDB-SOMA" ], "papers": [ "PMID:39607691" ], "access": [ "open" ], "updatedAt": "2026-08-19T13:07:29-04:00", "fileCount": 4, "checksum": "sha256:b772d5abbb7b4b1f330adc6ff3dbcbe752bddfa5ba51383dedcff1712ac2eafa", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 1, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 9 }, "url": "https://heurekaskills.com/cellxgene-census/", "manifest": "https://heurekaskills.com/cellxgene-census/skill.json" }, { "slug": "codex-phenocycler", "name": "codex-phenocycler", "description": "Take a CODEX or PhenoCycler image from pixels to a cell-by-marker table — choosing segmentation channels, running Cellpose over a multiplex stack, measuring per-cell intensity in micrometres, and building the AnnData that spatial analysis starts from. Includes the licence and token gates on the tools this workflow is usually built with.", "category": "analysis", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "microscopy", "multiplex-imaging", "segmentation", "spatial", "single-cell" ], "updatedAt": "2026-08-26T10:31:58-04:00", "fileCount": 1, "checksum": "sha256:b1745a8d413a2cef645f9aa3a04de082038e43374220926732d055f375b80720", "signals": null, "url": "https://heurekaskills.com/codex-phenocycler/", "manifest": "https://heurekaskills.com/codex-phenocycler/skill.json" }, { "slug": "datamol", "name": "datamol", "description": "Cheminformatics with datamol, a Pythonic layer over RDKit with sensible defaults — SMILES parsing and standardization, descriptors, fingerprints, clustering, 3D conformers, and parallel processing.", "category": "analysis", "version": "1.2.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "cheminformatics", "rdkit", "smiles", "descriptors", "fingerprints" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 9, "checksum": "sha256:47224784d6448dde1394c88ff4aaa004d6663dc6237c6d2a3d44fbc2c0f52972", "signals": null, "url": "https://heurekaskills.com/datamol/", "manifest": "https://heurekaskills.com/datamol/skill.json" }, { "slug": "dbgap", "name": "dbgap", "description": "Find controlled-access human cohorts in the dbGaP study catalogue by disease, cohort name or assay, and build a table on disk of accessions, versions, study design, subject counts, consent codes and their data use limitations, and the access policy. Delivers study metadata only — the individual-level genotypes and phenotypes stay behind an application this skill cannot make.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "dbgap", "controlled-access", "gwas", "human-genetics", "public-data" ], "covers": [ "dbgap", "phs accession", "controlled access", "data access committee", "consent groups", "GRU", "HMB", "data use limitation", "data use certification", "research use statement", "genotype", "phenotype", "gwas", "whole genome sequencing", "whole exome sequencing", "longitudinal cohort", "case-control", "aging", "InCHIANTI", "BLSA", "SardiNIA", "Framingham", "Million Veteran Program", "macular degeneration", "cataract", "Alzheimer disease", "frailty", "sarcopenia", "DNA methylation", "serum iron" ], "papers": [ "PMID:17898773", "PMID:24297256", "PMID:11129752", "PMID:19880490", "PMID:19303062", "PMID:10588299" ], "access": [ "open", "controlled" ], "updatedAt": "2026-08-19T12:44:09-04:00", "fileCount": 1, "checksum": "sha256:7cca9cadcbac64ac24e942ccab57df0e248e87fe4cdf65ce82c17afe17c5964c", "signals": null, "url": "https://heurekaskills.com/dbgap/", "manifest": "https://heurekaskills.com/dbgap/skill.json" }, { "slug": "diffdock-nim", "name": "diffdock-nim", "description": "Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets — blind ligand docking of SMILES or SDF inputs, returning ranked poses with confidence scores, hosted NVIDIA API or local Docker.", "category": "models", "version": "1.4.0", "author": "NVIDIA BioNeMo Agent Toolkit (adapted by Heureka Labs)", "license": "CC-BY-4.0 AND Apache-2.0", "tags": [ "molecular-docking", "binding-pose", "nim", "nvidia", "diffdock" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 6, "checksum": "sha256:1b1c6b5651f1504f74afa67ca2c7de463f7111938303eb9239c75ab7c84d76a3", "signals": null, "url": "https://heurekaskills.com/diffdock-nim/", "manifest": "https://heurekaskills.com/diffdock-nim/skill.json" }, { "slug": "esm", "name": "esm", "description": "Run EvolutionaryScale ESM protein language models — ESM3 sequence and structure generation, ESMC embeddings, inverse folding, and ESMFold2 structure prediction, locally or through the hosted Biohub API.", "category": "models", "version": "1.3.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "protein-language-model", "esm3", "esmc", "embeddings", "structure-prediction" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 6, "checksum": "sha256:ae41f9a892cca03aa24596334164ef07aa29bf8dd912327e045a7c575907db45", "signals": { "installs_total": 1, "installs_user": 1, "installs_agent": 0, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 5 }, "url": "https://heurekaskills.com/esm/", "manifest": "https://heurekaskills.com/esm/skill.json" }, { "slug": "experimental-design", "name": "experimental-design", "description": "Design a study before data is collected — pick a design, randomize, block and stratify, and lay out treatment combinations. Covers factorial and fractional-factorial DOE, crossover, split-plot, Latin squares, and plate layouts.", "category": "utility", "version": "1.2.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "doe", "randomization", "blocking", "factorial", "study-design" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 5, "checksum": "sha256:92225c3098da878c27b5826c4867ecd0dd572e2335f9988c4511e8622fba9c0d", "signals": null, "url": "https://heurekaskills.com/experimental-design/", "manifest": "https://heurekaskills.com/experimental-design/skill.json" }, { "slug": "gaudi", "name": "gaudi", "description": "Unsupervised multi-omics integration with GAUDI — two-stage UMAP, HDBSCAN clustering, and SHAP metagenes, in R or Python. Use when two or more omics layers share samples and you need sample clusters plus the features driving them.", "category": "analysis", "version": "1.2.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "multi-omics", "umap", "hdbscan", "clustering", "shap" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 4, "checksum": "sha256:d1b4f6f2ae79ca29b303656f6f5d365c82fbe3001165db744dcd4c800aef4362", "signals": { "installs_total": 3, "installs_user": 3, "installs_agent": 0, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 3, "trending_rank": 1 }, "url": "https://heurekaskills.com/gaudi/", "manifest": "https://heurekaskills.com/gaudi/skill.json" }, { "slug": "geo", "name": "geo", "description": "Find, triage and download public gene expression datasets from NCBI GEO — search series by tissue, disease, organism, assay and file type through E-utilities, read the esummary triage fields before transferring anything, then pull the counts matrices from all three places GEO keeps them — suppl/, the per-platform series matrix, and the per-sample directories.", "category": "data", "version": "1.2.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "geo", "rna-seq", "transcriptomics", "public-data", "entrez" ], "covers": [ "geo", "gse", "gsm", "gds", "gpl", "rna-seq", "microarray", "scRNA-seq", "spatial transcriptomics", "expression", "transcriptomics", "counts matrix", "series matrix", "superseries", "multi-platform", "soft", "aging", "senescence", "skeletal muscle", "liver", "brain", "heart", "kidney", "blood", "pbmc", "lung", "cancer", "human", "mouse", "e-utilities" ], "papers": [ "PMID:11752295", "PMID:23193258", "PMID:27008011", "PMID:17496320", "PMID:36516485", "PMID:31862890" ], "access": [ "open" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 1, "checksum": "sha256:ba3ac85f2a778639451793ff063facdd89a1601df1068c0298b70cf9448c0ca9", "signals": null, "url": "https://heurekaskills.com/geo/", "manifest": "https://heurekaskills.com/geo/skill.json" }, { "slug": "graphical-abstract", "name": "graphical-abstract", "description": "Turn a paper or results summary into an accurate, accessible graphical abstract as editable SVG — choose the figure type, compose it, then audit palette contrast, greyscale separation and colour-vision safety before submission.", "category": "communication", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "graphical-abstract", "figures", "accessibility", "svg", "publishing" ], "updatedAt": "2026-08-18T20:25:23-04:00", "fileCount": 4, "checksum": "sha256:fe4a3c4fb2a3c9a21f83bc770da467f22895e107fc54b32ad45c0fbcf2b1a5a1", "signals": null, "url": "https://heurekaskills.com/graphical-abstract/", "manifest": "https://heurekaskills.com/graphical-abstract/skill.json" }, { "slug": "gtex", "name": "gtex", "description": "Query GTEx human tissue expression and eQTLs through the GTEx Portal API — median TPM across 54 tissues including heart left ventricle, atrial appendage and skeletal muscle, per-sample values by donor age bracket, and significant cis-eQTLs by gene and tissue. Resolves gene symbols to the versioned GENCODE ids GTEx requires, and says which data is open and which is dbGaP-controlled.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "gtex", "transcriptomics", "eqtl", "rna-seq", "public-data" ], "covers": [ "heart", "left ventricle", "atrial appendage", "skeletal muscle", "brain cortex", "cerebellum", "liver", "lung", "whole blood", "skin", "thyroid", "testis", "pancreas", "kidney cortex", "adipose", "esophagus", "artery", "nerve", "eqtl", "egene", "sqtl", "gene expression", "median tpm", "transcriptomics", "bulk rna-seq", "human", "aging", "gencode", "dbgap", "genotype-tissue expression" ], "papers": [ "PMID:23715323", "PMID:25954001", "PMID:29022597", "PMID:32913098" ], "access": [ "open", "controlled" ], "updatedAt": "2026-08-19T12:39:37-04:00", "fileCount": 1, "checksum": "sha256:b01a02f81678ada61b19af472e4244847d50fbd9485904bbd0d5849faba2a447", "signals": null, "url": "https://heurekaskills.com/gtex/", "manifest": "https://heurekaskills.com/gtex/skill.json" }, { "slug": "journal-selection", "name": "journal-selection", "description": "Build a shortlist of candidate journals for a finished manuscript, grouped by the angle the author chooses to lead with — the subject framing and the methods framing are found separately, and each angle gets its own specialist and broad-scope options with the evidence behind them.", "category": "utility", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "publishing", "manuscript", "openalex", "bibliometrics" ], "covers": [ "journal selection", "where to submit", "target journal", "venue", "publishing", "scope match", "journal scope", "cover letter", "open access", "article processing charge", "apc", "impact", "citedness", "openalex", "bibliometrics", "manuscript submission" ], "updatedAt": "2026-08-24T12:13:45-04:00", "fileCount": 1, "checksum": "sha256:48e89764ede0cc86cda1be2260b020577d341d873c277431c5e611b4c863fb33", "signals": null, "url": "https://heurekaskills.com/journal-selection/", "manifest": "https://heurekaskills.com/journal-selection/skill.json" }, { "slug": "metabolights", "name": "metabolights", "description": "Find and retrieve public metabolomics studies from EMBL-EBI MetaboLights — search by disease, tissue or organism, read the ISA-Tab study design and factors, and download the Metabolite Assignment File holding identified metabolites and their per-sample intensities. Covers LC-MS, GC-MS and NMR studies across human, mouse and rat.", "category": "data", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "metabolomics", "mass-spectrometry", "nmr", "metabolites", "public-data" ], "covers": [ "metabolomics", "lipidomics", "mass spectrometry", "LC-MS", "GC-MS", "NMR", "metabolites", "metabolite profiling", "untargeted", "targeted", "serum", "plasma", "urine", "skeletal muscle", "liver", "sarcopenia", "aging", "diabetes", "cancer", "human", "mouse", "rat", "ISA-Tab", "MAF", "isotopologue" ], "papers": [ "PMID:31691833", "PMID:24214965" ], "access": [ "open" ], "platform": "isa-tab", "updatedAt": "2026-08-18T21:06:24-04:00", "fileCount": 1, "checksum": "sha256:29d4dca0fb774baeec9cb777838711d718452dea40b45ba8ac4c5cfc8f49218d", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 1, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 10 }, "url": "https://heurekaskills.com/metabolights/", "manifest": "https://heurekaskills.com/metabolights/skill.json" }, { "slug": "metabolomics-workbench", "name": "metabolomics-workbench", "description": "Find and retrieve public metabolomics and lipidomics studies from the NIH Metabolomics Workbench — study design, experimental factors, named metabolites and measured values over its path-segment REST API — plus the RefMet endpoints that map arbitrary metabolite names onto one nomenclature so two studies can be joined.", "category": "data", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "metabolomics", "lipidomics", "mass-spectrometry", "public-data", "multi-omics" ], "covers": [ "metabolomics", "lipidomics", "mass spectrometry", "nmr", "metabolites", "refmet", "metabolomics workbench", "mwtab", "gc-ms", "lc-ms", "ce-ms", "skeletal muscle", "plasma", "serum", "urine", "liver", "feces", "blood", "sarcopenia", "aging", "muscle atrophy", "cachexia", "diabetes", "cancer", "human", "mouse", "kegg", "hmdb", "lipid nomenclature", "untargeted metabolomics" ], "papers": [ "PMID:26467476", "PMID:33199890", "PMID:31320689", "PMID:29706851", "PMID:41590684" ], "access": [ "open" ], "updatedAt": "2026-08-17T10:28:39-04:00", "fileCount": 1, "checksum": "sha256:1cc3fedcfe01a2a5ad0636edda3182f5dbe6752748d12f41ccd1d291008b1289", "signals": null, "url": "https://heurekaskills.com/metabolomics-workbench/", "manifest": "https://heurekaskills.com/metabolomics-workbench/skill.json" }, { "slug": "microscopy-quantification", "name": "microscopy-quantification", "description": "Quantify fluorescence microscopy images — open acquisition formats with pixel size and channels intact, segment nuclei or cells, and export per-object area, shape, intensity and colocalization as a tidy CSV with QC overlays.", "category": "analysis", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "microscopy", "image-analysis", "segmentation", "cell-counting", "scikit-image" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 1, "checksum": "sha256:ea89810689afc1eae6213ec374d4c34d3834a43845e649cec511a90364253f55", "signals": null, "url": "https://heurekaskills.com/microscopy-quantification/", "manifest": "https://heurekaskills.com/microscopy-quantification/skill.json" }, { "slug": "motrpac", "name": "motrpac", "description": "Retrieve MoTrPAC multi-omics from the openly licensed R data package and public bucket instead of the account-gated Data Hub API — transcriptomics, proteomics, phosphoproteomics, acetylome, metabolomics, ATAC-seq and RRBS across twenty rat tissues including heart, skeletal muscle, liver and adipose, in endurance-trained animals. Young-adult 6-month cohort, not an aged one.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "multi-omics", "exercise", "rat", "transcriptomics", "public-data" ], "covers": [ "exercise", "endurance training", "treadmill", "multi-omics", "transcriptomics", "proteomics", "phosphoproteomics", "acetylome", "ubiquitylome", "metabolomics", "epigenomics", "atac-seq", "rrbs", "dna methylation", "immunoassay", "heart", "skeletal muscle", "gastrocnemius", "vastus lateralis", "liver", "white adipose", "brown adipose", "kidney", "lung", "hippocampus", "rat", "f344", "pass1b", "vo2max", "aging" ], "papers": [ "PMID:38693412", "PMID:32589957", "PMID:38701776", "PMID:38693320", "PMID:38984994", "doi:10.5281/zenodo.7877121" ], "access": [ "open" ], "platform": "motrpac", "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 1, "checksum": "sha256:d0b00db115b169cb1258b05b0ecff0bb15f64c15aee397952bc46a67054680f5", "signals": null, "url": "https://heurekaskills.com/motrpac/", "manifest": "https://heurekaskills.com/motrpac/skill.json" }, { "slug": "multiplex-imaging-io", "name": "multiplex-imaging-io", "description": "Open multiplex imaging files — Akoya QPTIFF from PhenoCycler and Vectra, CODEX multichannel TIFF, OME-TIFF, and folders of single-channel TIFFs — resolving channels by marker name rather than position, reading regions instead of whole slides, and recovering pixel size in micrometres from the file's own tags.", "category": "utility", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "microscopy", "multiplex-imaging", "file-io", "qptiff", "image-analysis" ], "updatedAt": "2026-08-26T07:53:55-04:00", "fileCount": 1, "checksum": "sha256:788cee63f60c4892cdd190f00a9cedf52fe2fa9310bd813a116d64020dba02ea", "signals": null, "url": "https://heurekaskills.com/multiplex-imaging-io/", "manifest": "https://heurekaskills.com/multiplex-imaging-io/skill.json" }, { "slug": "nih-dms-plan", "name": "nih-dms-plan", "description": "Draft an NIH Data Management and Sharing plan from a project's aims, in the 2026 structured format required for applications since May 2026 and for all awards from FY2027. Produces a clean plan plus a separate summary of what was proposed, inferred, and left for the PI. Covers repository choice, the word limits, the genomic data sharing elements, and the Just-in-Time and RPPR transition paths.", "category": "grants", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "nih", "grants", "data-sharing", "compliance" ], "covers": [ "dms plan", "data management and sharing", "data sharing plan", "nih", "grant application", "just-in-time", "rppr", "progress report", "genomic data sharing", "gds", "dbgap", "repository selection", "specific aims", "period of performance", "no-cost extension", "institutional certification", "scientific data", "controlled access", "human subjects" ], "access": [ "open" ], "updatedAt": "2026-08-19T09:39:59-04:00", "fileCount": 2, "checksum": "sha256:d90475eefd4388316b97bff87af04087c3ff0ffe27292e6bd5dc02bed26c7ef1", "signals": null, "url": "https://heurekaskills.com/nih-dms-plan/", "manifest": "https://heurekaskills.com/nih-dms-plan/skill.json" }, { "slug": "paperpush", "name": "paperpush", "description": "Fill a journal or preprint submission portal from a manuscript directory — choose a venue, generate its submission file, extract the field values from the paper, validate them, then hand a signed-in browser to the author for the final submit.", "category": "communication", "version": "1.2.0", "author": "Pachter Lab (adapted by Heureka Labs)", "license": "BSD-2-Clause", "tags": [ "manuscript", "preprint", "submission", "publishing" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 1, "checksum": "sha256:ac398666f44b30e50856571518055c83e5075ce5deb883d6836cdccb734524d6", "signals": null, "url": "https://heurekaskills.com/paperpush/", "manifest": "https://heurekaskills.com/paperpush/skill.json" }, { "slug": "pathway-cca-coessentiality", "name": "pathway-cca-coessentiality", "description": "Score pathway-pathway association by PCA to k components then first canonical correlation", "category": "analysis", "version": "1.3.0", "author": "Pol Castellano-Escuder", "license": "CC-BY-4.0", "tags": [ "cca", "pathway-coessentiality" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 1, "checksum": "sha256:0d63125a1421f42815209d14656e656602aa9128f39bcdf137d4f7030d13a285", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 11 }, "url": "https://heurekaskills.com/pathway-cca-coessentiality/", "manifest": "https://heurekaskills.com/pathway-cca-coessentiality/skill.json" }, { "slug": "pathway-enrichment", "name": "pathway-enrichment", "description": "Pathway and gene-set enrichment on a gene list or ranked table — over-representation (Enrichr, g:Profiler), preranked GSEA, and ssGSEA/GSVA against GO, KEGG, Reactome, and MSigDB, with background choice and FDR handled correctly.", "category": "analysis", "version": "1.2.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "gsea", "enrichment", "gene-ontology", "kegg", "reactome" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 4, "checksum": "sha256:b7b5251e83672c5b2993548e4b4a33073f4eee37b94eda9e3497700e2ce17693", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 1, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 12 }, "url": "https://heurekaskills.com/pathway-enrichment/", "manifest": "https://heurekaskills.com/pathway-enrichment/skill.json" }, { "slug": "polars-bio", "name": "polars-bio", "description": "Genomic interval operations and bioinformatics file I/O on Polars DataFrames — overlap, nearest, merge, coverage, complement, and subtract over BED/VCF/BAM/GFF/BigWig, plus streaming FastQC, with cloud-native paths.", "category": "utility", "version": "1.2.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "genomic-intervals", "bed", "vcf", "polars", "file-io" ], "updatedAt": "2026-08-26T08:41:36+00:00", "fileCount": 8, "checksum": "sha256:d2a639016455af951ca25a9d886143fd441135e5574cee81e1340d8bf07c6e22", "signals": null, "url": "https://heurekaskills.com/polars-bio/", "manifest": "https://heurekaskills.com/polars-bio/skill.json" }, { "slug": "pride", "name": "pride", "description": "Search the PRIDE Archive at EMBL-EBI for public mass-spectrometry proteomics datasets by keyword, organism, tissue, disease, instrument or software — read the free-text sample and data processing protocols, tell COMPLETE from PARTIAL submissions, and download raw, mzML, mzIdentML and search-engine output with checksums.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "proteomics", "mass-spectrometry", "pride", "public-data", "multi-omics" ], "covers": [ "proteomics", "proteome", "mass spectrometry", "phosphoproteomics", "lipidomics", "immunopeptidomics", "LC-MS/MS", "shotgun proteomics", "data-independent acquisition", "TMT", "SILAC", "label-free", "mzML", "mzIdentML", "mzTab", "Orbitrap", "timsTOF", "MaxQuant", "DIA-NN", "PXD", "ProteomeXchange", "liver", "heart", "blood plasma", "kidney", "brain", "human", "mouse", "hepatocellular carcinoma", "aging" ], "papers": [ "PMID:39494541", "PMID:34723319", "PMID:36370099", "PMID:20716697", "PMID:40915658" ], "access": [ "open" ], "updatedAt": "2026-08-19T12:47:41-04:00", "fileCount": 1, "checksum": "sha256:d2765673c751396e26b49c94d14705d6dd132cfcfd78cf665247f7c5492c9fe5", "signals": null, "url": "https://heurekaskills.com/pride/", "manifest": "https://heurekaskills.com/pride/skill.json" }, { "slug": "pydeseq2", "name": "pydeseq2", "description": "Differential gene expression for bulk RNA-seq with PyDESeq2 — formulaic designs, Wald tests, FDR correction, LFC shrinkage, and result visualization.", "category": "analysis", "version": "1.1.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "rna-seq", "differential-expression", "deseq2", "statistics" ], "updatedAt": "2026-08-24T08:30:49+00:00", "fileCount": 5, "checksum": "sha256:827033228daf52215d251103017c39da9db8249777ab499de2d273e572a46d28", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 1, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 13 }, "url": "https://heurekaskills.com/pydeseq2/", "manifest": "https://heurekaskills.com/pydeseq2/skill.json" }, { "slug": "reviewer-scouting", "name": "reviewer-scouting", "description": "Propose suggested reviewers for a manuscript submission, grouped so they cover every angle of the paper — find researchers who both publish on an angle and have recently published in the target journal, screen them against the author list for conflicts, and recover each one's published email address.", "category": "utility", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "publishing", "peer-review", "openalex", "bibliometrics" ], "covers": [ "suggested reviewers", "reviewer selection", "peer review", "referee", "conflict of interest", "coi", "cover letter", "manuscript submission", "editorial", "expertise matching", "coauthor screen", "openalex", "bibliometrics" ], "updatedAt": "2026-08-25T08:29:16-04:00", "fileCount": 1, "checksum": "sha256:d74514ae0d68d38a72eb5387403a9c90d30ec010e5889a393bc4fcb85f11061d", "signals": null, "url": "https://heurekaskills.com/reviewer-scouting/", "manifest": "https://heurekaskills.com/reviewer-scouting/skill.json" }, { "slug": "sam2", "name": "sam2", "description": "Segment and track objects with Meta's SAM 2.1 — point, box and mask prompts on a single image, automatic mask generation over a whole field, and propagation of a segmentation through a time-lapse. Covers where a natural-image model misreads microscopy, and what to check before trusting a count.", "category": "models", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "segmentation", "image-analysis", "microscopy", "sam2", "time-lapse" ], "updatedAt": "2026-08-26T10:13:27-04:00", "fileCount": 1, "checksum": "sha256:c0cccb0b3e8bdbf3c6d6bdb804c1f8af991b963b6b013c71759c63ee8fda4db4", "signals": null, "url": "https://heurekaskills.com/sam2/", "manifest": "https://heurekaskills.com/sam2/skill.json" }, { "slug": "scientific-critical-thinking", "name": "scientific-critical-thinking", "description": "Evaluate scientific claims and evidence quality — assess experimental design validity, identify bias and confounding, and apply grading frameworks such as GRADE and Cochrane Risk of Bias.", "category": "utility", "version": "1.1.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "evidence-appraisal", "bias", "confounding", "grade", "study-validity" ], "updatedAt": "2026-08-17T08:32:12+00:00", "fileCount": 8, "checksum": "sha256:344e854656d3eb23a89e0ee725963a8db0265d8115713ba88ecbbab897a7b9cb", "signals": null, "url": "https://heurekaskills.com/scientific-critical-thinking/", "manifest": "https://heurekaskills.com/scientific-critical-thinking/skill.json" }, { "slug": "scikit-bio", "name": "scikit-bio", "description": "Biological data analysis with scikit-bio — sequence handling, alignments, phylogenetic trees, alpha and beta diversity including UniFrac, ordination (PCoA), and PERMANOVA. Built for microbiome work.", "category": "analysis", "version": "1.2.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "microbiome", "diversity", "unifrac", "ordination", "permanova" ], "updatedAt": "2026-08-25T08:31:57+00:00", "fileCount": 2, "checksum": "sha256:b4dfaf954a91f2f78f1519d8915d0e5ae8dc3e83e324cb59c30780834b9c41b4", "signals": { "installs_total": 1, "installs_user": 1, "installs_agent": 0, "installs_7d": 0, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 6 }, "url": "https://heurekaskills.com/scikit-bio/", "manifest": "https://heurekaskills.com/scikit-bio/skill.json" }, { "slug": "scvi-tools", "name": "scvi-tools", "description": "Deep generative models for single-cell omics with scvi-tools — probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, and multi-modal integration (totalVI, MultiVI).", "category": "models", "version": "1.3.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "single-cell", "batch-correction", "generative-models", "scvi", "multimodal" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 9, "checksum": "sha256:dddfdf98c87c9cc24e3bb405cdd4ea5c49bc4da4fb1c1c39644247c31d70e100", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 1, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 14 }, "url": "https://heurekaskills.com/scvi-tools/", "manifest": "https://heurekaskills.com/scvi-tools/skill.json" }, { "slug": "spatial-phenotyping", "name": "spatial-phenotyping", "description": "Spatial statistics on a segmented multiplex dataset — a cell-by-marker AnnData with coordinates, from CODEX, MxIF, IMC or MIBI. Phenotyping, neighborhood enrichment, cellular neighborhoods, Ripley's L and co-occurrence, with the per-slide graph construction and per-patient aggregation that keep the statistics honest.", "category": "analysis", "version": "1.0.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "spatial", "single-cell", "multiplex-imaging", "h5ad", "statistics" ], "updatedAt": "2026-08-26T10:13:27-04:00", "fileCount": 1, "checksum": "sha256:5806b4e586501256c310a8f8c64a70ebd9e107e700e2d36aa730aca8eb238c77", "signals": null, "url": "https://heurekaskills.com/spatial-phenotyping/", "manifest": "https://heurekaskills.com/spatial-phenotyping/skill.json" }, { "slug": "statistical-power", "name": "statistical-power", "description": "Sample-size and power calculations for planning a study — a priori power, minimum detectable effect, and power curves. Closed-form for t-tests, ANOVA, proportions, correlation, and regression; Monte Carlo simulation for the rest.", "category": "utility", "version": "1.2.0", "author": "K-Dense Inc. (adapted by Heureka Labs)", "license": "MIT", "tags": [ "power-analysis", "sample-size", "effect-size", "study-planning" ], "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 4, "checksum": "sha256:3a18c98d2d219ea19f488c4d78e340113a4a6a3b6178ceb3932f218b885314df", "signals": { "installs_total": 1, "installs_user": 0, "installs_agent": 1, "installs_7d": 1, "installs_user_7d": 0, "installs_30d": 1, "trending_rank": 15 }, "url": "https://heurekaskills.com/statistical-power/", "manifest": "https://heurekaskills.com/statistical-power/skill.json" }, { "slug": "synapse", "name": "synapse", "description": "Find and retrieve consortium datasets from Synapse (Sage Bionetworks) — resolve a syn id to entity metadata and annotations, walk a project's folders, and read an entity's access tier before attempting a download. Covers AMP-AD, the AD Knowledge Portal, PsychENCODE and HTAN. Most Synapse files need a free account; some need an approved data use certificate.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "synapse", "public-data", "controlled-access", "alzheimers", "consortium-data" ], "covers": [ "synapse", "sage bionetworks", "syn id", "amp-ad", "ad knowledge portal", "agora", "alzheimers", "dementia", "neurodegeneration", "aging", "rosmap", "mount sinai brain bank", "mayo rnaseq", "psychencode", "htan", "dorsolateral prefrontal cortex", "superior temporal gyrus", "hippocampus", "cerebellum", "amygdala", "plasma proteomics", "brain proteomics", "tmt", "rna-seq", "methylation", "metabolomics", "gwas", "human", "mouse", "data use certificate" ], "papers": [ "PMID:24071850", "PMID:26853544", "PMID:33085189", "PMID:30084846", "PMID:29865057", "PMID:30204156", "PMID:27727239", "PMID:35115731", "PMID:32302568" ], "access": [ "open", "registered", "controlled" ], "platform": "synapse", "updatedAt": "2026-08-26T11:33:25-04:00", "fileCount": 1, "checksum": "sha256:138733f67159f97dbfeca9320e5337138665eb32a130496546165fe5b35f2867", "signals": null, "url": "https://heurekaskills.com/synapse/", "manifest": "https://heurekaskills.com/synapse/skill.json" }, { "slug": "uk-biobank", "name": "uk-biobank", "description": "Search UK Biobank's openly published field catalogue — 11,821 variables in 410 categories with participant counts, units, the instanced/arrayed shape that decides how many columns a field becomes, and the 172 retired fields the website hides but the download still carries — and report what an access application requires, applications being paused as of August 2026. Never fetches participant data.", "category": "data", "version": "1.1.0", "author": "Heureka Labs", "license": "CC-BY-4.0", "tags": [ "uk-biobank", "cohort", "epidemiology", "controlled-access", "public-data" ], "covers": [ "uk biobank", "biobank", "cohort", "nmr metabolomics", "plasma proteomics", "olink", "ukb-ppp", "gwas", "imaging", "brain mri", "cardiac mri", "abdominal mri", "liver fat", "dxa", "accelerometer", "spirometry", "blood biochemistry", "whole exome sequencing", "whole genome sequencing", "polygenic risk score", "icd10", "hospital inpatient records", "cancer registry", "death registry", "type 2 diabetes", "dementia", "coronary artery disease", "breast cancer", "aging", "data dictionary" ], "papers": [ "PMID:25826379", "PMID:30305743", "PMID:32457287", "PMID:34662886", "PMID:36737450", "PMID:37794186", "PMID:38057571" ], "access": [ "open", "controlled" ], "updatedAt": "2026-08-19T12:37:38-04:00", "fileCount": 1, "checksum": "sha256:d0187c4b44980211a4972f0a04d26285ba4b0d44a5e5dd66c117a447895a87ac", "signals": null, "url": "https://heurekaskills.com/uk-biobank/", "manifest": "https://heurekaskills.com/uk-biobank/skill.json" } ] }