mims-harvard/tooluniverse-stem-cell-organoid
skills/tooluniverse-stem-cell-organoid/SKILL.md
Stem cell, iPSC, and organoid research — pluripotency markers, differentiation protocol pathways, lineage commitment factors, organoid model selection. Use for iPSC characterization, differentiation protocol design via developmental-pathway recapitulation, and organoid-model selection for disease modeling.
$ install --global
skillsauthnpx skillsauth add mims-harvard/tooluniverse tooluniverse-stem-cell-organoidInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 27, 2026, 7:05 AM195.9s1 file scanned
SKILL.md
- name:
- tooluniverse-stem-cell-organoid
- description:
- Stem cell, iPSC, and organoid research — pluripotency markers, differentiation protocol pathways, lineage commitment factors, organoid model selection. Use for iPSC characterization, differentiation protocol design via developmental-pathway recapitulation, and organoid-model selection for disease modeling.
- disable-model-invocation:
- true
Stem Cell & Organoid Research
Pipeline for investigating stem cell biology, iPSC characterization, organoid models, and cell differentiation using ToolUniverse tools.
Reasoning Strategy
Stem cell differentiation follows developmental biology — to make any target cell type from iPSCs, the protocol must mimic the embryonic signaling pathway that generates that cell type in vivo. For neural induction: inhibit BMP and TGF-beta (dual SMAD inhibition). For cardiomyocytes: activate WNT then inhibit WNT. For pancreatic beta cells: activate Activin/Nodal → FGF → Notch inhibition → BMP in sequence. The order and timing of growth factors matters critically — adding BMP4 during neural induction will redirect cells toward mesoderm. Mouse and human stem cells differ in their signaling requirements (LIF/STAT3 for mouse naive pluripotency; FGF/ERK for human primed pluripotency), so protocols are not interchangeable. Organoids recapitulate some but not all organ features — always assess maturation state (fetal vs. adult gene expression) before drawing disease-relevance conclusions.
LOOK UP DON'T GUESS: Do not assume which markers define a target cell type or which signaling pathway drives differentiation — query CellMarker_search_by_cell_type for markers and kegg_search_pathway for the relevant pathway. Do not assume organoid fidelity; look up published CellxGene or HCA atlas data for comparison.
Key principles:
- Marker-based identity — stem cell identity is defined by marker expression profiles (OCT4, SOX2, NANOG for pluripotency)
- Differentiation is a trajectory — not a binary state; analyze intermediate progenitor stages
- Organoid ≠ organ — organoids recapitulate some but not all organ features; always note limitations
- Species matters — mouse and human stem cells differ in signaling requirements
- Evidence grading — T1: validated in clinical iPSC study, T2: functional assay (teratoma, engraftment), T3: marker expression only, T4: computational prediction
Core Tools
| Tool | Use For |
|------|---------|
| CELLxGENE_get_census_versions | Discover CELLxGENE Census release versions; then use CELLxGENE_get_cell_metadata / CELLxGENE_get_expression_data for specific cells / genes. Requires cellxgene-census package (pip install cellxgene-census). May not be installed by default. |
| CellMarker_search_by_cell_type | Cell type marker genes. Requires operation="search_by_cell_type", cell_name= (NOT cell_type=) |
| CellMarker_search_by_gene | Which cell types express a gene. Requires operation="search_by_gene", gene_symbol= |
| hca_search_projects | Human Cell Atlas organoid/development projects |
| GEO_search_rnaseq_datasets | Find stem cell RNA-seq datasets |
| kegg_search_pathway | Differentiation signaling pathways (WNT, Notch, Hedgehog) |
| ReactomeAnalysis_pathway_enrichment | Pathway analysis of stem cell gene sets |
| STRING_get_network | Pluripotency/differentiation gene networks |
| OpenTargets_get_associated_targets_by_disease_efoId | Disease genes for organoid disease modeling |
| PubMed_search_articles | Stem cell and organoid literature |
| search_clinical_trials | iPSC-based clinical trials |
Workflow
Phase 0: Define the Question
Pluripotency? Differentiation? Disease modeling? Drug screening?
|
Phase 1: Cell Identity & Markers
CellMarker → pluripotency/lineage markers → verify identity
|
Phase 2: Differentiation Pathways
KEGG/Reactome → WNT, Notch, BMP, FGF signaling
|
Phase 3: Atlas & Dataset Discovery
CellxGene/HCA → reference datasets for target cell type
|
Phase 4: Disease Modeling (if applicable)
OpenTargets → disease genes → organoid recapitulation assessment
|
Phase 5: Report
Evidence-graded findings with clinical translation potential
Phase 1: Cell Identity & Markers
Pluripotency markers (must be co-expressed): OCT4 (POU5F1), SOX2, NANOG (essential); SSEA-4, TRA-1-60 (human surface markers). KLF4 and MYC are Yamanaka factors but also expressed in somatic cells — do not rely on them alone. Use CellMarker_search_by_cell_type to retrieve the full validated marker set for any target cell type.
Lineage markers: Ectoderm → PAX6/SOX1 (early), MAP2/TUBB3 (neurons); Mesoderm → TBXT/MIXL1 (early), CD34 (blood); Endoderm → SOX17/FOXA2 (early), PDX1/NKX6.1 (pancreas). Retrieve current marker lists from CellMarker rather than relying on memory.
Phase 2: Differentiation Pathways
Key signaling pathways for directed differentiation:
| Pathway | KEGG ID | Role in Stem Cells | Common Modulators | |---------|---------|-------------------|-------------------| | WNT signaling | hsa04310 | Pluripotency maintenance (canonical) vs differentiation (non-canonical) | CHIR99021 (activator), IWP-2 (inhibitor) | | Notch signaling | hsa04330 | Lateral inhibition, fate decisions | DAPT (gamma-secretase inhibitor) | | BMP/TGF-beta | hsa04350 | Mesoderm/trophectoderm induction | BMP4 (activator), Noggin (inhibitor) | | FGF signaling | hsa04010 | Self-renewal, neural induction | bFGF (activator), SU5402 (inhibitor) | | Hedgehog | hsa04340 | Patterning, organoid maturation | SAG (activator), cyclopamine (inhibitor) | | Hippo/YAP | hsa04390 | Mechanotransduction, organoid size | Verteporfin (YAP inhibitor) |
Phase 3: Atlas & Dataset Discovery
# Find stem cell single-cell datasets
CELLxGENE_get_census_versions() # discover available Census releases, then use CELLxGENE_get_cell_metadata / CELLxGENE_get_expression_data
hca_search_projects(query="organoid")
GEO_search_rnaseq_datasets(query="iPSC differentiation neural", organism="Homo sapiens")
Phase 4: Organoid Model Assessment
Organoid fidelity scoring — how well does the organoid recapitulate the organ?
| Feature | High Fidelity (3) | Moderate (2) | Low (1) | |---------|------------------|-------------|---------| | Cell type diversity | All major cell types present | Most cell types, missing rare ones | Only 1-2 cell types | | Architecture | Self-organized, correct spatial arrangement | Partial organization | Disorganized aggregate | | Function | Measurable organ function (secretion, contraction, electrophysiology) | Some functional markers | Marker expression only | | Maturation | Adult-like gene expression profile | Fetal-like | ESC-like (failed differentiation) | | Disease relevance | Recapitulates patient phenotype | Some disease features | No disease phenotype |
Evidence Grading
| Grade | Criteria | Example | |-------|---------|---------| | T1 | Clinical iPSC study or approved therapy | iPSC-derived RPE for macular degeneration (Mandai 2017) | | T2 | Functional validation (teratoma, engraftment, drug response) | Organoid drug screening with patient-specific response | | T3 | Marker expression + morphology | iPSC colony expressing OCT4/SOX2/NANOG | | T4 | Computational prediction or single-marker evidence | Predicted pluripotent by gene expression classifier |
Synthesis Questions
- Is the cell identity verified? (co-expression of 3+ pluripotency markers, or lineage-appropriate markers)
- Is the differentiation protocol reproducible? (published, peer-reviewed, with quantified efficiency)
- Does the organoid model the disease? (patient-derived iPSC shows disease phenotype in organoid)
- What are the translational barriers? (scalability, maturation, immune compatibility, tumorigenicity)
- What's the best reference dataset? (CellxGene atlas for comparison)
Limitations
- No organoid protocol database — protocols are scattered across publications; use PubMed search
- Maturation gap — most organoids resemble fetal, not adult tissue; always note maturation state
- Batch variability — iPSC-derived cells vary between passages and donor lines
- No direct culture tools — this skill analyzes published data and designs experiments; it does not control bioreactors
- Species differences — mouse ESCs require LIF; human ESCs require bFGF. Don't mix protocols
Related Skills
mims-harvard/tooluniverse-product-safety-surveillance
tools
VerifiedTrustedCommunity
Post-market safety surveillance and recall/adverse-event RETRIEVAL across the full spectrum of FDA-regulated products that are NOT covered by the drug-AE signal skills: medical devices, food / dietary supplements / cosmetics, veterinary drugs, and drug supply (shortages). Orchestrates openFDA endpoints (MAUDE device adverse events + device recalls + 510(k), CAERS food/supplement/ cosmetic adverse events, veterinary adverse events, drug shortages, and cross-product enforcement/recall reports). USE WHEN the user asks: "are there adverse events for [device / pacemaker / infusion pump / insulin pump]", "device recalls for [firm/product]", "supplement / vitamin / cosmetic adverse reactions", "is [drug] in shortage", "what injectables are on shortage", "veterinary / animal adverse events for [drug] in [dog/cat/horse]", "food recall for listeria", "MAUDE report for [device]", "CAERS reactions for [brand]". DO NOT USE for drug adverse-event SIGNAL detection or disproportionality (PRR / ROR / IC) or drug-AE association scoring — that is `tooluniverse-pharmacovigilance` / `tooluniverse-adverse-event-detection`. This skill is multi-product surveillance and retrieval, not drug-AE statistical signal mining.
1,446SKILL.mdUpdated Jun 13, 2026
mims-harvard/skills/tooluniverse-phewas
tools
VerifiedTrustedCommunity
--- name: tooluniverse-phewas description: Cross-ancestry / cross-biobank phenome-wide association (PheWAS) and replication. Given ONE variant (rsID) or ONE gene, look up every phenotype it associates with across European/UK (UKB-TOPMed), Finnish (FinnGen), Japanese (BioBank Japan), and Taiwanese (TPMI) biobanks, plus exome-wide gene-burden PheWAS (Genebass), then judge whether an association replicates across ancestries or is population-specific. Use whenever the user asks "what else is this va
1,446SKILL.mdUpdated Jun 13, 2026
mims-harvard/tooluniverse-natural-product-dereplication
tools
VerifiedTrustedCommunity
Dereplicate a putative natural product and assign its chemical taxonomy. Use to answer "is [compound] a known natural product", "what microbe/organism produces [compound]", "what chemical class is [compound]", "dereplicate this metabolite (by formula/exact mass/InChIKey/SMILES)", or "classify this molecule into ChemOnt". Searches NPAtlas for known microbial natural products (producing organism + literature reference), assigns the ChemOnt kingdom→superclass→class→subclass hierarchy via ClassyFire, resolves systematic IUPAC names to structure via OPSIN, and cross-references identity in PubChem. NOT for general drug/compound identity or ADMET (use tooluniverse-chemical-compound-retrieval / tooluniverse-small-molecule-discovery) and NOT for metabolomics pathway/enrichment analysis (use tooluniverse-metabolomics skills).
1,446SKILL.mdUpdated Jun 13, 2026
mims-harvard/tooluniverse-microbial-genome-characterization
tools
VerifiedTrustedCommunity
Genome-ASSEMBLY discovery, QC, and replicon mapping for any organism (bacteria, archaea, fungi, and beyond) using NCBI Datasets. Resolves an organism name or taxid to assemblies, picks the reference/representative or best-quality assembly, pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%, assembly level, RefSeq category), enumerates chromosomes and plasmids via per-replicon sequence reports, and compares candidate assemblies on quality. Use for "what genomes are available for [organism]", "assembly stats / N50 / GC content for [GCF_/GCA_ accession]", "how many plasmids does [strain] have", "compare assemblies for [species]", "find the reference genome for [taxon]", "is this assembly Complete Genome or just contigs". NOT for gene-level orthology/synteny (use tooluniverse-comparative-genomics), plant gene structure (use tooluniverse-plant-genomics), de novo assembly from raw reads (no tool exists), or taxonomy-only name/lineage lookups.
1,446SKILL.mdUpdated Jun 13, 2026