Tooluniverse

GitHub workflow for ToolUniverse - push code safely by moving temp files, activating pre-commit hooks, running tests, and cleaning staged files. Use when pushing to GitHub, fixing CI failures, or cleaning up before commits.

ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}'` to extract its cell outputs and apply EVERY filter/sample-exclusion the notebook used — even when the question says 'Using DESeq2/Run X/Compute Y' (this describes the METHOD the notebook used, not a request to rerun). The notebook's cell outputs are the only published authoritative answers; reimplementing or reading stale pre-computed CSVs in the data folder produces different numbers because of outlier-sample removal, library version, and filter steps you don't see by skimming. STEP 2 routing — pick a sub-skill name from this exact list (never invent): tooluniverse-rnaseq-deseq2 (RNA/miRNA-seq DE, correlation, PCA, clustering, dispersion), tooluniverse-gene-enrichment (GO/KEGG/Reactome/GSEA/pathway enrichment), tooluniverse-statistical-modeling (regression, ANOVA, ordinal/logistic, chi-square, correlation, power), toolunive

Fix failing ToolUniverse tools by diagnosing test failures, identifying root causes, implementing fixes, and validating solutions. Use when ToolUniverse tools fail tests, return errors, have schema validation issues, or when asked to debug or fix tools in the ToolUniverse framework.

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.

TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code execution, (A) automated validation, (B) ToolUniverse audit, (E) less-is-more simplification. Core philosophy: each concept appears exactly once; remove don't add; no emojis; single setup entry point. Use when reviewing docs, before releases, after API changes, or when asked to audit, fix, or simplify documentation.

Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/find/info/run/test/status/build/serve), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.

Set up, launch, validate, and troubleshoot the ESM ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Install or update ToolUniverse in Claude Science — create the conda env, install the tooluniverse pip package, and (re)build the tooluniverse-research skill by fetching the current workflow library from GitHub. Use for first-time setup, upgrading the ToolUniverse version, refreshing the bundled workflows after an upstream release, or reinstalling on a new machine.

Set up, launch, validate, and troubleshoot the LDSC ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the Milo ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the MOFA+ ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the PAGA ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the scVI ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Continuous improvement system for ToolUniverse tools, skills, and plugin. Run benchmarks, diagnose failures, route fixes to devtu skills, retest. Use after skill optimization, tool additions, or as regression check.

Set up, launch, validate, and troubleshoot the Boltz-2 ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the LIANA ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the MACS3 ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Immunology research workflows: antibody-antigen interactions, T/B cell repertoire, MHC/HLA binding prediction, autoimmune disease genetics, vaccine epitope mapping. Uses IEDB, IMGT, SAbDab, UniProt. Use for adaptive immunity questions, immune response analysis, antibody/TCR/BCR characterization, immunogenicity prediction, and immune-pathway-to-disease mapping.

Lipid analysis and lipid-disease associations using LIPID MAPS classification, HMDB metabolite data, KEGG/Reactome lipid pathways (sphingolipid, eicosanoid, steroid, fatty acid), and PubChem chemical info. Use for lipid identification, lipid metabolism pathway mapping, and lipid-associated disease analysis (cardiovascular, diabetes, NAFLD).

Drug and chemical toxicity assessment via adverse outcome pathways (AOPs), real-world FAERS adverse event signals, FDA labels, and toxicogenomic associations. Triangulates molecular initiating event to cellular outcome to organ-level toxicity to clinical adverse event. Use for hepatotoxicity/cardiotoxicity/nephrotoxicity prediction and toxicology reports.

Set up, launch, validate, and troubleshoot the Borzoi ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the scANVI ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the scVelo ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Add custom local tools to ToolUniverse alongside the 1000+ built-in tools. Covers JSON-config tools (simplest, no code), Python class tools (REST/SOAP/GraphQL APIs, computational logic), and best-practices for return schemas. Use for wrapping new APIs, adding domain-specific computations, or contributing tools to the registry.

Genomics and epigenomics analysis: DNA methylation (CpG, 5mC, 5hmC, bisulfite, RRBS), m6A RNA modification (MeRIP-seq), ChIP-seq peaks, ATAC-seq accessibility, histone modifications, chromatin state, multi-omics integration. Combines pandas/scipy/pysam computation with ToolUniverse annotation tools. Use for genome-wide epigenomic statistics, methylation analysis, and chromatin-genome integration.

Review existing work against the user's actual goal and surface evidence-backed strengths, gaps, risks, and next fixes. Use when asked to eval, evaluate, review, assess, or check current/this/my/our work; decide whether a task is complete; build a definition-of-done checklist or rubric; or perform grading, LLM-as-judge, Qworld, or RET evaluation. Treat plain eval/review requests as qualitative: resolve "current work" from the conversation, artifacts, files, or diff, and never assign numeric scores unless the user explicitly requests scores, grades, points, ratings, weighted criteria, Qworld, or RET. Do not use for implementing automated eval suites, tests, graders, or benchmarks.

Single-cell RNA-seq analysis with scanpy/anndata — h5ad data loading, scRNA-seq quality control and QC gating (n_genes_by_counts, total_counts, mitochondrial percent / pct_counts_mt, pct_counts_ribo, doublet detection with Scrublet/scDblFinder, ambient RNA / SoupX awareness, empty-droplet filtering, MAD-based thresholds), normalization, dimensionality reduction (PCA, UMAP, t-SNE), clustering (Leiden, Louvain), marker gene identification, cell-type annotation, pseudotime/trajectory analysis. Use for any scRNA-seq workflow, including deciding which cells to filter, flag, or investigate before downstream analysis.

Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology.

Set up, launch, validate, and troubleshoot the Harmony ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the SingleR ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the Squidpy ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the Tangram ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on OpenAI Codex. ALWAYS consult this skill for any of those — don't answer from memory, because the exact marketplace name (mims-harvard/ToolUniverse), the "codex plugin marketplace add" then "codex plugin add -m tooluniverse" flow, Codex's startup auto-upgrade behavior, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Codex, says the Codex plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Codex updates it, wants to pin or remove it, or finds it running an old tool version — even if they never say the word "plugin". Not for the Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.

Drug-combination synergy analysis — quantify whether two drugs together are synergistic, additive, or antagonistic using the standard reference models (Bliss independence, HSA / highest single agent, Loewe additivity, ZIP, and the Chou-Talalay Combination Index). Use when you have measured single-drug and combination effects (inhibition/viability) and need a synergy score. Explains which model to use, what data each one needs, and how to read the score. NOT for looking up pre-computed synergy in a database (use the SYNERGxDB tool / cell-line-profiling skill).

Metabolomics research — metabolite identification, study analysis, and database searches across HMDB, MetaboLights, Metabolomics Workbench, KEGG. Use for annotating mass-spec features to known metabolites, finding metabolomics studies of a disease, and structured metabolomics research reports with metabolite-pathway mapping.

Neuroscience research workflows: neuroanatomy, neural circuits, neurotransmitter biology, neurological/psychiatric disease genetics, neural-protein function. Uses Allen Brain Atlas, WormBase (C. elegans connectome), UniProt for neural proteins, PubMed for primary literature. Use for brain-region biology, neural development, neurodegeneration mechanisms (Alzheimer's, Parkinson's, ALS), and synaptic-protein characterization.

Host, validate, and privately share a user's own model, Python function, workflow, or existing Streamable HTTP MCP endpoint through ToolUniverse Platform. Use when turning a local CPU/GPU workload or lab endpoint into a stable TU remote tool, diagnosing its setup, or preparing it for controlled sharing.

Set up, launch, validate, and troubleshoot the CellRank ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the Enformer ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the Monocle 3 ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the PINNACLE ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Set up, launch, validate, and troubleshoot the Scrublet ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Dose-response / concentration-response curve fitting — IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency from paired concentration vs response data (enzyme/cell assays, drug screening, agonist/antagonist pharmacology). Fits the 4-parameter logistic (Hill sigmoidal) model. Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality. NOT for image-derived dose-response (use tooluniverse-image-analysis) and NOT for survival/regression (use tooluniverse-statistical-modeling).

Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory work.

Meta-analysis / evidence synthesis — pool effect sizes across studies (odds ratios, risk ratios, hazard ratios, mean differences, correlations, GWAS betas) with fixed- or random-effects models, quantify heterogeneity (Q, I², τ²), and build a forest plot. Use when you have results from MULTIPLE studies and need a single pooled estimate, or to synthesize evidence from a systematic review / multiple GWAS / replicated experiments. Handles the error-prone effect-size + standard-error preparation (converting OR/HR/CI, two-group means±SD, proportions, and correlations into the (effect, SE) the pooling step needs).

Non-coding RNA analysis — miRNAs (miRBase, miRDB targets), lncRNAs (LNCipedia, RNAcentral), circRNAs, snoRNAs, and other ncRNA classes. Distinct mechanisms per class — miRNAs repress mRNA; lncRNAs scaffold/decoy/enhance. Use for ncRNA function prediction, miRNA-target prediction, lncRNA functional annotation, and ncRNA-disease association queries.

Phylogenetic analysis — de novo multiple sequence alignment (Clustal Omega/MUSCLE/MAFFT via EBI_msa_align) and neighbour-joining/UPGMA tree building (EBI_build_phylogenetic_tree) from your own sequences, plus tree analysis, treeness, saturation (PhyKIT), parsimony-informative sites, alignment gap analysis, DVMC, long-branch detection, BUSCO orthologs. Uses PhyKIT, Biopython, DendroPy. Use to align a set of sequences, build a tree from sequences or an alignment, or for phylogenetic tree QC, multi-gene phylogenomics, evolutionary-rate analysis, and comparative-genomics studies.

PCR / qPCR primer and oligo design — design forward/reverse primers for a target region (SantaLucia nearest-neighbor thermodynamics), compute melting temperature (Tm) and annealing temperature (Ta), check GC content, and screen an oligo for hairpins and primer-dimers. Use when you need primers for a sequence, want to QC an existing primer pair, or need the Tm of an oligo. Covers the primer-design rules (Tm matching, GC clamp, 3'-end, length) and the tools' constraint quirks.

RNA-seq differential expression analysis with DESeq2, edgeR, and limma-voom — DEG lists, fold changes, dispersion estimation, design formulas including covariates, multi-condition contrasts, and Venn-set operations across groups. Routes across DESeq2 (default), edgeR (QL-F / exact test for small replicate counts), and limma-voom (large n / complex designs). Use when you have a count matrix + metadata, want to find DEGs, or need dispersion/PCA/clustering analysis. Includes RULE ZERO precedence (read executed.ipynb if present).

Optimize tool descriptions in ToolUniverse JSON configs for clarity and usability. Reviews descriptions for missing prerequisites, unexpanded abbreviations, unclear parameters, and missing usage guidance. Use when reviewing tool descriptions, improving API documentation, or when user asks to check if tools are easy to understand.

Set up, launch, validate, and troubleshoot the Slingshot ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.

Universal data access patterns for downloading and parsing scientific data when ToolUniverse tools don't cover the source, only return metadata, or you need bulk records. Use for VCF/h5ad/BAM/SDF/GCT parsing, multi-step API workflows (search to filter to download to parse), thousands of records at once, or sources with no dedicated tool. Write Python code via Bash for every step.

Evaluate the human safety liability of knocking down, knocking out, degrading, or pharmacologically inhibiting a gene. Use for gene safety scoring, on-target toxicity assessment, essentiality and genetic-constraint review, critical-organ expression analysis, or deciding whether a target needs partial, transient, or tissue-specific modulation.

Microscopy and quantitative imaging analysis — colony morphometry, fluorescence intensity quantification, cell-count statistics, dose-response curves, and ANOVA/Dunnett on image-derived measurements. Uses pandas/numpy/scipy/scikit-image. Use for analyzing tabular outputs from CellProfiler/ImageJ, image-derived measurement statistics, and image-based assay quantification.

Detect and auto-install missing ToolUniverse research skills. Checks common Claude Code/Cursor/Codex skill directories for the canary file, and installs any missing skills if none found. Use when the plugin's research skills aren't loading, when migrating between clients, or when verifying a skill installation.

Plant genomics and biology research — PlantReactome pathways, Ensembl Plants gene structure, POWO species taxonomy, UniProt annotation, KEGG plant pathways. Handles polyploidy (wheat hexaploidy etc.) and homeologous gene copies. Use for crop-gene annotation, plant secondary metabolism queries, and plant-disease/stress-response biology.

Computational vaccine candidate design: peptide/subunit vaccines via MHC-I/MHC-II epitope prediction (IEDB), population HLA coverage optimization, B-cell epitope identification, and cross-strain conservation analysis. Use for vaccine epitope prediction, HLA allele coverage, multi-epitope construct design, and immunogenicity assessment. Combines predicted MHC binding with experimentally validated IEDB epitopes for higher-confidence designs.

Set up, launch, validate, and troubleshoot the CellTypist ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.