ToolUniverse

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.

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.

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.

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.

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.

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.

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.

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.

Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases/services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.

Code quality patterns and guidelines for ToolUniverse tool development. Apply when writing, fixing, or refactoring tool Python code in the ToolUniverse project. Encodes lessons from 80+ debug rounds. Use alongside devtu-fix-tool and devtu-self-evolve. Triggers: implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug fixes.

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.

Automatically discover life science APIs online, create ToolUniverse tools, validate them, and prepare integration PRs. Performs gap analysis to identify missing tool categories, web searches for APIs, automated tool creation using devtu-create-tool patterns, validation with devtu-fix-tool, and git workflow management. Use when expanding ToolUniverse coverage, adding new API integrations, or systematically discovering scientific resources.

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

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...

End-to-end variant-to-mechanism analysis — trace a variant (rsID/coordinates) through regulatory context, target gene(s), molecular pathway(s), and phenotypic consequences. Integrates 7+ databases across 3 evidence layers (regulatory, molecular, disease) for a mechanistic model. Use for GWAS-hit-to-mechanism, eQTL-causal-gene tracing, and full causal-chain reports.

Validate a variant-effect predictor (AlphaMissense, ESM-C SAE, ESM logits, EVE, conservation scores, or any per-variant numeric score) against experimental deep mutational scanning (DMS) data. Computes per-variant predictor scores, splits variants into neutral vs disruptive groups by DMS effect, runs a Mann-Whitney U test on the predictor scores, and sweeps the stratification thresholds for robustness. Use when you need to know whether a predictor's scores track real functional disruption on a specific protein.

Clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Use for VUS classification, pathogenicity assessment with cited criteria, structure-based variant impact (AlphaFold/PDB), non-coding/regulatory variant effect prediction with sequence deep-learning models (AlphaGenome, Enformer, Borzoi, ChromBPNet, Evo 2), and producing clinical-grade variant reports for return of results or molecular tumor boards. Use this whenever a user asks about a variant's significance, an intronic/promoter/enhancer/UTR non-coding variant's functional impact, or needs ACMG classification — even if they don't say "ACMG".

Functional annotation of protein variants — ProtVar structural/functional context, ClinVar clinical classifications, gnomAD population frequencies, CADD deleteriousness, ClinGen gene-disease validity, plus FAVOR one-call comprehensive GRCh38 annotation. Use for variant annotation pipelines, missense effect prediction, and protein-level variant interpretation with functional context.

VCF and variant analysis — parsing, annotation, classification (synonymous, missense, frameshift, stop_gained), VAF filtering, coding vs non-coding categorization, multi-condition variant comparison. Use for VCF parsing, variant fraction calculations (denominator = coding subset only, NOT all variants), and per-sample mutation profiling.

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.

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.

Comprehensive drug-target intelligence — tissue expression (GTEx, HPA), pathways, protein interactions (STRING), variant landscape (ClinVar, gnomAD), druggability (DGIdb, ChEMBL approved drugs). 9 parallel research paths with citations. Use for full target profile reports, target characterization for drug discovery, and 'tell me about target X' queries.

Systems biology and pathway analysis integrating Reactome, KEGG, WikiPathways, BioCarta, NCI-Nature Pathway Interaction Database. Multi-database pathway enrichment, protein-pathway relationships, network reasoning. Use for pathway analysis on a gene list, multi-source pathway concordance, and systems-level interpretation across databases.

Structural variant (SV) clinical interpretation: deletions, duplications, inversions, translocations, complex rearrangements. Applies ACMG-adapted criteria with ClinGen HI/TS dosage scores, gnomAD frequencies, and ClinVar evidence. Produces 5-tier classification with explicit per-criterion evidence. Use for clinical genomics SV review, dosage-sensitivity assessment, breakpoint analysis, and CNV pathogenicity calls. Gene-dosage-driven reasoning.

Structural biology plus proteomics integration for drug target validation. Combines PDB experimental structures, AlphaFold predictions, GPCRdb, SAbDab antibody structures, ProteinsPlus binding-site prediction, and BindingDB ligand-affinity data. Use for druggability assessment, binding-site characterization, ligand-pocket analysis, structural-confidence scoring (resolution, pLDDT), and antibody-target interface analysis.