tooluniverse-install-skills
This Claude Code skill automatically detects and installs the ToolUniverse research skill package by checking for a canary file across common client directories and downloading the missing skills from the GitHub repository if needed. Use it when ToolUniverse research capabilities aren't available, when switching between Claude clients, or to verify that specialized skills are properly installed in the correct directory structure.
git clone --depth 1 https://github.com/mims-harvard/ToolUniverse /tmp/tooluniverse-install-skills && cp -r /tmp/tooluniverse-install-skills/plugin/skills/tooluniverse-install-skills ~/.claude/skills/tooluniverse-install-skillsSKILL.md
# ToolUniverse Install Skills Checks whether the ToolUniverse specialized skills are installed and installs them automatically if not. ## Detection Use the Shell tool to check for the canary file across all common client locations: ```bash ls .cursor/skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || ls .agents/skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || ls .windsurf/skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || ls .gemini/skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || ls .claude/skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || ls .opencode/skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || ls .trae/skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || ls .skills/tooluniverse-drug-research/SKILL.md 2>/dev/null \ || echo "NOT_INSTALLED" ``` - **Output is a file path** → skills already installed, stop here. - **Output is `NOT_INSTALLED`** → proceed to installation. ## Installation ```bash # 1. Download skills from GitHub (shallow, sparse — only skills/ folder) git clone --depth 1 --filter=blob:none --sparse \ https://github.com/mims-harvard/ToolUniverse.git /tmp/tu-skills cd /tmp/tu-skills && git sparse-checkout set skills # 2. Copy to the correct directory for the detected client: mkdir -p .cursor/skills && cp -r /tmp/tu-skills/skills/* .cursor/skills/ # Cursor # mkdir -p .agents/skills && cp -r /tmp/tu-skills/skills/* .agents/skills/ # Codex/OpenAI # mkdir -p .windsurf/skills && cp -r /tmp/tu-skills/skills/* .windsurf/skills/ # Windsurf # mkdir -p .gemini/skills && cp -r /tmp/tu-skills/skills/* .gemini/skills/ # Gemini CLI # mkdir -p .claude/skills && cp -r /tmp/tu-skills/skills/* .claude/skills/ # Claude Code # mkdir -p .opencode/skills && cp -r /tmp/tu-skills/skills/* .opencode/skills/ # OpenCode # mkdir -p .trae/skills && cp -r /tmp/tu-skills/skills/* .trae/skills/ # Trae # mkdir -p .skills && cp -r /tmp/tu-skills/skills/* .skills/ # Cline/VS Code # 3. Clean up rm -rf /tmp/tu-skills ``` If the client cannot be detected automatically, ask the user which one they use before running step 2. ## Client Detection Detect the client from the presence of config files: | Config file present | Client | |---|---| | `.cursor/` | Cursor | | `.agents/` | Codex / OpenAI | | `.windsurf/` | Windsurf | | `.gemini/` | Gemini CLI | | `.claude/` | Claude Code | | `.opencode/` | OpenCode | | `.trae/` | Trae | | None of the above | Ask the user | ## After Installation Confirm success: ```bash ls .cursor/skills/tooluniverse-drug-research/SKILL.md ``` Tell the user: "ToolUniverse skills installed successfully. You now have access to 50+ specialized research workflows."
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".
Systematic ACMG/AMP germline variant classification with all 28 criteria (PVS1, PS1-4, PM1-6, PP1-5, BA1, BS1-4, BP1-7) for clinical significance. Produces 5-tier verdict (Pathogenic / Likely Pathogenic / VUS / Likely Benign / Benign) with cited evidence per criterion. Use for variant interpretation, VUS resolution, and pathogenicity assessment. Combines ClinVar, gnomAD, computational predictors, and gene-mechanism context.
Comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiling for drug candidates. Integrates ADMET-AI predictions, SwissADME drug-likeness, PubChemTox experimental toxicity, ChEMBL clinical data, Lipinski rule-of-five, and CYP interaction data. Use for drug-likeness assessment, BBB penetration, bioavailability, hepatotoxicity prediction, ADME/PK profiling, or screening compound libraries before lab testing.
Detect and analyze adverse drug event signals using FDA FAERS reports, drug labels, and disproportionality statistics (PRR, ROR, IC). Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, regulatory submissions, and detecting rare AE signals not visible in clinical trials.
Map environmental and industrial chemicals to adverse outcome pathways (AOPs) — molecular initiating event to organ-level toxicity. Uses AOPWiki, GHS classification, IARC carcinogen status, and LD50 data. Use for environmental/industrial chemical risk assessment, regulatory-grade hazard characterization, and AOP stressor mapping. Distinct from drug-safety analysis (use tooluniverse-pharmacovigilance for drugs).
Aging biology, cellular senescence, and longevity research. Covers senescence markers (p16/CDKN2A, SASP, SA-beta-gal), aging hallmarks, senolytic drug discovery (dasatinib+quercetin, fisetin, navitoclax), epigenetic clocks, telomere biology, and longevity GWAS. Use for senescence-pathway analysis, age-related disease genetics, senolytic-target discovery, and centenarian-genetics queries. Distinguishes correlative vs causal evidence (knockout, intervention).
Therapeutic antibody engineering and optimization, lead-to-clinical-candidate. Covers sequence humanization (germline alignment, framework retention), affinity maturation, developability (aggregation, stability, PTMs), structure modeling (AlphaFold/PDB CDR analysis), immunogenicity prediction, and manufacturing feasibility. Use for biologic-drug optimization, mAb design review, biosimilar engineering, and clinical-precedent comparison.
Discover novel small-molecule binders for protein targets using structure-based and ligand-based screening. Covers druggability assessment, known-ligand mining (ChEMBL, BindingDB), similarity expansion, ADMET filtering, and synthesis feasibility. Use for hit identification, virtual screening, target-to-compounds workflows, and lead-finding before commit-to-medchem.