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.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Checks whether the ToolUniverse specialized skills are installed and installs them automatically if not.
Use the Shell tool to check for the canary file across all common client locations:
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"
NOT_INSTALLED → proceed to installation.# 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.
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 |
Confirm success:
ls .cursor/skills/tooluniverse-drug-research/SKILL.md
Tell the user: "ToolUniverse skills installed successfully. You now have access to 50+ specialized research workflows."
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
The English summary is being prepared. Showing the original description.
ADMET property prediction for drug candidates. Full pharmacokinetic panel (Caco-2, PPB, clearance, CYP), toxicity (hERG, AMES, DILI), drug-likeness (Lipinski, QED), using RDKit descriptors and TDC models.
The English summary is being prepared. Showing the original description.
Interpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).
The English summary is being prepared. Showing the original description.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
The English summary is being prepared. Showing the original description.
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
The English summary is being prepared. Showing the original description.
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
The English summary is being prepared. Showing the original description.