Scientific Agent Skills is a collection of reusable procedures that give AI agents capabilities for scientific research across areas such as biology, chemistry, medicine, and drug discovery. It is used by researchers and by people building AI scientist workflows with compatible coding agents. The catalogue contains many of the project's skills and supporting instructions.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add K-Dense-AI/scientific-agent-skills --skill torchdruggit clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/k-dense-ai/scientific-agent-skills/torchdrug)<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agent-skills/torchdrug"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/torchdrug/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agent-skills/torchdrug"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/torchdrug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 62 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.03007 |
| Opus 5.5 | $0.00026 | $0.01203 |
| Sonnet 5.5 | $0.00013 | $0.00601 |
| Haiku 4.5 | $0.00006 | $0.00301 |
Grade A, and why
torchdrug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- torchdrug — 100% identical, 57 lines differ
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TorchDrug
Use TorchDrug as a modular PyTorch graph-learning stack:
- load a
datasets.*dataset, - choose a
models.*representation model, - wrap it in a
tasks.*objective, - train and evaluate it with
core.Engine.
The current official documentation and latest published release are both 0.2.1 (released July 2023; rechecked October 1, 2026). Treat newer Python or PyTorch combinations as unverified rather than silently assuming compatibility.
Start with the version guard
Before generating or debugging code, inspect the environment:
python --version
python -c "import torch; print(torch.__version__)"
python -c "import torchdrug; print(torchdrug.__version__)"
The supported matrix for TorchDrug 0.2.1 is:
- Python 3.7 through 3.10
- PyTorch 1.8 through 2.0
- Linux, Windows, or macOS
- Apple Silicon: PyTorch 1.13 or later, CPU only; no MPS support
If the project uses Python 3.11+ or PyTorch 2.1+, create a compatible environment or explicitly test a source build. Do not present such combinations as supported.
Installation
Prefer a dedicated Python 3.10 environment and pin the TorchDrug release:
uv venv --python 3.10
source .venv/bin/activate
uv pip install "torch==2.0.0" "numpy==1.26.4" "setuptools<81" wheel
Install torch-scatter and torch-cluster wheels matched to the exact PyTorch
and CUDA pair, following the
official installation page. For a
CPU-only PyTorch 2.0 environment on a platform listed in that wheel index, use:
uv pip install --only-binary :all: "torch-scatter==2.1.2" "torch-cluster==1.6.3" \
--find-links "https://data.pyg.org/whl/torch-2.0.0+cpu.html"
uv pip install "torchdrug==0.2.1" "numpy==1.26.4" "scipy==1.13.1" \
"rdkit-pypi==2022.9.5" "fair-esm==2.0.0" "decorator==5.1.1"
Do not copy a CUDA wheel URL between environments. Match the PyTorch version,
CUDA build, Python ABI, and platform. On Apple Silicon, the official docs require
building torch-scatter and torch-cluster from source; the wheel index above
has no macOS ARM64 wheels. Install PyTorch before building with
--no-build-isolation. A working compiler/SDK is also required; having PyTorch
installed alone does not guarantee a successful native build. See
review and environment evidence for the exact audit stack.
Use the fair-esm distribution, which imports as esm; the newer distribution
named esm is a different SDK. Do not install both RDKit distributions (rdkit
and rdkit-pypi) into one environment. NumPy 1.x avoids the old binary stack's
NumPy 2 ABI incompatibility; setuptools<81 retains pkg_resources for PyTorch 2.0.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/core_concepts.md 7.3 KB
- references/datasets.md 8.9 KB
- references/knowledge_graphs.md 5.8 KB
- references/models_architectures.md 5.6 KB
- references/molecular_generation.md 6.2 KB
- references/molecular_property_prediction.md 7.3 KB
- references/protein_modeling.md 8.2 KB
- references/retrosynthesis.md 7.4 KB
- references/review.md 7.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 25d ago Changed · +23 lines · +3 tokens per session 03538274e00a
- 26d ago Changed b8a891692613
- 1mo ago First seen · 259 lines · 61 tokens per session scan A 6e03c6bb0645
torchdrug is a skill published in the GitHub repository K-Dense-AI/scientific-agent-skills (54,777 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 3,007 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
bio-prefect-dask-nextflow
Choose and scaffold Prefect+Dask or Nextflow pipelines. Use when designing a local, distributed, or Slurm-backed bioinformatics workflow.
discovery-toolbox
A routed repertoire of 90 scientific thinking operators for biological research agents - visual reasoning, detectability and information budgets, search reframing, causal identification, competing explanations, observation and selection processes, pipeline artifact diagnosis, effort allocation, and confirmation…
rdkit-qsar-pharmacophore
Computes 2048-bit ECFP4 Morgan fingerprints from SMILES, trains LightGBM regressors for pIC50 prediction, and extracts SHAP feature attributions.
discovery-director
Operate as a research director making original discoveries from a given biological question and dataset. Use when the task is open-ended scientific research, exploring omics or experimental data for findings, hypothesis generation and testing, screening a large candidate space of genes, variants, features or…
bulk-rnaseq-counts-to-de-deseq2
Run differential expression analysis on bulk RNA-seq count data with DESeq2 (R). Covers DESeqDataSet construction from a count matrix, tximport (Salmon/Kallisto), featureCounts, or SummarizedExperiment; pre-filtering; design formulas (simple, batch, paired, interaction, multi-factor, LRT); result extraction by…
seurat-skill
Comprehensive Seurat v5 (R) guide for single-cell RNA-seq and multimodal analysis. Covers installation, standard workflows (Normalize/SCTransform), clustering, integration (CCA/RPCA/Harmony), differential expression (FindMarkers/FindAllMarkers), visualization (DimPlot/FeaturePlot/VlnPlot/DoHeatmap), spatial…