This repository is a curated collection of 177+ domain-specific scientific 'skills' for AI agents, following the Agent Skills standard. Each skill is a self-contained module providing a CLI tool, documentation, and tests for a specific scientific or technical task—ranging from single-cell RNA-seq analysis (scanpy) and molecular docking (diffdock) to clinical report validation and ISO standards readiness. The architecture is a monorepo of independent skills, each with its own scripts/, references/, assets/, and tests/. Skills are designed to be safe, bounded, and reproducible: they validate inputs before execution, enforce resource limits, avoid network access unless explicitly required, and produce structured JSON reports. The repository also includes a shared test infrastructure (skill_contract) and a meta-skill (autoskill) that can automatically propose new skills from screen activity. While primarily an application library for AI agents, it has strong data/research characteristics due to its heavy use of scientific data formats and validation of research artifacts.
The Allegro package implements the Allegro E(3)-equivariant machine learning interatomic potential as an extension for the NequIP framework. It provides a neural network architecture that predicts energies and forces in atomic systems while being invariant to translations, rotations, and reflections. The model is built using a combination of scalar and tensor feature tracks, interacting through tensor product layers, and is designed to be strictly local with a configurable cutoff radius. The architecture centers around the `AllegroModel` function, which constructs a graph neural network. Input atomic data (positions, types, and optionally cell) is processed through embedding layers to generate initial scalar and tensor features. These features then pass through multiple Allegro layers, each consisting of tensor product operations (via the `Contracter` module) and mixing layers (MLPs). The final features are reduced to per-atom energies, summed to get the total energy, and forces and stresses are computed via automatic differentiation if requested. Key entry points include the `AllegroModel` function and the package's entry point for NequIP integration. The package relies on external dependencies such as NequIP, PyTorch, and e3nn, with optional accelerations via NVIDIA's CuEquivariance library or custom Triton kernels for GPU performance. The codebase demonstrates strong engineering practices, including performance optimizations for the tensor product bottleneck (through both the base `Contracter` implementation and GPU-accelerated variants), a clear modular structure, and comprehensive testing. Reusable components such as the `Contracter` and `MakeWeightedChannels` modules showcase efficient tensor product handling and feature weighting strategies that could be adapted to other equivariant neural network architectures with minimal modification.
BoltzGen is a deep learning pipeline for computational protein and peptide binder design. It provides a command-line interface (boltzgen) that orchestrates a multi-step workflow: diffusion-based backbone generation, inverse folding (sequence design given structure), folding with Boltz-2, affinity prediction, analysis, and filtering/ranking of designs. The system supports diverse protocols including protein, peptide, nanobody, antibody, and small-molecule targeting, with extensive conditioning options like binding sites, disulfide bonds, cyclization, and per-residue constraints. The codebase is structured as a Python package with modular components for data parsing (YAML design specs, mmCIF/PDB), featurization, tokenization, cropping, and model layers (pairformer, attention, diffusion, inverse folding). It includes training pipelines with Hydra configuration, PyTorch Lightning, and validation splits. While primarily an application, it also contains research-grade example datasets and a Jupyter notebook for filtering, reflecting its origin in a bioRxiv publication. The architecture is well-organized but shows some technical drift (hardcoded paths, print statements, broad exception handling) and dependency on specific CUDA versions.
This repository is a comprehensive catalog of containerized AI agents for scientific computing, primarily in chemistry, biology, materials science, and engineering domains. It includes over 40 agents (e.g., AutoDock Vina, AlphaFold, OpenFOAM, GWP predictor) each packaged as a Docker container with a utility module, example inputs, and tests. The platform also provides a Python CLI tool (`discovery`) for submitting jobs to an Azure-based HPC service, managing storage, and monitoring job status. The repository is hybrid in nature, containing both production-ready application components (CLI, agent deployment infrastructure) and research artifacts (training pipelines for the GWP predictor, model weights, and data ingestion scripts). The agent architecture follows a consistent pattern: each agent has a `quick_setup`/`save_final_results` lifecycle and is designed to run in a containerized environment with mounted `/input` and `/output` directories. The CLI is well-structured with Typer and Rich, and includes extensive tests. However, the codebase exhibits significant duplication (e.g., `molecular_utils.py` and `io_utils.py` appear identically in multiple agents) and some hardcoded paths, which reduces maintainability. The GWP predictor training pipeline is a notable research component with a multi-step ETL process and active learning, but it is tightly coupled to specific external data sources. Overall, the repository serves as a strong foundation for deploying scientific AI agents on Azure, with moderate reusability of individual components.