NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test inside the container. Every other kermt- skill depends on this; invoke it first.
NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
End-to-end Proteina-Complexa design pipeline driver. Use when the user wants to "design a binder", "design binders for X", "run complexa design", "de novo binder", "PDL1 binder", "TrkA binder", "design proteins for target", "protein binder design", "ligand binder", "design a small-molecule binder", "ATP-binding…
NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
Standalone evaluation of an existing PDB directory with Proteina-Complexa. Use when the user wants to "evaluate PDB files", "re-fold these designs", "compute interface pAE", "compute ipLDDT for a folder", "run AF2 / RF3 / ESMFold on my designs", "score binder candidates", "designability of this folder", "scRMSD for…
NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
First-time setup, environment configuration, and model-weight installation for Proteina-Complexa. Reach for this skill whenever the user says "set up complexa", "install complexa", "configure my environment file", "first-time setup", "what models do I have installed", "what's in my environment file", "download model…
NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
Use this skill whenever the user wants to run a parameter sweep over a Proteina-Complexa design pipeline — cartesian-product hyperparameter scans, Pareto search over generation/reward/evaluation knobs, or any "compare configurations" workflow. Trigger phrases include "sweep beam width", "sweep nsteps", "hyperparameter…
NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
Use this skill whenever the user wants to add, register, edit, list, show, or validate a Proteina-Complexa design target for any pipeline — protein binder (default), ligand binder, or AME / enzyme scaffolding. Triggers include "add a target", "define a new target for binder design", "register a hotspot", "set up a…
NVIDIA-BioNeMo/bionemo-agent-toolkit
Plugin Claude Code
NVIDIA BioNeMo agent skills for life sciences — protein folding, molecular docking, generative chemistry, genomics, protein design, and biomarker discovery as ready-to-call tools.
NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
Run a complete protein binder design campaign with NVIDIA Proteina-Complexa: resolve a target structure and hotspots from a name/sequence/PDB, co-design binder sequence+structure with reward-guided test-time search (best-of-n, beam search, FK steering, MCTS), select with the internal AF2 reward gate, then…
NVIDIA-BioNeMo/bionemo-agent-toolkit
Skill Claude CodeCodex
Orchestrate an end-to-end de novo protein binder design campaign against a protein target by composing BioNeMo NIM skills. Use for binder design, minibinder design, de novo binders, RFdiffusion + ProteinMPNN + Boltz2/OpenFold3 pipelines, epitope/hotspot-targeted design, in-silico binder validation, and ranking designs…
NVIDIA-BioNeMo/bionemo-agent-toolkit
Cursor rule
Side-by-side comparison of the two de novo binder-design routes (complexa-binder-design vs protein-binder-design) to help choose one for a given target and constraints.
NVIDIA-BioNeMo/bionemo-agent-toolkit
Cursor rule
Route selection and orchestration for de novo protein binder design. Composes two independent binder-design skills — complexa-binder-design (Proteina-Complexa reward-guided co-design) and protein-binder-design (RFdiffusion + ProteinMPNN + Boltz2/OpenFold3 NIM orchestration). Each resolves a target and hotspots…
Skill Claude CodeCodex
Write code that calls the installed nvMolKit Python API for GPU-accelerated, batched RDKit-style operations - Morgan fingerprints, Tanimoto/cosine similarity, ETKDG conformer embedding, MMFF/UFF optimization, TFD, conformer RMSD, Butina clustering, substructure search, and maximum common substructure (MCS) search. Use…
Plugin Claude Code
Plugin marketplace listing 1 plugin: fold-cp.
Plugin Claude Code
Integrate DTensor-based context parallelism (CP) into a custom co-folding / structure-prediction model — sharding the O(N²) pair and attention tensors across a multi-GPU device mesh via explicit ring/transpose collectives. A top-level cpizemodelworkflow conductor prioritizes, sequences, and gates the whole effort end.
Hook
Runs when a session starts, running an inline shell check. From NVIDIA-BioNeMo/boltz-cp.
Hook
Runs before the agent uses a tool for Write, Edit and Bash tool calls, executing guard_serial_and_tests.py via python3. From NVIDIA-BioNeMo/boltz-cp.
Skill Claude CodeCodex
Benchmark a CP inference or training workflow to find the maximum token count that fits at a given CP size and to record end-to-end walltime. Sweeps input size (tokens N, atoms, MSA depth S) over real or synthesized data, ramps N until OOM to report the max, times fwd (inference) or fwd+bwd+step (training) with warmup…
Skill Claude CodeCodex
Probe and establish the distributed test infrastructure for CP development. Inventories local GPUs (count, model, memory, NVLink topology), checks the software stack (Python, PyTorch+CUDA, NCCL, torch.distributed), and runs shipped smoke tests for batchisendirecv P2P, allgather, allreduce, reducescatter, and a DTensor…
Skill Claude CodeCodex
Orchestrate the END-TO-END integration of context parallelism into a custom co-folding / structure-prediction model: turn the whole effort into a prioritized, dependency-sorted worklist, then drive it phase by phase — map the model (learncontext), verify infra (buildinfra), shard data features (sharddatafeats), port…
Skill Claude CodeCodex
Orchestrate a team of agents to integrate many CP modules and tests in parallel. Builds the work-list from the module map, derives a data-flow dependency graph, topologically sorts it into GPU-slot-bounded waves, and spawns a coder+reviewer pair per work item. Reviewers enforce serial-as-ground-truth…
Skill Claude CodeCodex
Stand up the distributed-model lifecycle for a CP training/inference run: device placement before DTensor wrapping, the all-trainable-params-are-DTensors invariant (with placeholder/freeze for unimplemented modules), checkpoint save (DTensor → plain) and load (realign via the live statedict template + redistribute…
Skill Claude CodeCodex
Implement DTensor-based context-parallel model modules that mirror a serial reference. Maps each serial layer/module to its Boltz-CP counterpart with exact input/output shapes, placements, collectives, and backward memory budget; writes the CP implementation following the autograd.Function conventions (explicit…
Skill Claude CodeCodex
Explore a custom co-folding / structure-prediction model to understand its inference and training workflows, entry points, training framework (PyTorch Lightning vs DeepSpeed), data-feature format, and featurization pipeline — then map those components onto the existing Boltz-CP context-parallel reference so downstream…
Skill Claude CodeCodex
Memory-profile a context-parallel (CP) inference (or training) workflow with the PyTorch CUDA caching-allocator history, then attribute the top-N memory peaks to specific modules and lines of code. Wraps the end-to-end forward in torch.cuda.memory.recordmemoryhistory() + dumpsnapshot() (the same mechanism as Boltz2's…