Agent skill · nvidia
molmim-nim
Use this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. Invoke for MolMIM, molecular embeddings, hidden states, latent decoding, sampling around a seed SMILES, CMA-ES guided molecule generation, QED or plogP optimization, hosted NVIDIA API calls, or local Docker deployment.
What it needs
About 3k tokens when loaded.
What this skill does
MolMIM NIM Generate, sample, embed, and decode small molecules with MolMIM. Use this guide for first-pass hosted/local usage; load supplemental files only when needed: references/api.md: endpoints, schema, Docker flags, response fields. references/science.md: use cases, strengths, limits, and handoffs. references/parameters.md: generation, sampling, and optimization effects. references/validation.md: SMILES/property/artifact checks. references/examples.md: compact hosted/local request patterns. Choose Mode Ask only when context is unclear: Hosted NVIDIA API or local Docker NIM? See references/api.md under Endpoints for the full hosted/local endpoint list. Mode difference: the hosted API reference exposes /generate; the local container exposes the broader latent-space workflow (/embedding, /hidden, /decode, /sampling, /generate). Do not invent hosted latent endpoints. Hosted requests use Authorization: Bearer $NGCAPIKEY. Local inference uses no auth header after readiness. Local Docker Use shell env first; source repo-root .env only if present. Do not print keys. MolMIM docs use NGCCLIAPIKEY for the local container; this repo accepts NGCAPIKEY or NVIDIAAPIKEY and maps to NGCCLIAPIKEY for startup. Mount LOCALNIMCACHE at /home/nvs/.cache/nim. For the exact startup preflight (the NGCAPIKEY/NVIDIAAPIKEY → NGCCLIAPIKEY mapping, docker login, and the docker run for nvcr.io/nim/nvidia/molmim:1.0.0), copy the command block in references/api.md under Local Docker verbatim. Readiness check: Local embedding smoke test after readiness. Local inference uses no Authorization header: Hosted Generation Pattern Use hosted /generate for seed-SMILES generation or optimization. Use algorithm: "CMA-ES" for guided property optimization and algorithm: "none" for unguided sampling around the seed. Generation gotchas: Field name is smi, not smiles. algorithm is "CMA-ES" or "none". propertyname is "QED" or "plogP". nummolecules is 1-100. iterations is 1-1000. particles is 2-1000. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/bionemo-molmim-nim