<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs
Devsly

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated today

by NVIDIA

skills

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

  • Active — Updated in the last 14 days
Works with
  • Claude
  • Codex
View on GitHub (opens in a new tab)

3.9k GitHub stars (3,862)

+338 in 30 days

Stars gained per day · daily snapshots since Sep 26
Stars gained per day, Sep 26 to Nov 5: +415 in total; the busiest day was Oct 21 with +29 stars.Sep 27: +2 starsSep 28: +12 starsSep 29: +17 starsSep 30: +11 starsOct 1: +2 starsOct 2: +7 starsOct 3: +5 starsOct 4: +11 starsOct 5: +6 starsOct 6: +4 starsOct 7: +6 starsOct 8: +7 starsOct 9: +6 starsOct 10: +10 starsOct 11: +3 starsOct 12: +5 starsOct 13: +9 starsOct 14: +17 starsOct 15: +12 starsOct 16: +8 starsOct 17: +23 starsOct 18: +2 starsOct 19: +6 starsOct 20: +13 starsOct 21: +29 starsOct 22: +3 starsOct 23: +12 starsOct 24: +16 starsOct 25: +8 starsOct 26: +14 starsOct 27: +15 starsOct 28: +15 starsOct 29: +15 starsOct 30: +13 starsOct 31: +9 starsNov 1: +6 starsNov 2: +6 starsNov 3: +19 starsNov 4: +15 starsNov 5: +16 stars
Stars gained between daily snapshots
PeriodNew stars
Sep 27+2
Sep 28+12
Sep 29+17
Sep 30+11
Oct 1+2
Oct 2+7
Oct 3+5
Oct 4+11
Oct 5+6
Oct 6+4
Oct 7+6
Oct 8+7
Oct 9+6
Oct 10+10
Oct 11+3
Oct 12+5
Oct 13+9
Oct 14+17
Oct 15+12
Oct 16+8
Oct 17+23
Oct 18+2
Oct 19+6
Oct 20+13
Oct 21+29
Oct 22+3
Oct 23+12
Oct 24+16
Oct 25+8
Oct 26+14
Oct 27+15
Oct 28+15
Oct 29+15
Oct 30+13
Oct 31+9
Nov 1+6
Nov 2+6
Nov 3+19
Nov 4+15
Nov 5+16
  • 30 skills (30 skills found in its SKILL.md files)
  • 488 forks (488 forks)
  • Today last update (Last updated today)

Install

Skills CLI

npx skills add NVIDIA/skills

Asks which skills and agents to install. Just one: npx skills add NVIDIA/skills --skill accelerated-computing-cudf — add -g for every project.

Claude Code

git clone https://github.com/NVIDIA/skillscp -r "skills/skills/accelerated-computing-cudf" ~/.claude/skills/

Copies the accelerated-computing-cudf skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add NVIDIA/skills

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md — showing the first 30 of 418 files.

  • accelerated-computing-cudf

    Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

    skills/accelerated-computing-cudf/SKILL.md on GitHub (opens in a new tab)

  • ambient-healthcare-agent-with-nemotron-voice-agent

    Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.

    skills/ambient-healthcare-agent-with-nemotron-voice-agent/SKILL.md on GitHub (opens in a new tab)

  • amc-run-rtsp-calibration

    Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

    skills/amc-run-rtsp-calibration/SKILL.md on GitHub (opens in a new tab)

  • amc-run-sample-calibration

    Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.

    skills/amc-run-sample-calibration/SKILL.md on GitHub (opens in a new tab)

  • amc-run-video-calibration

    Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`.

    skills/amc-run-video-calibration/SKILL.md on GitHub (opens in a new tab)

  • amc-setup-calibration-stack

    Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.

    skills/amc-setup-calibration-stack/SKILL.md on GitHub (opens in a new tab)

  • boltz2-nim

    Use Boltz2 NIM for biomolecular structure prediction and binding affinity. Invoke for Boltz2, protein structures, protein-ligand/DNA/RNA complexes, SMILES or CCD ligands, pIC50/IC50 affinity scoring, mmCIF output, hosted NVIDIA API calls, or local Docker deployment.

    skills/bionemo-boltz2-nim/SKILL.md on GitHub (opens in a new tab)

  • codonfm-embed

    Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.

    skills/bionemo-codonfm-embed/SKILL.md on GitHub (opens in a new tab)

  • codonfm-finetune

    Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune CodonFM or Encodon for regression or classification. Support generic public-v1 Encodon workflows only; reject Decodon, MissenseDataset, missense_synom_agg, and generation workflows.

    skills/bionemo-codonfm-finetune/SKILL.md on GitHub (opens in a new tab)

  • codonfm-score

    Validate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the user explicitly requests CodonFM or Encodon, or that context is already established in the conversation. Do not select this skill for a generic variant-scoring request without that context; ask for the variant and intended analysis first.

    skills/bionemo-codonfm-score/SKILL.md on GitHub (opens in a new tab)

  • codonfm-setup

    Set up the public CodonFM v1 repository and download public Encodon checkpoints. Use for requests to build or launch the CodonFM development container, configure local data/checkpoint mounts, verify GPU access, or download public Encodon 80M, 600M, 1B, or Cdwt-1B weights. Do not use for Decodon, Encodon 5B/10B, missense-aggregation, or codon-optimization setup because those implementations are no…

    skills/bionemo-codonfm-setup/SKILL.md on GitHub (opens in a new tab)

  • complexa-evaluate-pdbs

    Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score designs, compute interface pAE, i_pLDDT, scRMSD, motif RMSD, or designability, run complexa analysis, or assess third-party BindCraft, AlphaProteo, or RFdiffusion outputs. SKILL.md selects and invokes the evaluation configuration; bundled executables on…

    skills/bionemo-complexa-evaluate-pdbs/SKILL.md on GitHub (opens in a new tab)

  • complexa-sweep

    Agent runbook for Proteina-Complexa parameter sweeps through the separately installed first-party CLI and config generator. Use for cartesian-product hyperparameter scans, sweeper YAML authoring, configuration comparisons, ablations, tuning, success-rate ranking, or Pareto searches over quality and wall-clock cost. Do not use for a single existing-job launch or SLURM submission template. SKILL.md…

    skills/bionemo-complexa-sweep/SKILL.md on GitHub (opens in a new tab)

  • complexa-target

    Add, edit, inspect, or validate Proteina-Complexa target definitions for protein binders, ligand binders, and AME motif scaffolding. Use for target registries, chain/residue selectors, hotspots, ligand fields, and incomplete motif inputs. Covers direct YAML edits and complexa target/validate target commands; running a campaign with an already registered target belongs to complexa-design.

    skills/bionemo-complexa-target/SKILL.md on GitHub (opens in a new tab)

  • diffdock-nim

    Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets. Use for DiffDock, molecular docking, ligand docking, blind docking, SMILES or SDF ligands, ranked poses, confidence scores, hosted NVIDIA API, or local Docker deployment.

    skills/bionemo-diffdock-nim/SKILL.md on GitHub (opens in a new tab)

  • drug-discovery-pipeline

    NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for confidential or proprietary data. Run a complete computational drug discovery pipeline using NVIDIA BioNeMo NIMs: generate drug-like molecules with GenMol, dock them to a protein target with DiffDock, then predict binding affinity with Boltz2. U…

    skills/bionemo-drug-discovery-pipeline/SKILL.md on GitHub (opens in a new tab)

  • evo2-nim

    Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted generation, local Docker deployment, local forward passes, layer outputs, logits, sampled probabilities, and BioNeMo NIM workflows.

    skills/bionemo-evo2-nim/SKILL.md on GitHub (opens in a new tab)

  • genmol-nim

    Generate novel drug-like molecules using the GenMol NIM microservice. Use for de novo generation, scaffold decoration, motif extension, lead optimization, SAFE notation, QED or LogP ranking, hosted NVIDIA API calls, or local Docker deployment. GenMol takes SAFE notation in the smiles field, not ordinary SMILES.

    skills/bionemo-genmol-nim/SKILL.md on GitHub (opens in a new tab)

  • genomics-workflow-acceleration

    Use when accelerating existing genomics workflows with NVIDIA Parabricks, improving runtime or price/performance, converting pipeline steps to GPUs, or comparing CPU and GPU workflow outputs. Adds optional GPU steps in-place with runtime toggles (default off). Do NOT use for individual pbrun command routing — use parabricks.

    skills/bionemo-genomics-workflow-acceleration/SKILL.md on GitHub (opens in a new tab)

  • kermt-add-cmim-pretrain

    Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue pretraining on the user's corpus as hybrid (vocab + contrast). Effectively kermt-continue-pretrain with a one-time ckpt-conversion step prepended.

    skills/bionemo-kermt-add-cmim-pretrain/SKILL.md on GitHub (opens in a new tab)

  • kermt-continue-pretrain

    Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized training and write model bundles, prepared data, logs, and checkpoints to user-selected host directories.

    skills/bionemo-kermt-continue-pretrain/SKILL.md on GitHub (opens in a new tab)

  • kermt-embed

    Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized embedding extraction and write model bundles, per-readout .npy embeddings, canonical SMILES, and validity arrays to user-selected host directories.

    skills/bionemo-kermt-embed/SKILL.md on GitHub (opens in a new tab)

  • kermt-finetune

    Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Write model bundles, prepared data, logs, and trained models to user-selected host directories.

    skills/bionemo-kermt-finetune/SKILL.md on GitHub (opens in a new tab)

  • kermt-infer

    Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rdkit_2d features), then launches main.py predict inside the kermt container (blocking, minutes-scale).

    skills/bionemo-kermt-infer/SKILL.md on GitHub (opens in a new tab)

  • kermt-monitor

    Check progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).

    skills/bionemo-kermt-monitor/SKILL.md on GitHub (opens in a new tab)

  • kermt-pretrain-scratch

    Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrain_ddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model is randomly initialized.

    skills/bionemo-kermt-pretrain-scratch/SKILL.md on GitHub (opens in a new tab)

  • kermt-setup

    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.

    skills/bionemo-kermt-setup/SKILL.md on GitHub (opens in a new tab)

  • 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.

    skills/bionemo-molmim-nim/SKILL.md on GitHub (opens in a new tab)

  • msa-search-nim

    Generate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. Use for homolog search, UniRef30/ColabFold env searches, A3M or FASTA alignments, paired MSA search for complexes, PDB70 structural templates, hosted NVIDIA API calls, or local Docker deployment. For local deployment, download the databases in parallel with aria2c and launch via NIM_MODEL_NAME (…

    skills/bionemo-msa-search-nim/SKILL.md on GitHub (opens in a new tab)

  • msa-structure-prediction-pipeline

    NOTE: your protein sequence and the retrieved MSA alignment are transmitted to external NVIDIA-hosted APIs (health.api.nvidia.com) on every call. Use local NIM containers for confidential or proprietary sequences. Run a complete protein structure prediction pipeline using NVIDIA BioNeMo NIMs: search for MSA alignments with MSA-Search (ColabFold), then predict the structure with OpenFold3 using th…

    skills/bionemo-msa-structure-prediction-pipeline/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.