Skills

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

ambient-healthcare-agent-with-nemotron-voice-agent is a skill in NVIDIA/skills, last changed 2 Oct 2026. It can touch credentials, run shell commands, reach the network, name web addresses, bundle scripts and pre-approve tools — read the findings before installing. Our pattern check found 1 item to review at commit d7e1e2c on 27 Oct 2026.

Pattern check: 1 item to review · commit d7e1e2c · 27 Oct 2026

Install
From the author
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.
Licence
CC BY 4.0 and Apache 2.0
Repo stars
3.8k
Folder last changed
2 Oct 2026 (opens in a new tab)
Publisher
NVIDIA
Files
42 files
Checked
d7e1e2c (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit d7e1e2c, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit d7e1e2c, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  git -C "$tmp" sparse-checkout set -- skills/ambient-healthcare-agent-with-nemotron-voice-agent &&
  git -C "$tmp" checkout -q d7e1e2c728579ad38174443ef22382d0fb4615b5 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/ambient-healthcare-agent-with-nemotron-voice-agent &&
  cp -R "$tmp"/skills/ambient-healthcare-agent-with-nemotron-voice-agent/. .claude/skills/ambient-healthcare-agent-with-nemotron-voice-agent/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit d7e1e2c. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Bundles scripts

    The folder holds code files the agent may run.

    evals/grader.py · references/appointment-making/database/db.py · references/appointment-making/database/schema.sql and 3 more

  • Pre-approves tools

    Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

    SKILL.md:5

  • Touches credentials

    It reads, asks for or contains keys, tokens, passwords or similar secrets.

    SKILL.md:65

Pattern check

Pattern check: 1 item to review · commit d7e1e2c · 27 Oct 2026

We checked every text file in this skill, at commit d7e1e2c on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://github.com/NVIDIA-AI-Blueprints/nemotron-voice-agent
  • https://github.com/NVIDIA-AI-Blueprints/nemotron-voice-agent.git
  • https://integrate.api.nvidia.com/v1
  • https://app.intigriti.com/programs/nvidia/nvidiavdp/detail

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

    • Note

      The description doesn't say when to use the skill. D6

      Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.

    • Note

      Reference files that SKILL.md doesn't link: BENCHMARK.md, evals/EVAL.md, references/custom/generic-implementation.md, references/custom/testing-protocol.md and skill-card.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (143 lines), references/custom/guide.md (142 lines), references/custom/testing-protocol.md (299 lines), references/deployment-modes.md (126 lines), references/example-design-choices.md (134 lines) and 1 more. B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

    • Note

      Reference files that SKILL.md doesn't link: BENCHMARK.md, evals/EVAL.md, references/custom/generic-implementation.md, references/custom/testing-protocol.md and skill-card.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (143 lines), references/custom/guide.md (142 lines), references/custom/testing-protocol.md (299 lines), references/deployment-modes.md (126 lines), references/example-design-choices.md (134 lines) and 1 more. B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

    • Note

      Reference files that SKILL.md doesn't link: BENCHMARK.md, evals/EVAL.md, references/custom/generic-implementation.md, references/custom/testing-protocol.md and skill-card.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (143 lines), references/custom/guide.md (142 lines), references/custom/testing-protocol.md (299 lines), references/deployment-modes.md (126 lines), references/example-design-choices.md (134 lines) and 1 more. B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

  • VS Code & CopilotPasses

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

SKILL.md

Files

42 files

PathSize
BENCHMARK.md (opens in a new tab)8.3 KB
SKILL.md (opens in a new tab)14.1 KB
evals/EVAL.md (opens in a new tab)2.5 KB
evals/config.yml (opens in a new tab)303 B
evals/evals.json (opens in a new tab)5.1 KB
evals/grader.py (opens in a new tab)8.4 KB
references/appointment-making/database/__init__.py (opens in a new tab)210 B
references/appointment-making/database/db.py (opens in a new tab)3.7 KB
references/appointment-making/database/schema.sql (opens in a new tab)893 B
references/appointment-making/database/seed.py (opens in a new tab)2.9 KB
references/appointment-making/database/seed_data/appointment_types.jsonl (opens in a new tab)2.2 KB
references/appointment-making/database/seed_data/doctors.jsonl (opens in a new tab)116 B
references/appointment-making/expected-conversation.yaml (opens in a new tab)9.1 KB
references/appointment-making/prompt.yaml (opens in a new tab)13.4 KB
references/appointment-making/test-ambient-agent-tools.py (opens in a new tab)2.6 KB
references/appointment-making/tool-implementation.py (opens in a new tab)13 KB
references/appointment-making/tools.yaml (opens in a new tab)4.7 KB
references/custom/expected-conversation-template.yaml (opens in a new tab)2 KB
references/custom/generic-implementation.md (opens in a new tab)2.9 KB
references/custom/guide.md (opens in a new tab)6.3 KB
Show 22 more
PathSize
references/custom/prompt-template.yaml (opens in a new tab)1.9 KB
references/custom/testing-protocol.md (opens in a new tab)13.4 KB
references/custom/tool-implementation-template.py (opens in a new tab)3.3 KB
references/custom/tools-template.yaml (opens in a new tab)891 B
references/deployment-modes.md (opens in a new tab)6.7 KB
references/example-design-choices.md (opens in a new tab)12.9 KB
references/patient-intake/expected-conversation.yaml (opens in a new tab)10.9 KB
references/patient-intake/patient-intake-speech-guard.py (opens in a new tab)13.5 KB
references/patient-intake/prompt.yaml (opens in a new tab)6.5 KB
references/patient-intake/test-ambient-agent-tools.py (opens in a new tab)22.2 KB
references/patient-intake/tool-implementation.py (opens in a new tab)8.8 KB
references/patient-intake/tools.yaml (opens in a new tab)3.1 KB
references/user-experience-flowchart.md (opens in a new tab)5.7 KB
scripts/apply_generic_agent_template.py (opens in a new tab)51.4 KB
scripts/inspect_nva_generic_defaults.py (opens in a new tab)1.9 KB
scripts/nva_generic_defaults.py (opens in a new tab)27.7 KB
scripts/run_expected_conversation.py (opens in a new tab)28.3 KB
scripts/verify_docker_compose_access.py (opens in a new tab)3.9 KB
skill-card.md (opens in a new tab)4.4 KB
skill.oms.sig (opens in a new tab)13.9 KB
tests/test_apply_template_safety.py (opens in a new tab)5.1 KB
tests/test_eval_contract.py (opens in a new tab)3.1 KB

More from NVIDIA/skills

  • accelerated-computing-cudf

    NVIDIA/skills

    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.

    • Runs shell commands
    • Names web addresses
    • +1 more
    Pattern check: Nothing flagged

    CC BY 4.0 and Apache 2.0 · 3.8k repo stars · Updated 15 Oct 2026

  • amc-run-rtsp-calibration

    NVIDIA/skills

    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.

    • Touches credentials
    • Runs shell commands
    • +3 more
    Pattern check: Nothing flagged

    Apache 2.0 · 3.8k repo stars · Updated 4 Sept 2026

  • amc-run-sample-calibration

    NVIDIA/skills

    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'.

    • Downloads software
    • Runs shell commands
    • +3 more
    Pattern check: Nothing flagged

    Apache 2.0 · 3.8k repo stars · Updated 4 Sept 2026

  • amc-run-video-calibration

    NVIDIA/skills

    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`.

    • Runs shell commands
    • Reaches the network
    • +2 more
    Pattern check: Nothing flagged

    Apache 2.0 · 3.8k repo stars · Updated 4 Sept 2026

  • amc-setup-calibration-stack

    NVIDIA/skills

    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.

    • Touches credentials
    • Runs shell commands
    • +2 more
    Pattern check: 1 item to review

    Apache 2.0 · 3.8k repo stars · Updated 14 Jul 2026

  • boltz2-nim

    NVIDIA/skills

    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.

    • Touches credentials
    • Runs shell commands
    • +3 more
    Pattern check: 1 item to review

    Apache 2.0 and CC BY 4.0 · 3.8k repo stars · Updated 2 Oct 2026

All skills in NVIDIA/skills