nvidia/digital-health-skills
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
NVIDIA Digital Health skills repo for agent-guided healthcare AI workflows, including evaluation, data generation, model adaptation, deployment guidance, and developer best practices.
概要
Agent skills and worked examples for healthcare AI workflows from NVIDIA Digital Health. This repository hosts — markdown-based workflow guides consumable by AI coding assistants (Claude Code, Cursor, GitHub Copilot, and any client that supports the agentskills.io specification). The first set covers a : term curation, synthetic clinical-speech benchmark generation, KER (Keyword Error Rate) / entity-level scoring, and fine-tune guidance. These skills are . They do not ship companion runtime code; an agent following them will use the user's own environment and any required NVIDIA APIs (NIMs at build.nvidia.com, NeMo containers, etc.). Each skill folder contains SKILL.md (the workflow guide), optional references/*.md (deeper detail loaded on demand), and evals/evals.json (trigger / behavior / boundary test cases). Skills are loaded by your agent's skill loader.
README
以下は原文 README の抜粋です。原文を見る。
NVIDIA Digital Health Examples
Agent skills and worked examples for healthcare AI workflows from NVIDIA Digital Health.
This repository hosts agent skills — markdown-based workflow guides consumable by AI coding assistants (Claude Code, Cursor, GitHub Copilot, and any client that supports the agentskills.io specification).
The first set covers a clinical ASR (automatic speech recognition) evaluation workflow: term curation, synthetic clinical-speech benchmark generation, KER (Keyword Error Rate) / entity-level scoring, and fine-tune guidance.
These skills are docs-only workflow guides. They do not ship companion runtime code; an agent following them will use the user’s own environment and any required NVIDIA APIs (NIMs at build.nvidia.com, NeMo containers, etc.).
Skills in this repo
| Skill | Stage | What it guides |
|---|---|---|
digital-health-clinical-asr-setup |
1 | Verify NVIDIA_API_KEY, install Python deps, set up NGC + Docker for the NeMo training container, smoke-test the NVCF stack with Magpie TTS + Parakeet/Nemotron ASR. |
digital-health-clinical-asr-build |
2 | Specialty interview, term curation, two-tier IPA tagging, NeMo-format manifest synthesis. Inlines a Magpie TTS NVCF recipe. |
digital-health-clinical-asr-eval |
3 | Transcribe a NeMo manifest via Parakeet/Nemotron ASR, score WER/CER/KER/SER, produce a five-section leaderboard, route via the post-eval decision tree. |
digital-health-clinical-asr-finetune |
4 | Stock NeMo SFT on Parakeet TDT v2, term-aware train/val split, offline cycle N+1 re-eval, optional Riva NIM deploy. |
Each skill folder contains SKILL.md (the workflow guide), optional references/*.md (deeper detail loaded on demand), and evals/evals.json (trigger / behavior / boundary test cases).
Getting started
Skills are loaded by your agent’s skill loader. For Claude Code:
git clone [email protected]:NVIDIA/digital-health-skills.git
cd digital-health-skills
# Either symlink or copy the four skill folders into your Claude Code skills dir:
mkdir -p ~/.claude/skills
ln -s "$(pwd)/skills/digital-health-clinical-asr-setup" ~/.claude/skills/
ln -s "$(pwd)/skills/digital-health-clinical-asr-build" ~/.claude/skills/
ln -s "$(pwd)/skills/digital-health-clinical-asr-eval" ~/.claude/skills/
ln -s "$(pwd)/skills/digital-health-clinical-asr-finetune" ~/.claude/skills/
Then invoke them from your agent: /digital-health-clinical-asr-setup, /digital-health-clinical-asr-build, /digital-health-clinical-asr-eval, /digital-health-clinical-asr-finetune.
The skills walk the agent through each stage and hand off to the next. Start with /digital-health-clinical-asr-setup.
Requirements
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add nvidia/digital-health-skills