i4h-workflow-finetune
i4h-workflow-finetune is an agent skill published by nvidia, listed under training models. It lives in the NVIDIA/skills repository, which has 3,735 GitHub stars and is licensed under Apache-2.0; we last read it on 2026-10-08.
Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads NVIDIA/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add NVIDIA/skills
Maintenance
Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.
i4h-workflow-finetune compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| i4h-workflow-finetune (this page) | nvidia | Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not… | 3,735 | 2026-10-26 |
| nemo-mbridge-mlm-bridge-training(same repository) | nvidia | Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, availa… | 3,735 | 2026-10-26 |
| nemotron-asr-finetune(same repository) | nvidia | Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal… | 3,735 | 2026-10-26 |
| nemotron-customize(same repository) | nvidia | Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines:… | 3,735 | 2026-10-26 |
| nvflare-convert-huggingface(same repository) | nvidia | Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated… | 3,735 | 2026-10-26 |
| paidf-anomalygen(same repository) | nvidia | Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG),… | 3,735 | 2026-10-26 |
| tao-finetune-cosmos-embed(same repository) | nvidia | Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication… | 3,735 | 2026-10-26 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about i4h-workflow-finetune
- What does i4h-workflow-finetune do?
- Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.
- How do I install i4h-workflow-finetune?
- Run npx skills add NVIDIA/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes i4h-workflow-finetune?
- nvidia.
- Is i4h-workflow-finetune maintained, and what licence does it use?
- Its repository has 3,735 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-26. The repository declares the Apache-2.0 licence.
More agent skills for training models
- ai-image-generationby 101-skills
- flux-imageby 101-skills
- p-imageby 101-skills
- firecrawl-knowledge-baseby firecrawl
- agent-platform-eval-flywheelby google
- agent-platform-tuningby google