New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Groot Finetune

by nvidia-isaac in nvidia-isaac/video_to_data

Run and extend embodiment-aware GR00T N1.7 post-training workflows from successful robot-policy collection through semantic recording, LeRobot conversion, statistics, fine-tuning, open-loop…

Custom licenceAuto-check passedAI & LLM Engineering

Install Groot Finetune

skills CLI
$ npx skills add nvidia-isaac/video_to_data --skill groot-finetune -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nvidia-isaac/video_to_data groot-finetune --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nvidia-isaac/video_to_data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/groot-finetune .claude/skills/groot-finetune && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
groot-finetune
GitHub stars
856
Token cost
~2.6k tokens
SKILL.md length
957 words
Files
6 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

Run and extend embodiment-aware GR00T N1.7 post-training workflows from successful robot-policy collection through semantic recording, LeRobot conversion, statistics, fine-tuning, open-loop…

  • Works in 9 steps: Preflight and plan → Collect and select timeout-eligible… → Record or rerender semantic demonstrations → …
  • VLA fine-tuning
  • SKILL.md covers Resolve an embodiment contract, Keep runtimes explicit, Follow the gated workflow and Validation
  • Calls python, bash and git

What it does

Groot Finetune is an agent skill from nvidia-isaac/video_to_data. Run and extend embodiment-aware GR00T N1.7 post-training workflows from successful robot-policy collection through semantic recording, LeRobot conversion, statistics, fine-tuning, open-loop validation, task-level closed-loop evaluation, and success-only recordings. Use for GR00T or VLA fine-tuning, policy-to-data generation, floating-hand Sharpa, Vega/Dexmate Sharpa, new robot embodiments, modality/action contracts, exact successful-episode filtering, or reproducible closed-loop evaluation.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/adding-embodiment.md` and `references/embodiment-contract.md`).

It sits in AI & LLM Engineering, covering Fine-tuning and Statistics. The repository describes itself as: Nvidia Isaac Video to Data Pipeline.

When your agent uses it

  • VLA fine-tuning
  • Policy-to-data generation
  • Floating-hand Sharpa
  • Vega/Dexmate Sharpa

Example prompts

  • “/groot-finetune”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Preflight and plan
  2. Collect and select timeout-eligible source episodes
  3. Record or rerender semantic demonstrations
  4. Convert and audit LeRobot data
  5. Generate statistics and fine-tune
  6. Gate on open-loop evaluation
  7. Evaluate task success in closed loop
  8. Retain successful recordings
  9. Report and clean up

What it can do on your machine

Read from SKILL.md and the folder at commit 193382a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • bash
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Groot Finetune loads about 2.6k tokens when it runs, and up to ~6k if it reads all its reference files. Until then it costs about 128 tokens; SKILL.md has 957 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~128
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 957 words (~2,637 tokens).

“Own the requested workflow through validated artifacts. Execute stages when the user asks for a run; do not stop after printing commands. Keep source-data success, pipeline validity, and fine-tuned task success as three separate results.”

— opening of SKILL.md by nvidia-isaac, Custom licence
name
groot-finetune

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (references) in .codex/skills/groot-finetune of nvidia-isaac/video_to_data.

  • SKILL.md
  • agents/openai.yaml
  • references/adding-embodiment.md
  • references/embodiment-contract.md
  • references/floating-hand.md
  • references/vega-sharpa.md

Open the folder on GitHubat commit 193382a

Compare with similar skills

Groot Finetune next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Groot Finetune compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Groot Finetune this skillnvidia-isaac/video_to_data856—~2.6kAutomated safety check: PassCustom licence
Nvflare Fed StatsNVIDIA/skills3.5k—~3kAutomated safety check: PassApache-2.0
Sentence-Transformers Training Routerhuggingface/skills11k1 repos~2.6kAutomated safety check: PassApache-2.0
Train RlOpenPipe/ART11k—~2.4kAutomated safety check: PassApache-2.0
Qwopus27b Rl TrainingR6410418/Jackrong-llm-finetuning-guide1.7k—~830Automated safety check: PassApache-2.0
Dataset Evaluationawslabs/agent-plugins9151 repos~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Nvflare Fed Stats

    NVIDIA/skills

    Official

    Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count, failurecount, pixel-intensity histogram) across…

    3.5k GitHub stars~3k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Sentence-Transformers Training Router

    huggingface/skills

    Official

    Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.

    11k GitHub starsUsed in 1 repo~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Train Rl

    OpenPipe/ART

    RL training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Qwopus27b Rl Training

    R6410418/Jackrong-llm-finetuning-guide

    Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.

    1.7k GitHub stars~830 tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Dataset Evaluation

    awslabs/agent-plugins

    Official

    Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).

    915 GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Train Sft

    OpenPipe/ART

    SFT training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.9k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from nvidia-isaac/video_to_data

All 13 skills in this repo

  • Hoi Object Reconstruction Setup

    nvidia-isaac/video_to_data

    Prepare this repository's HOI object reconstruction environment for BundleSDF or SAM3D.

    856 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Run Mv Hoi Reconstruction

    nvidia-isaac/video_to_data

    Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.

    856 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Ego Reconstruction Setup

    nvidia-isaac/video_to_data

    Prepare the repository-local egocentric reconstruction pipeline for Codex-driven work.

    856 GitHub stars~826 tokensUpdated today
    Auto-check passed

  • Run Ego Reconstruction Video

    nvidia-isaac/video_to_data

    Run the egocentric reconstruction pipeline on an input video.

    856 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Hoi Object Reconstruction Doctor

    nvidia-isaac/video_to_data

    Diagnose and repair failures in this repository's BundleSDF or SAM3D HOI object reconstruction workflow.

    856 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Hoi Object Reconstruction Run

    nvidia-isaac/video_to_data

    Launch, monitor, resume, and verify this repository's BundleSDF or SAM3D HOI object reconstruction pipeline.

    856 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Groot Finetune

What does Groot Finetune do?

Run and extend embodiment-aware GR00T N1.7 post-training workflows from successful robot-policy collection through semantic recording, LeRobot conversion, statistics, fine-tuning, open-loop…. Groot Finetune is an agent skill from nvidia-isaac/video_to_data.7 post-training workflows from successful robot-policy collection through semantic recording, LeRobot conversion, statistics, fine-tuning, open-loop validation, task-level closed-loop evaluation, and success-only recordings.

When should I use Groot Finetune?

Groot Finetune fits situations like: VLA fine-tuning; policy-to-data generation; floating-hand Sharpa; vega/Dexmate Sharpa.

How do I install Groot Finetune in Claude Code?

Run `npx skills add nvidia-isaac/video_to_data --skill groot-finetune -a claude-code`. Or copy the skill folder (.codex/skills/groot-finetune in nvidia-isaac/video_to_data) into .claude/skills/groot-finetune in your project. Claude Code loads it when a task matches its description.

How do I install Groot Finetune in Codex?

Run `npx skills add nvidia-isaac/video_to_data --skill groot-finetune -a codex`. Or copy the skill folder (.codex/skills/groot-finetune in nvidia-isaac/video_to_data) into .agents/skills/groot-finetune in your project. Codex loads it when a task matches its description.

Can I use Groot Finetune in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nvidia-isaac/video_to_data --skill groot-finetune -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/groot-finetune, .gemini/skills/groot-finetune, .github/skills/groot-finetune and .opencode/skills/groot-finetune in your project.

What does Groot Finetune need to run?

Going by SKILL.md and its folder, Groot Finetune needs the command-line tools its instructions call (python, bash and git). Our summary lists: Python 3.

Does Groot Finetune access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Groot Finetune safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Groot Finetune use?

Groot Finetune has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Groot Finetune use?

About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Groot Finetune?

Skills that share tags, products or a category with Groot Finetune: Nvflare Fed Stats (NVIDIA/skills, 3.5k stars), Sentence-Transformers Training Router (huggingface/skills, 11k stars), Train Rl (OpenPipe/ART, 11k stars) and Qwopus27b Rl Training (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Groot Finetune?

nvidia-isaac (a GitHub organization) maintains it in nvidia-isaac/video_to_data, which has 856 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 2026.

Source: nvidia-isaac/video_to_data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.