Hugging Face Local Model Evals
huggingface/skills
Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.
Integrate TileGym kernels into Hugging Face transformers models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load…
Install Tilegym Monkey Patch Kernels To Transformers
$ npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/skills tilegym-monkey-patch-kernels-to-transformers --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tilegym-monkey-patch-kernels-to-transformers .claude/skills/tilegym-monkey-patch-kernels-to-transformers && rm -rf skills-srcUse ~/.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/
Install the "tilegym-monkey-patch-kernels-to-transformers" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/tilegym-monkey-patch-kernels-to-transformers into .claude/skills/tilegym-monkey-patch-kernels-to-transformers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilegym-monkey-patch-kernels-to-transformers", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/NVIDIA/skills/tree/main/skills/tilegym-monkey-patch-kernels-to-transformersType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/skills tilegym-monkey-patch-kernels-to-transformers --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tilegym-monkey-patch-kernels-to-transformers .agents/skills/tilegym-monkey-patch-kernels-to-transformers && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tilegym-monkey-patch-kernels-to-transformers" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/tilegym-monkey-patch-kernels-to-transformers into .agents/skills/tilegym-monkey-patch-kernels-to-transformers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilegym-monkey-patch-kernels-to-transformers", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/skills tilegym-monkey-patch-kernels-to-transformers --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tilegym-monkey-patch-kernels-to-transformers .cursor/skills/tilegym-monkey-patch-kernels-to-transformers && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tilegym-monkey-patch-kernels-to-transformers" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/tilegym-monkey-patch-kernels-to-transformers into .cursor/skills/tilegym-monkey-patch-kernels-to-transformers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilegym-monkey-patch-kernels-to-transformers", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/NVIDIA/skills.git --path skills/tilegym-monkey-patch-kernels-to-transformers--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/skills tilegym-monkey-patch-kernels-to-transformers --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tilegym-monkey-patch-kernels-to-transformers .gemini/skills/tilegym-monkey-patch-kernels-to-transformers && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tilegym-monkey-patch-kernels-to-transformers" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/tilegym-monkey-patch-kernels-to-transformers into .gemini/skills/tilegym-monkey-patch-kernels-to-transformers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilegym-monkey-patch-kernels-to-transformers", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install NVIDIA/skills tilegym-monkey-patch-kernels-to-transformersInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tilegym-monkey-patch-kernels-to-transformers .github/skills/tilegym-monkey-patch-kernels-to-transformers && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tilegym-monkey-patch-kernels-to-transformers" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/tilegym-monkey-patch-kernels-to-transformers into .github/skills/tilegym-monkey-patch-kernels-to-transformers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilegym-monkey-patch-kernels-to-transformers", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NVIDIA/skills tilegym-monkey-patch-kernels-to-transformers --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tilegym-monkey-patch-kernels-to-transformers .opencode/skills/tilegym-monkey-patch-kernels-to-transformers && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tilegym-monkey-patch-kernels-to-transformers" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/tilegym-monkey-patch-kernels-to-transformers into .opencode/skills/tilegym-monkey-patch-kernels-to-transformers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilegym-monkey-patch-kernels-to-transformers", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
tilegym-monkey-patch-kernels-to-transformers- GitHub stars
- 3.5k
- Token cost
- ~741 tokens
- SKILL.md length
- 262 words
- Files
- 10 (incl. references)
- Skills in repo
- 380
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Integrate TileGym kernels into Hugging Face transformers models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load…
- Works in 4 steps: Prepare experiment environment. Follow… → Integrate existing TileGym kernels to… → Autonomously create new cuTile kernels… → …
- Requires integrating TileGym kernels into transformers models
- SKILL.md covers Instructions, Workflow and Disciplines
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Tilegym Monkey Patch Kernels To Transformers is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Integrate TileGym kernels into Hugging Face transformers models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into transformers models.
Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `BENCHMARK.md`, `evals/evals.json` and `references/auto-kernelize.md`). Compatibility notes: Verified on Claude Code with Opus-4.6 and onward, CodeX with GPT-5.5 and onward, and Cursor (Agent mode) with GPT-5.3-CodeX and stronger models.
It sits in AI & LLM Engineering. It works with Transformers. The repository describes itself as: 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. The licence is Apache-2.0.
When your agent uses it
- Requires integrating TileGym kernels into transformers models
Example prompts
- “s submodule(s) and certain class(es)”
- “/tilegym-monkey-patch-kernels-to-transformers”
Requirements
- Compatibility (from SKILL.md): Verified on Claude Code with Opus-4.6 and onward, CodeX with GPT-5.5 and onward, and Cursor (Agent mode) with GPT-5.3-CodeX and stronger models.
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Prepare experiment environment. Follow environment-setup.md
- Integrate existing TileGym kernels to the target model. Follow kernel-integration.md
- Autonomously create new cuTile kernels for uncovered PyTorch code. Follow auto-kernelize.md
- Summarize and report
What it can do on your machine
Read from SKILL.md and the folder at commit 0e0d506. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are claudecodex).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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.
Compatibility
Verified on Claude Code with Opus-4.6 and onward, CodeX with GPT-5.5 and onward, and Cursor (Agent mode) with GPT-5.3-CodeX and stronger models.
From compatibility in the SKILL.md frontmatter.
Context cost
Tilegym Monkey Patch Kernels To Transformers loads about 741 tokens when it runs, and up to ~286k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 262 words of instructions outside code blocks.
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
The full file from NVIDIA/skills at commit 0e0d506, republished under its Apache-2.0 licence (© NVIDIA). 262 words, ~741 tokens.
Download SKILL.mdSave it as
.claude/skills/tilegym-monkey-patch-kernels-to-transformers/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- tilegym-monkey-patch-kernels-to-transformers
- description
- Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
- compatibility
- Verified on Claude Code with Opus-4.6 and onward, CodeX with GPT-5.5 and onward, and Cursor (Agent mode) with GPT-5.3-CodeX and stronger models.
- license
- CC-BY-4.0 AND Apache-2.0
- metadata.author
- TileGym Team <TileGym@nvidia.com>
- metadata.version
- 2026.06.03
- metadata.tags
- tilegym, transformers, integration, kernel, monkey-patch
Integrate and create cuTile kernels into 🤗 Transformers
The main purpose of TileGym project is to provide performant kernels for LLM training and inference. We will integrate proper kernels available in TileGym project to LLM models provided by Hugging Face transformers library to validate end-to-end functional correctness and performance improvements. Instead of modifying transformers source code, we will take a non-intrusive monkey-patch approach: We will replace certain modules/classes/methods in transformers library that implement the Transformer model we would like to integrate, such that at model instantiation, that model's core components will be replaced by TileGym implementations. At runtime the model will actually invoke TileGym kernels under the hood. In addition, we will follow an auto-research-style agent harness loop to create and integrate new cuTile kernels to the target model to improve kernel coverage and end-to-end throughput.
Instructions
This is for human readers: Simply prompt your favorite AI Agent with skill name and target model ID. E.g.,:
Hi, please /monkey-patch-kernels-to-transformers Qwen/Qwen3.5-0.8B.The Agent might ask you several questions. Make clarifications and give a go confirmation.
Workflow
- Prepare experiment environment. Follow environment-setup.md
- Integrate existing TileGym kernels to the target model. Follow kernel-integration.md
- Autonomously create new cuTile kernels for uncovered PyTorch code. Follow auto-kernelize.md
- Feel free to add new cuTile kernels with constraints in mind
- Do not stop until meet auto-kernelize loop stop conditions
- Summarize and report
Disciplines
This is for AI Agents executing this workflow.
Kernel inventory
Reusable transformer-local kernels must be represented with FlashInfer-Bench-style Definition and Solution metadata. Follow kernel-inventory-schema.md when researching compute requirements, inventorying existing kernels, proposing candidates, or creating new generated kernels.
© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 9 other files (references) in skills/tilegym-monkey-patch-kernels-to-transformers of NVIDIA/skills.
- SKILL.md
- BENCHMARK.md
- evals/evals.json
- references/auto-kernelize.md
- references/environment-setup.md
- references/kernel-integration.md
- references/kernel-inventory-schema.md
- references/workflow-diagram.png
- skill-card.md
- skill.oms.sig
Open the folder on GitHubat commit 0e0d506
Compare with similar skills
Tilegym Monkey Patch Kernels To Transformers 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tilegym Monkey Patch Kernels To Transformers this skillNVIDIA/skills | 3.5k | — | ~741 | Automated safety check: Pass | Apache-2.0 | |
| Hugging Face Local Model Evalshuggingface/skills | 11k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Fine Tuning With TrlOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Hugging Face Vision Trainerhuggingface/skills | 11k | 1 repos | ~7.5k | Automated safety check: Pass | Apache-2.0 | |
| bitsandbytes Model QuantizationOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Quark Torch Quant Perfamd/Quark | 181 | — | ~3k | Automated safety check: Pass | MIT |
Similar skills
- Official
Fine Tuning With Trl
Orchestra-Research/AI-Research-SKILLs
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.
- Official
Hugging Face Vision Trainer
huggingface/skills
Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.
bitsandbytes Model Quantization
Orchestra-Research/AI-Research-SKILLs
Loads large language models in 8-bit or 4-bit with bitsandbytes so they fit smaller GPUs, and sets up QLoRA fine-tuning on a 4-bit base model.
Quark Torch Quant Perf
amd/Quark
Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.
Hugging Face Transformers Usage
davila7/claude-code-templates
Loads pre-trained Hugging Face Transformers models for text, vision and audio tasks, runs inference with pipelines and fine-tunes on custom datasets.
More from NVIDIA/skills
All 380 skills in this repo- Official
Vss Deploy Detection Tracking 2D
NVIDIA/skills
A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.
- Official
HSB IP Def File Tool
NVIDIA/skills
Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.
- Official
Isaac Sim Mission Control Showcase
NVIDIA/skills
Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.
- Official
Defect Image Generation with Cosmos AnomalyGen
NVIDIA/skills
Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.
- Official
Physical AI Video Augmentation on OSMO
NVIDIA/skills
Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.
- Official
TAO Detection KPI Analysis
NVIDIA/skills
Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.
Related
Works with
Categories
Questions about Tilegym Monkey Patch Kernels To Transformers
What does Tilegym Monkey Patch Kernels To Transformers do?
Integrate TileGym kernels into Hugging Face transformers models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load…. Tilegym Monkey Patch Kernels To Transformers is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Integrate TileGym kernels into Hugging Face transformers models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models.
When should I use Tilegym Monkey Patch Kernels To Transformers?
Tilegym Monkey Patch Kernels To Transformers fits situations like: requires integrating TileGym kernels into transformers models.
How do I install Tilegym Monkey Patch Kernels To Transformers in Claude Code?
Run `npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a claude-code`. Or copy the skill folder (skills/tilegym-monkey-patch-kernels-to-transformers in NVIDIA/skills) into .claude/skills/tilegym-monkey-patch-kernels-to-transformers in your project. Claude Code loads it when a task matches its description.
How do I install Tilegym Monkey Patch Kernels To Transformers in Codex?
Run `npx skills add NVIDIA/skills --skill tilegym-monkey-patch-kernels-to-transformers -a codex`. Or copy the skill folder (skills/tilegym-monkey-patch-kernels-to-transformers in NVIDIA/skills) into .agents/skills/tilegym-monkey-patch-kernels-to-transformers in your project. Codex loads it when a task matches its description.
Can I use Tilegym Monkey Patch Kernels To Transformers 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/skills --skill tilegym-monkey-patch-kernels-to-transformers -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tilegym-monkey-patch-kernels-to-transformers, .gemini/skills/tilegym-monkey-patch-kernels-to-transformers, .github/skills/tilegym-monkey-patch-kernels-to-transformers and .opencode/skills/tilegym-monkey-patch-kernels-to-transformers in your project.
What does Tilegym Monkey Patch Kernels To Transformers need to run?
SKILL.md names no scripts, command-line tools or credentials: Tilegym Monkey Patch Kernels To Transformers is instructions for the agent only. Compatibility (from SKILL.md): Verified on Claude Code with Opus-4.6 and onward, CodeX with GPT-5.5 and onward, and Cursor (Agent mode) with GPT-5.3-CodeX and stronger models..
Does Tilegym Monkey Patch Kernels To Transformers access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Tilegym Monkey Patch Kernels To Transformers 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 Tilegym Monkey Patch Kernels To Transformers use?
Tilegym Monkey Patch Kernels To Transformers is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Tilegym Monkey Patch Kernels To Transformers use?
About 741 tokens (SKILL.md is roughly 3k 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 286k tokens, read only when the agent opens those files.
What are the alternatives to Tilegym Monkey Patch Kernels To Transformers?
Skills that share tags, products or a category with Tilegym Monkey Patch Kernels To Transformers: Hugging Face Local Model Evals (huggingface/skills, 11k stars), Fine Tuning With Trl (Orchestra-Research/AI-Research-SKILLs, 13k stars), Hugging Face Vision Trainer (huggingface/skills, 11k stars) and bitsandbytes Model Quantization (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tilegym Monkey Patch Kernels To Transformers?
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,534 GitHub stars. The repository holds 380 skills in this directory. The repository was last updated on October 7, 2026.
Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.