Megatron-Core LLM Training
Orchestra-Research/AI-Research-SKILLs
Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count.
Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree.
$ npx skills add NVIDIA/skills --skill jetson-generate-kb -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/skills jetson-generate-kb --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/jetson-generate-kb .claude/skills/jetson-generate-kb && 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 "jetson-generate-kb" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/jetson-generate-kb into .claude/skills/jetson-generate-kb/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jetson-generate-kb", 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/jetson-generate-kbType 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 jetson-generate-kb -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/skills jetson-generate-kb --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/jetson-generate-kb .agents/skills/jetson-generate-kb && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "jetson-generate-kb" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/jetson-generate-kb into .agents/skills/jetson-generate-kb/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jetson-generate-kb", 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 jetson-generate-kb -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/skills jetson-generate-kb --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/jetson-generate-kb .cursor/skills/jetson-generate-kb && 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 "jetson-generate-kb" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/jetson-generate-kb into .cursor/skills/jetson-generate-kb/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jetson-generate-kb", 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/jetson-generate-kb--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 jetson-generate-kb -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/skills jetson-generate-kb --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/jetson-generate-kb .gemini/skills/jetson-generate-kb && 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 "jetson-generate-kb" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/jetson-generate-kb into .gemini/skills/jetson-generate-kb/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jetson-generate-kb", 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 jetson-generate-kbInstalls 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 jetson-generate-kb -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/jetson-generate-kb .github/skills/jetson-generate-kb && 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 "jetson-generate-kb" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/jetson-generate-kb into .github/skills/jetson-generate-kb/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jetson-generate-kb", 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 jetson-generate-kb -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 jetson-generate-kb --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/jetson-generate-kb .opencode/skills/jetson-generate-kb && 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 "jetson-generate-kb" agent skill from https://github.com/NVIDIA/skills/tree/main/skills/jetson-generate-kb into .opencode/skills/jetson-generate-kb/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jetson-generate-kb", 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.
jetson-generate-kbBuild a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree.
Jetson Generate Kb is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use after init-image / init-source; not for editing profile fields.
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `BENCHMARK.md`, `evals/evals.json` and `skill-card.md`).
It sits in Knowledge Management, covering GPU and accelerator computing and Knowledge bases. It works with NVIDIA AI Platform. 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.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 67a13c0. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Jetson Generate Kb loads about 3.8k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 1,261 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.
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.
The full file from NVIDIA/skills at commit 67a13c0, republished under its Apache-2.0 licence (© NVIDIA). 1,261 words, ~3,775 tokens.
.claude/skills/jetson-generate-kb/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.This skill produces a per-profile markdown reference at
target-platform/<profile-stem>.md (sibling to the profile YAML). It
bundles three things into one file so a future Claude session — or the
user — can see the shape of the active target without re-walking the
filesystem:
bsp_image.root_path, presence of canonical subtrees (rootfs/,
bootloader/, source/, …), and the nvpmodel variants matching
the active module SKU.source.root_path (kernel-jammy-src/, hardware/nvidia/,
nvidia-oot/, etc.) and devicetree files matching the chip family.documents.* references recorded in the
profile, with local-path existence checks and one-line descriptions.The KB is a snapshot, dated in its header. Re-run this skill whenever the underlying data changes — it is intentionally re-runnable and overwrites the previous KB on each run.
jetson-init-image prepares the BSP for a freshly authored
profile.bsp_image.root_path.source.root_path.bsp_image.* or documents.* in the profile YAML.Resolve the active profile per the contract in
../../context/target-platform-contract.md;
cache it in memory — the rest of the skill consumes only this
profile. Record <profile-stem> (the bare filename minus .yaml)
as the KB output filename stem.
| Field | Required for KB? | If missing |
|---|---|---|
bsp_image.root_path | yes | Refuse. A KB with no BSP root to scan is just a YAML restatement; tell the user to run jetson-init-image or hand-edit the profile. |
source.root_path | no | Skip the source-tree section; note "source_root not recorded" in the KB. |
documents.* | no | Render an empty Documents table with a "no documents recorded" note. |
If bsp_image.root_path is set but the directory does not exist on disk,
refuse with a clear message — do not fabricate a layout for a path
that isn't there.
bsp_image.root_path)Run only the following cheap operations — no recursive scans, no file content reads beyond directory listings:
ls -1 of bsp_image.root_path (one level deep). Record which
directories are present.rootfs/, bootloader/, kernel/, source/, tools/,
nv_tegra/.flash_config file exists at
<bsp_image.root_path>/<flash_config>. Record its path or
(missing).rootfs/etc/nvpmodel/ and filter to filenames matching
nvpmodel_<module.id>_<module.sku>*.conf. Record each match.
Use the lower-case module id (e.g. p3767) and the YAML-quoted
sku string (e.g. 0001).source.root_path)Skip this step entirely if source.root_path is NA or missing.
Otherwise, run only:
ls -1 of source.root_path (one level deep).kernel-jammy-src/, hardware/nvidia/, nvidia-oot/, nvgpu/,
nvethernetrm/, nvdisplay/, hwpm/, kernel-devicetree/.kernel-devicetree/generic-dts/dts/ exists, list filenames
matching tegra<chip>* where <chip> is the chip-family numeric
prefix (see chip-family map below). Record up to 30 hits; if more,
record the count and a "showing first 30" note.Derive <chip> from module.id:
module.id | Chip family | <chip> prefix |
|---|---|---|
p3701, p3767 | T234 — Orin | 234 |
p3834 | T264 — Thor | 264 |
If module.id is not in this table, record the chip as
unknown (module.id=<value>) and skip the chip-prefixed devicetree
filter.
For each field in documents.* from the loaded profile:
http://, https://,
or ftp://) or local path (anything else).os.path.exists. Record the path; if
missing on disk, append (missing).The one-line description for each field comes from the marker in
../../references/platform_template.yaml
— strip the <OPTIONAL: …> wrapper and use the inner text.
If the profile has no documents: block, render the section with a
single line: _No documents recorded — run jetson-link-docs or hand-edit the profile to add references._
Render the markdown using the structure below. Use today's date (YYYY-MM-DD) in the header. Always overwrite any existing KB file at the destination — do not prompt before overwriting; re-runs are the intended use.
Destination: target-platform/<profile-stem>.md.
# Target knowledge base — <profile-stem>
> Generated <YYYY-MM-DD> from `<bsp_image.root_path>` (BSP version `<bsp_image.version>`).
> Re-run `jetson-generate-kb` after extracting a new BSP, applying
> patches, or editing profile fields. This file is a regenerated
> snapshot — do not hand-edit.
## Profile facts
- **Reference devkit:** `<reference_devkit.name>`
- **Module:** `<module.id>-<module.sku>` (`<chip family label>`)
- **Reference carrier:** `<carrier.id>-<carrier.sku>`
- **Custom carrier:** `<custom_carrier.name>` (`<custom_carrier.id>-<custom_carrier.sku>`) _← omit this row if Case 1_
- **Active flash conf:** `<flash_config>`
- **BSP path:** `<bsp_image.root_path>`
- **BSP version:** `<bsp_image.version>`
- **Source root:** `<source.root_path>` _← or "_not recorded_" if NA_
## BSP image layout
Top-level directories under `<bsp_image.root_path>`:
| Directory | Present | Purpose |
|---|---|---|
| `rootfs/` | ✓ / ✗ | userspace rootfs (nvpmodel, nvfan, systemd units, etc.) |
| `bootloader/` | ✓ / ✗ | firmware blobs, BCT, MB1/MB2 dts |
| `kernel/` | ✓ / ✗ | prebuilt kernel + modules |
| `source/` | ✓ / ✗ | BSP source tree (kernel, OOT drivers, DT) |
| `tools/` | ✓ / ✗ | flashing helpers, jetson-io, kernel_flash |
| `nv_tegra/` | ✓ / ✗ | nvidia firmware tarballs, kernel-supplements |
Active flash conf `<flash_config>`: present at
`<bsp_image.root_path>/<flash_config>` _or_ `(missing — verify before flashing)`.
### nvpmodel files matching the active SKU
Filtered from `rootfs/etc/nvpmodel/` by `nvpmodel_<module.id>_<module.sku>*.conf`:
- `<each match, one per line>`
The active variant at boot is selected by `nvpower.sh` from
`/proc/device-tree/compatible` plus super / safety state — see
`jetson-customize-nvpmodel` for the resolution rules.
## Source tree layout
(omit this whole section if `source.root_path` is `NA`/missing)
Top-level subtrees under `<source.root_path>`:
| Subtree | Present | Purpose |
|---|---|---|
| `kernel-jammy-src/` | ✓ / ✗ | mainline 5.x kernel sources |
| `hardware/nvidia/` | ✓ / ✗ | NVIDIA platform DTs (per chip family) |
| `nvidia-oot/` | ✓ / ✗ | NVIDIA out-of-tree kernel modules |
| `nvgpu/` | ✓ / ✗ | GPU driver |
| `nvethernetrm/` | ✓ / ✗ | ethernet driver |
| `nvdisplay/` | ✓ / ✗ | display driver |
| `hwpm/` | ✓ / ✗ | hardware performance monitor |
| `kernel-devicetree/` | ✓ / ✗ | devicetree sources |
### Devicetree files for chip family `<chip>`
(omit if `kernel-devicetree/generic-dts/dts/` is absent)
Files matching `tegra<chip>*` under `kernel-devicetree/generic-dts/dts/`:
- `<each match, one per line — cap at 30, then a "first 30 of N" note>`
## Documents
| Field | Reference |
|---|---|
| Documents root folder | `<doc_root>` _or_ _not recorded_ |
| BSP / Jetson Linux developer guide | `<bsp_developer_guide>` _or_ _not recorded_ |
| Tegra SoC Technical Reference Manual | `<soc_tech_ref_manual>` _or_ _not recorded_ |
| Jetson module data sheet | `<module_data_sheet>` _or_ _not recorded_ |
| Jetson module design guide (PDG) | `<module_design_guide>` _or_ _not recorded_ |
| Jetson module thermal design guide (TDG) | `<module_thermal_design_guide>` _or_ _not recorded_ |
| Jetson module schematic | `<module_schematic>` _or_ _not recorded_ |
| Reference carrier board specification | `<carrier_board_spec>` _or_ _not recorded_ |
| Reference carrier schematic | `<carrier_schematic>` _or_ _not recorded_ |
| Custom carrier schematic | `<custom_carrier_schematic>` _or_ _not recorded / N/A (no custom carrier)_ |
| Reference-devkit pinmux spreadsheet | `<ref_devkit_pinmux_xls>` _or_ _not recorded_ |
| Custom-carrier pinmux spreadsheet | `<custom_carrier_pinmux_xls>` _or_ _not recorded / N/A (no custom carrier)_ |
(Local paths are tagged ` (missing)` if absent on disk. URLs are
recorded verbatim and not fetched. If `doc_root` is set, also tag
` (missing)` on it if the directory itself is gone — that signals
auto-mapping in `jetson-link-docs` won't work on a re-run.)
## How to refresh this file
Re-run `jetson-generate-kb` whenever any of the following changes:
- the BSP at `<bsp_image.root_path>` is re-extracted, patched, or upgraded,
- the source tree at `<source.root_path>` changes,
- the active profile's `bsp_image.*` or `documents.*` fields are edited.
This file is overwritten on every run. Do not hand-edit it — edit the
source data (profile YAML or the BSP tree) and re-run instead.Print a short summary:
target-platform/<profile-stem>.md.(missing).If a downstream skill triggered this run, tell the user to re-issue their original request.
target-platform/<profile-stem>.md. This is intentional —
re-runnability is the whole point. Tell the user not to hand-edit
the file; edit profile YAML or the BSP and regenerate.bsp_image.root_path = NA. A profile with no BSP path
produces a content-free KB. Do not write one — instead, point the
user at the profile YAML to fill in.target-platform/<stem>.md next to <stem>.yaml. Don't accidentally
read .md files in the profile-listing logic of
jetson-set-target (it already filters to *.yaml, but check
before adding new file types).chip: unknown rather than fabricate a <chip> prefix.
Update this skill's chip-family table when a new chip lands.../../context/target-platform-contract.md.bsp_image: recorded by /jetson-init-image; this is the only
required on-disk tree. If source.root_path is missing, render the KB
without the source-tree section./jetson-init-source already resolved source: when the
user wants source-tree discovery included./jetson-link-docs already wrote the
documents: block.chip: unknown
rather than a fabricated prefix.target-platform/<stem>.md to stay next
to the profile YAML; renaming the YAML invalidates the link.bsp_image.root_path not found — re-run /jetson-init-image so
the BSP is extracted and the path is recorded before regenerating
the KB.source.root_path
override is stale; rerun /jetson-init-source or correct the
profile field.documents: block missing from the KB — /jetson-link-docs was
never run; the KB falls back to "no documents bound" rather than
guessing paths.../../context/target-platform-contract.md — read-order contract this skill follows.../../context/bsp-customization-workflow.md — origin of the canonical BSP/source subtree list.../../references/platform_template.yaml — source of the documents-field one-line descriptions.../jetson-init-target/SKILL.md — sibling skill that authors the active target identity.../jetson-init-image/SKILL.md — sibling skill that authors the BSP image metadata this skill scans.../jetson-set-target/SKILL.md — sibling skill that flips the active pointer this skill resolves.© 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
SKILL.md and 4 other files in skills/jetson-generate-kb of NVIDIA/skills.
Open the folder on GitHubat commit 67a13c0
Jetson Generate Kb 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 |
|---|---|---|---|---|---|---|
| Jetson Generate Kb this skillNVIDIA/skills | 3.5k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Megatron-Core LLM TrainingOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~2.4k | Automated safety check: Pass | MIT | |
| OpenVLA-OFT Fine-TuningOrchestra-Research/AI-Research-SKILLs | 13k | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Cosmos Policy EvaluationOrchestra-Research/AI-Research-SKILLs | 13k | — | ~3.7k | Automated safety check: Pass | MIT | |
| Compound Docsoliver-kriska/claude-elixir-phoenix | 565 | — | ~547 | Automated safety check: Pass | MIT | |
| Knowledgebaseopen-edge-platform/edge-ai-suites | 140 | — | ~900 | Automated safety check: Pass | Apache-2.0 |
Orchestra-Research/AI-Research-SKILLs
Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count.
Orchestra-Research/AI-Research-SKILLs
Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.
Orchestra-Research/AI-Research-SKILLs
Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling.
oliver-kriska/claude-elixir-phoenix
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter.
open-edge-platform/edge-ai-suites
Generic RAG query skill - Retrieve any information from the local knowledge base and generate structured reports, summaries, or Q&A responses.
NateBJones-Projects/OB1
Conversation-first workflow for turning tacit work patterns into a structured operating model.
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.
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.
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.
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.
NVIDIA/skills
Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.
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.
Works with
Categories
Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Jetson Generate Kb is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree.
Jetson Generate Kb fits situations like: tasks that involve GPU and accelerator computing; tasks that involve Knowledge bases.
Run `npx skills add NVIDIA/skills --skill jetson-generate-kb -a claude-code`. Or copy the skill folder (skills/jetson-generate-kb in NVIDIA/skills) into .claude/skills/jetson-generate-kb in your project. Claude Code loads it when a task matches its description.
Run `npx skills add NVIDIA/skills --skill jetson-generate-kb -a codex`. Or copy the skill folder (skills/jetson-generate-kb in NVIDIA/skills) into .agents/skills/jetson-generate-kb in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill jetson-generate-kb -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jetson-generate-kb, .gemini/skills/jetson-generate-kb, .github/skills/jetson-generate-kb and .opencode/skills/jetson-generate-kb in your project.
SKILL.md names no scripts, command-line tools or credentials: Jetson Generate Kb is instructions for the agent only.
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.
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.
Jetson Generate Kb 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.
About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Jetson Generate Kb: Megatron-Core LLM Training (Orchestra-Research/AI-Research-SKILLs, 13k stars), OpenVLA-OFT Fine-Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars), Cosmos Policy Evaluation (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Compound Docs (oliver-kriska/claude-elixir-phoenix, 565 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,539 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.