fastgen-validate

NVIDIA/skills Testing & QA AI & ML engineering

fastgen-validate is a skill in NVIDIA/skills, last changed 9 Nov 2026. It can run shell commands and name web addresses.

From the author

Validate NVIDIA FastGen integrations and training quality: numerical parity against reference implementations, seeded side-by-side media, gradient and trainability checks, checkpoint round trips and repository tests. Use it whenever a claim about correctness, parity or quality needs evidence.

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit 2630133 · 11 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

QAI Index

71/QI

We rate every listed skill the same way, from 0 to 100.

A guide to compare by, not a verdict on the skill.

How it's scored

Install

Each tab says whether it installs commit 2630133, the one we checked, or the latest version.

OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. NVIDIA/skills/skills/fastgen-validate (opens in a new tab)

Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.

Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie and Amp. With This project, Any agent also reaches Antigravity and Claude Code reaches Cline. Kiro needs the folder copied by hand.

Pinned to commit 2630133, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 2630133f22e357f2005886567a39eddcc1b520e2 &&git -C "$tmp" sparse-checkout set -- skills/fastgen-validate &&git -C "$tmp" checkout -q 2630133f22e357f2005886567a39eddcc1b520e2 &&mkdir -p .claude/skills &&mkdir .claude/skills/fastgen-validate &&cp -R "$tmp"/skills/fastgen-validate/. .claude/skills/fastgen-validate/ &&rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs

Pinned to commit 2630133, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make fastgen-validate.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 2630133f22e357f2005886567a39eddcc1b520e2 &&git -C "$tmp" sparse-checkout set -- skills/fastgen-validate &&git -C "$tmp" checkout -q 2630133f22e357f2005886567a39eddcc1b520e2 &&out="$(mktemp -d)" &&cp -R "$tmp"/skills/fastgen-validate "$out"/fastgen-validate &&(cd "$out" && zip -qr - fastgen-validate) > fastgen-validate.zip &&rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose fastgen-validate.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit 2630133, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 2630133f22e357f2005886567a39eddcc1b520e2 &&git -C "$tmp" sparse-checkout set -- skills/fastgen-validate &&git -C "$tmp" checkout -q 2630133f22e357f2005886567a39eddcc1b520e2 &&mkdir -p .agents/skills &&mkdir .agents/skills/fastgen-validate &&cp -R "$tmp"/skills/fastgen-validate/. .agents/skills/fastgen-validate/ &&rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit 2630133, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 2630133f22e357f2005886567a39eddcc1b520e2 &&git -C "$tmp" sparse-checkout set -- skills/fastgen-validate &&git -C "$tmp" checkout -q 2630133f22e357f2005886567a39eddcc1b520e2 &&mkdir -p .cursor/skills &&mkdir .cursor/skills/fastgen-validate &&cp -R "$tmp"/skills/fastgen-validate/. .cursor/skills/fastgen-validate/ &&rm -rf "$tmp"

Cursor docs

Pinned to commit 2630133, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 2630133f22e357f2005886567a39eddcc1b520e2 &&git -C "$tmp" sparse-checkout set -- skills/fastgen-validate &&git -C "$tmp" checkout -q 2630133f22e357f2005886567a39eddcc1b520e2 &&mkdir -p .github/skills &&mkdir .github/skills/fastgen-validate &&cp -R "$tmp"/skills/fastgen-validate/. .github/skills/fastgen-validate/ &&rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install NVIDIA/skills skills/fastgen-validate/SKILL.md@2630133f22e357f2005886567a39eddcc1b520e2 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit 2630133, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 2630133f22e357f2005886567a39eddcc1b520e2 &&git -C "$tmp" sparse-checkout set -- skills/fastgen-validate &&git -C "$tmp" checkout -q 2630133f22e357f2005886567a39eddcc1b520e2 &&mkdir -p .gemini/skills &&mkdir .gemini/skills/fastgen-validate &&cp -R "$tmp"/skills/fastgen-validate/. .gemini/skills/fastgen-validate/ &&rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/NVIDIA/skills.git --path skills/fastgen-validate --scope workspace

Gemini CLI docs

Pinned to commit 2630133, the one we checked.

OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/NVIDIA/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 2630133f22e357f2005886567a39eddcc1b520e2 &&git -C "$tmp" sparse-checkout set -- skills/fastgen-validate &&git -C "$tmp" checkout -q 2630133f22e357f2005886567a39eddcc1b520e2 &&mkdir -p .agents/skills &&mkdir .agents/skills/fastgen-validate &&cp -R "$tmp"/skills/fastgen-validate/. .agents/skills/fastgen-validate/ &&rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add NVIDIA/skills --skill fastgen-validate

Agent Skills docs

Read SKILL.md first

Apache 2.0

Licence

3.9k

Repo stars

Folder last changed

Publisher

Files

Checked

11 Nov 2026

What it can touch

From the files and frontmatter at commit 2630133. This is how much a skill can do, not whether it is risky.

Runs shell commands
Its instructions or files give the agent commands to run on your computer.
Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Outside links we did not follow

Pattern check

Pattern check: nothing flagged · commit 2630133 · 11 Nov 2026

We checked every text file in this skill, at commit 2630133 on 11 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Outside links we did not follow

https://github.com/NVlabs/FastGen/blob/main/skills/fastgen-runtime/SKILL.md
https://github.com/NVlabs/FastGen/blob/main/skills/fastgen-inference/SKILL.md
https://github.com/NVlabs/FastGen/blob/main/skills/fastgen-train/SKILL.md
https://github.com/NVlabs/FastGen/blob/main/fastgen/networks/README.md#validate-a-new-network
https://github.com/NVlabs/FastGen/blob/main/skills/fastgen-train/references/run-contract.md#interpret-media-and-scalars-correctly
https://github.com/NVlabs/FastGen/blob/main/skills/fastgen-train/references/run-contract.md#resume-restores-state-not-the-exact-trajectory
https://github.com/NVlabs/FastGen/blob/main/scripts/README.md#fid-evaluation
https://github.com/NVlabs/FastGen/tree/main/tests
https://github.com/NVlabs/FastGen/blob/main/CONTRIBUTING.md#continuous-integration
https://github.com/NVlabs/FastGen/tree/e0a92619fc56daf4dfa081273c7729c045bf1dcc

Show 13 more

https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/networks/noise_schedule.py#L2123
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/networks/noise_schedule.py#L2186
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/networks/noise_schedule.py#L2277
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/networks/noise_schedule.py#L2311
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/tests/test_noise_schedule.py#L122
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/tests/test_noise_schedule.py#L1671
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/methods/distribution_matching/dmd2.py#L790
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/methods/distribution_matching/dmd2.py#L830
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/utils/checkpointer.py#L578
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/scripts/inference/inference_utils.py#L452
https://github.com/NVlabs/FastGen/blob/e0a92619fc56daf4dfa081273c7729c045bf1dcc/fastgen/utils/checkpointer.py#L405
https://docs.nvidia.com/fastgen
https://app.intigriti.com/programs/nvidia/nvidiavdp/detail

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses
The open format from agentskills.io, held to the strictest version of each rule among the agents we check.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
- Note
  Reference files that SKILL.md doesn't link: BENCHMARK.md, evals/files/noise_schedule_source.md, evals/files/training_evidence_source.md and skill-card.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (152 lines), evals/files/noise_schedule_source.md (221 lines), evals/files/training_evidence_source.md (157 lines) and skill-card.md (121 lines). B5
  Fix: Add a short list of the sections at the top of each.
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
- Note
  Reference files that SKILL.md doesn't link: BENCHMARK.md, evals/files/noise_schedule_source.md, evals/files/training_evidence_source.md and skill-card.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (152 lines), evals/files/noise_schedule_source.md (221 lines), evals/files/training_evidence_source.md (157 lines) and skill-card.md (121 lines). B5
  Fix: Add a short list of the sections at the top of each.
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
- Note
  The description is 293 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
  Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
  Reference files that SKILL.md doesn't link: BENCHMARK.md, evals/files/noise_schedule_source.md, evals/files/training_evidence_source.md and skill-card.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: BENCHMARK.md (152 lines), evals/files/noise_schedule_source.md (221 lines), evals/files/training_evidence_source.md (157 lines) and skill-card.md (121 lines). B5
  Fix: Add a short list of the sections at the top of each.
OpenAI (Codex & API)Passes
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
VS Code & CopilotPasses
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.

SKILL.md

Read SKILL.md on GitHub

Files

11 files

Path	Size
BENCHMARK.md (opens in a new tab)	9.9 KB
SKILL.md (opens in a new tab)	4.1 KB
evals/config.yml (opens in a new tab)	135 B
evals/evals.json (opens in a new tab)	7.2 KB
evals/files/noise_schedule_source.md (opens in a new tab)	9.9 KB
evals/files/parity-manifest.json (opens in a new tab)	1.2 KB
evals/files/reload-evidence.json (opens in a new tab)	2.1 KB
evals/files/rf-validation.json (opens in a new tab)	991 B
evals/files/training_evidence_source.md (opens in a new tab)	7.4 KB
skill-card.md (opens in a new tab)	7.5 KB
skill.oms.sig (opens in a new tab)	5.9 KB

More from NVIDIA/skills

Skill	QAI Index	What it can touch	Pattern check	Licence	Updated
accelerated-computing-cudfOfficial NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads. 64/QI Runs shell commands +2 more Pattern check: Nothing flaggedCC BY 4.0 and Apache 2.0Updated 15 Oct 2026	64/QI	Runs shell commands Names web addresses +1 more	Pattern check: Nothing flagged	CC BY 4.0 and Apache 2.0	15 Oct 2026
ambient-healthcare-agent-with-nemotron-voice-agentCustomize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend. 63/QI Touches credentials +5 more Pattern check: 1 item to reviewCC BY 4.0 and Apache 2.0Updated 2 Oct 2026	63/QI	Touches credentials Runs shell commands +4 more	Pattern check: 1 item to review	CC BY 4.0 and Apache 2.0	2 Oct 2026
amc-run-rtsp-calibrationCalibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration. 61/QI Touches credentials +4 more Pattern check: Nothing flaggedApache 2.0Updated 4 Sept 2026	61/QI	Touches credentials Runs shell commands +3 more	Pattern check: Nothing flagged	Apache 2.0	4 Sept 2026
amc-run-sample-calibrationRun end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'. 61/QI Downloads software +4 more Pattern check: Nothing flaggedApache 2.0Updated 4 Sept 2026	61/QI	Downloads software Runs shell commands +3 more	Pattern check: Nothing flagged	Apache 2.0	4 Sept 2026
amc-run-video-calibrationCalibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`. 61/QI Runs shell commands +3 more Pattern check: Nothing flaggedApache 2.0Updated 4 Sept 2026	61/QI	Runs shell commands Reaches the network +2 more	Pattern check: Nothing flagged	Apache 2.0	4 Sept 2026
amc-setup-calibration-stackLaunch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key. 53/QI Touches credentials +3 more Pattern check: 1 item to reviewApache 2.0Updated 14 Jul 2026	53/QI	Touches credentials Runs shell commands +2 more	Pattern check: 1 item to review	Apache 2.0	14 Jul 2026

All skills in NVIDIA/skills

Other Testing & QA skills

Same category, most repo stars first.

Skill	QAI Index	What it can touch	Pattern check	Licence	Updated
finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work obra/superpowers 74/QI Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 12 Aug 2026	74/QI	Runs shell commands Reaches the network	Pattern check: Nothing flagged	MIT	12 Aug 2026
systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes obra/superpowers 79/QI Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 3 Nov 2026	79/QI	Runs shell commands Bundles scripts	Pattern check: Nothing flagged	MIT	3 Nov 2026
agent-runtime-gateway-smoke-testVerify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection. affaan-m/ECC 77/QI Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 10 Oct 2026	77/QI	Runs shell commands Reaches the network	Pattern check: Nothing flagged	MIT	10 Oct 2026
ai-regression-testingRegression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change. affaan-m/ECC 74/QI Instructions only Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	74/QI	Instructions only	Pattern check: Nothing flagged	MIT	11 Aug 2026
webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. anthropics/skills 82/QI Runs shell commands +3 more Pattern check: Nothing flaggedApache 2.0Updated 20 Apr 2026	82/QI	Runs shell commands Reaches the network +2 more	Pattern check: Nothing flagged	Apache 2.0	20 Apr 2026
ponytail-auditQuality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding explained in plain English. One-shot report, changes nothing. Use for "audit this codebase", "review the whole repo", "find bloat", "what can I delete", /ponytail-audit. DietrichGebert/ponytail 78/QI Instructions only Pattern check: Nothing flaggedMITUpdated 8 Oct 2026	78/QI	Instructions only	Pattern check: Nothing flagged	MIT	8 Oct 2026

At a glance

What it can touch

Pattern check

QAI Index

Install

Claude Code

Claude apps

Codex

Cursor

Copilot & VS Code

Gemini CLI

Any agent

What it can touch

Pattern check

Outside links we did not follow

Format check

SKILL.md

Files

More from NVIDIA/skills

Other Testing & QA skills