AI Resources
NVIDIA Skills
NVIDIA Skills is a public catalog of agent skills for NVIDIA platform and developer workflows.
NVIDIA presents the catalog around NVIDIA-verified skills, with source repositories owned by product teams, skill cards, scanning, signing, daily syncs, and support for NVIDIA platform and developer workflows.
What it is
A catalog of NVIDIA agent skills
NVIDIA Skills is framed as a public skills catalog rather than a standalone assistant, with skills for areas such as cuOpt, TensorRT-LLM, NeMo tooling, NemoClaw, RAG, and video search workflows.
Why it stands out
Trust controls around reusable skills
The notable angle is the governance layer: NVIDIA describes scanning, skill cards, signing, source ownership, and verification status as ways to make reusable agent skills easier to inspect before use.
Availability
Repo, docs, and blog
Public materials include the NVIDIA/skills repository, NVIDIA Skills documentation, and a technical blog post explaining the verified-skills workflow.
Why it matters
What makes it useful
NVIDIA Skills shows reusable agent skills as cataloged capability packages with source ownership, skill cards, scanning, signing, daily syncs, and verification status. Readers can inspect the governance layer around skills rather than only loose prompt folders.
What to know
Where it fits
Open it beside other agent-skill and capability-catalog projects when comparing how reusable instructions are documented, scanned, signed, sourced, and installed before an agent uses them.
Notable points
What stands out
The source trail to check includes the skill catalog, product-owned source repositories, daily synchronization, skill cards, SkillSpector scanning, signing materials, and NVIDIA-stated compatibility with Claude Code, Codex, Cursor, and other skills-aware clients.
Before using
What to review
Which NVIDIA product area a skill belongs to and whether that skill matches the reader's actual local or enterprise workflow.
The SKILLCARD.yaml, signing files, scan documentation, source repository, and install path before relying on any individual skill.
NVIDIA's verification wording as a publisher-side review signal, not as a blanket assurance that every workflow will be suitable.
Check the original listing's documentation for current requirements, limitations, licensing and any relevant privacy or security considerations.
Reader fit
Who may find it relevant
Readers following agent skills, capability packs, and reusable workflow instructions for coding agents.
Builders working around NVIDIA tooling, GPU workflows, TensorRT-LLM, NeMo, cuOpt, RAG, video search, or secure agent sandboxing.
Less relevant for readers looking only for consumer chat tools, model rankings, or a finished agent app.
Editorial note
Why LifeHubber lists it
The source material around NVIDIA Skills gives readers a check on how agent skills are moving from informal workflow folders toward cataloged, documented, and signed capability packages.
Source links
Source materials
Reader note
About our listings
LifeHubber’s listings help you explore what’s available in AI and are not endorsements. We don’t independently verify every detail or guarantee that each listing is accurate, safe, actively maintained, or right for your needs.
What to explore next
Check a skill before giving it room to act.
Publisher signing and skill cards help with provenance. A separate scan and clear permission boundaries still matter before a skill reaches files, tools, or accounts.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Paperclip
paperclipai/paperclip
A self-hosted server and dashboard for coordinating agent teams through companies, goals, roles, issues, heartbeats, budgets, approvals, and persistent activity records.
llama-modchip
synchopate/llama-modchip
Patched llama.cpp engine and launcher for running compressed language models locally, with CPU inference and model presets for different RAM sizes.
Hermes Agent
NousResearch/hermes-agent
A Nous Research agent runtime with CLI and TUI use, persistent memory, reusable skills, scheduled automations, messaging gateways, subagents, tool configuration, provider switching, and multiple terminal backends.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
MORE ON LIFEHUBBER
Use AI on your own terms.
Explore more AI projects, stories, guides, tools and community insights across LifeHubber.