# NVIDIA Skill Documentation

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/skills/_mcp/server

## Docs

- [NVIDIA-Verified Agent Skills](https://docs.nvidia.com/skills.md): Capability governance for portable AI agent skills: what skills do, how to discover them, and how verification works.
- [A Trust Pipeline for Agent Skills](https://docs.nvidia.com/skills/agent-skill-trust-pipeline.md): How scanning, evaluation, signing, and skill cards work together to make AI agent skills easier to review and safer to deploy.
- [Scan Agent Skills Before Installation](https://docs.nvidia.com/skills/scanning-agent-skills.md): Use SkillSpector to detect vulnerabilities, malicious patterns, and policy risks in AI agent skills.
- [Evaluate Agent Skills Before Publication](https://docs.nvidia.com/skills/evaluating-agent-skills.md): How SkillEvaluator measures whether a skill improves an agent's output, what to ship so it can run, and how to read the result.
- [Verify Signed Agent Skills](https://docs.nvidia.com/skills/signing-agent-skills.md): Use detached OMS signatures to verify the integrity and authenticity of published agent skills.
- [Write Skill Cards People Can Trust](https://docs.nvidia.com/skills/skill-cards.md): A skill card records the owner, intended use, risks, outputs, and references for an AI agent skill.
- [Release Checklist](https://docs.nvidia.com/skills/release-checklist.md): A practical checklist for preparing an agent skill for enterprise review and publication.
- [Advanced Installation](https://docs.nvidia.com/skills/advanced-install.md): Install, update, and remove NVIDIA skills with control over agent, scope, and non-interactive workflows.