Agent Skills / IP top level

HSB · Agent Skill

IP top level

Create or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def generation or validation.

Install

npx skills add nvidia/skills --skill hsb-ip-create-top

Add --agent cursor, --agent claude-code, --agent codex, or --agent kiro-cli to target a specific agent.

At a glance

Skill	hsb-ip-create-top
Product	Holoscan Sensor Bridge
Version	0.1.0
License	Apache-2.0
Compatibility	Targets HSB IP rev 16'h2604; backward-compatible with 16'h2603. Prefer live HSB IP source when available; warn on unknown revisions. Designed to work standalone or as a companion to hsb-ip-def.
Tags	holoscan, hsb, fpga, systemverilog, top-level
Source	NVIDIA/skills ↗

This skill is ready for commercial/non-commercial use.

Owner

NVIDIA

Use Case

Developers and engineers creating fixed-format SystemVerilog top-level scaffolds that instantiate HOLOLINK_top from validated HSB definition files.

Deployment Geography for Use

Global

Requirements / Dependencies

Requires API Key or External Credential: [No]
Credential Type(s): [None]

Do not include secrets in prompts/logs/output; use least-privilege credentials; rotate keys as appropriate.

Known Risks and Mitigations

Risk: Review before execution as proposals could introduce incorrect or misleading guidance into skills.
Mitigation: Review and scan skill before deployment.

Reference(s)

• Fixed FPGA_top.sv Format
• Handoff Contract
• Live HSB IP Source Policy
• AgentSkills.io Specification

Skill Output

Output Type(s): [Code, Configuration instructions]
Output Format: [SystemVerilog source file]
Output Parameters: [1D]
Other Properties Related to Output: [None]

Evaluation Agents Used

• claude-code
• codex

Evaluation Tasks

Evaluated against 3 internal evaluation tasks using the NVSkills-Eval external profile.

Evaluation Metrics Used

Reported benchmark dimensions:

• Security: Checks whether skill-assisted execution avoids unsafe behavior such as secret leakage, destructive commands, or unauthorized access.
• Correctness: Checks whether the agent follows the expected workflow and produces the correct final output.
• Discoverability: Checks whether the agent loads the skill when relevant and avoids using it when irrelevant.
• Effectiveness: Checks whether the agent performs measurably better with the skill than without it.
• Efficiency: Checks whether the agent uses fewer tokens and avoids redundant work.

Underlying evaluation signals used in this run:

• security: Checks for unsafe operations, secret leakage, and unauthorized access.
• skill_execution: Verifies that the agent loaded the expected skill and workflow.
• skill_efficiency: Checks routing quality, decoy avoidance, and redundant tool usage.
• accuracy: Grades final-answer correctness against the reference answer.
• goal_accuracy: Checks whether the overall user task completed successfully.
• behavior_check: Verifies expected behavior steps, including safety expectations.
• token_efficiency: Compares token usage with and without the skill.

Evaluation Results

Dimension	Num	claude-code	codex
Security	3	100% (+0%)	100% (+0%)
Correctness	3	70% (+33%)	94% (+46%)
Discoverability	3	63% (+26%)	84% (+35%)
Effectiveness	3	59% (+43%)	83% (+60%)
Efficiency	3	66% (+38%)	76% (+34%)

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal team to ensure this skill meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

(For Release on NVIDIA Platforms Only)
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

All skills →