nvidia-skill-finder
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software,…
Choose or explain HSB Sensor RX packetizer fields for HOLOLINK_def.svh. Do not use for full defs, validation, or runtime APB programming.
$ npx -y skills add NVIDIA/skills --skill hsb-ip-packetizer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/hsb-ip-packetizerContext preview
The summary Claude sees to decide when to auto-load this skill.
Choose or explain HSB Sensor RX packetizer fields for HOLOLINK_def.svh. Do not use for full defs, validation, or runtime APB programming.
name: hsb-ip-packetizer
author: "Holoscan Team <holoscan-team@nvidia.com>"
description: Choose or explain HSB Sensor RX packetizer fields for HOLOLINK_def.svh. Do not use for full defs, validation, or runtime APB programming.
version: "0.1.0"
tags:
- holoscan
- hsb
- packetizer
- systemverilog
- fpga
license: Apache-2.0
compatibility: Targets HSB IP rev 16'h2604; backward-compatible with 16'h2603. Prefer live HSB IP packetizer source when available; warn on unknown revisions. Designed to work standalone or as a companion to hsb-ip-def.
metadata:
author: "Holoscan Team <holoscan-team@nvidia.com>"
team: holoscan
domain: fpga
vendor: nvidia
tags:
- holoscan
- hsb
- fpga
- packetizer
- systemverilog
languages:
- systemverilog
artifact: HOLOLINK_def.svh
hsb_ip_version: "16'h2604"Choose packetizer-related `HOLOLINK_def.svh` fields for the NVIDIA Holoscan Sensor Bridge Sensor RX path.
This skill owns only the packetizer slice of `HOLOLINK_def.svh`:
Use `hsb-ip-def` for whole-file generation, validation, comparison, and non-packetizer macros.
Prefer live HSB IP source over bundled packetizer references whenever the user's workspace provides it. The bundled references describe known rev `16'h2604` and backward-compatible rev `16'h2603`; live source is the authority for the checked-out IP.
When source is available:
1. Locate `HOLOLINK_top.sv` plus the packetizer RTL files:
2. Read `HOLOLINK_REV` and `HOLOLINK_BACKWARD_COMPAT_REV` from `HOLOLINK_top.sv` when present. 3. Verify that `HOLOLINK_top` still maps the five def fields into `packetizer_top` as documented before making source-sensitive claims. 4. If the rev is newer, unknown, or live RTL disagrees with this skill's references, state the mismatch. Trust the live RTL for explanation, avoid unsupported assumptions, and do not emit an enabled packetizer overlay unless the field mapping and RTL constraints can be verified from the live source.
When no source is available, use the bundled references as known-revision guidance and say that the answer is based on the skill's supported HSB IP rev.
Load only the reference needed for the user's task:
| File | When to load | |---|---| | `references/packetizer-def-fields.md` | Choosing or explaining `HOLOLINK_def.svh` packetizer fields, array length rules, bypass placeholders, RTL-derived constraints, or standalone SVH output formatting | | `references/packetizer-architecture.md` | Explaining packetizer blocks, data flow, clocks, APB registers, runtime-vs-def split, or why a field exists | | `references/handoff-contract.md` | Producing `packetizer_profile_overlay` YAML for `hsb-ip-def` or enforcing output-mode separation |
1. If the user is working inside a `HOLOLINK_def.svh` generation flow, use **Def-Skill Handoff**. 2. If the user asks for lines to add to an existing/new `HOLOLINK_def.svh`, use **Standalone SVH**. 3. If the user asks what a field does, why a value matters, or whether a combination is safe, use **Explain**. 4. If the user asks for APB pattern RAM programming, explain that it is runtime configuration and outside v1 generated output; load `references/packetizer-architecture.md` for the register context.
Col
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software,…
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and…
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
Calibrate 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;…
Run 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…