Use this skill for BlueField-3 (BF3) day-1 platform bring-up via the classic RShim/BFB path: pushing a BlueField bundle (BFB) to the DPU over RShim with bfb-install from the host, the host-to-DPU TMFIFO management channel (tmfifo_net0, the 192.168.100.x convention), RShim daemon state and console-over-rshim, DPU mode selection (DPU/embedded-function vs separated-host/NIC mode) via mlxconfig, post-BFB recovery, a six-state BlueField-state classifier, and verifying the install (cat /etc/mlnx-release plus version checks). Trigger even when the user does not say "BF3" — typical phrasings include {push a BFB to my BlueField-3}, {bfb-install exited 0 but the DPU never came back}, {ping 192.168.100.2 works but ssh fails}, or {is DOCA on the host or the Arm side?}. BFB reflash, mlxconfig set, mode changes, and firmware burns are destructive: require explicit target-bound confirmation and load doca-hardware-safety. App launch, container deploy, env install, and the BF4 BMC-Redfish path route elsewhere.

Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with DOCA_EXPERIMENTAL-marked C entry points that doca-bench loads to measure a workload class its built-in modes do not cover, with doca_bench_cuda as the shipped reference exemplar. Trigger even when the user does not say "doca-bench-extension" or "doca_bench_cuda" — typical implicit phrasings include "no built-in doca-bench mode fits my workload", "how do I benchmark a CUDA GPUNetIO RX/TX kernel", "doca-bench cannot find or load my custom .so", "extension exported symbols do not match what the parent expects", "soversion mismatch after a DOCA upgrade", or "my GPU kernel hangs because stop_flag was never set". Refuse and route elsewhere for questions about which built-in doca-bench mode to pick, DOCA GPUNetIO programming semantics, CUDA toolkit installation, or contributor work on in-tree extensions — those belong to other skills.

Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.

Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.

Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).

DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk I/O with GPUDirect Storage (GDS). Do not use it for Parquet/cuDF/raw-binary or other sharded/custom layouts (see the cupynumeric-parallel-data-load skill), Zarr or object-store/S3 output, .npz or pickled archives, plain h5py without cuPyNumeric, or pure array compute such as FFT, matmul, or reductions.

Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.

Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient frontiers, scenario generation, or NVIDIA cuOpt.

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 dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.

Official 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.

小说架构设计 - 当用户需要设计小说大纲、人物档案、世界观、伏笔台账时触发。关键词：大纲、世界观、人物设定、架构设计、故事规划。

章节归档 - 每章写完后的持久化操作，包括摘要生成、记忆更新和状态报告。关键词：归档、摘要、持久化、章节完成。

Automates browser interactions for social media management across Instagram, LinkedIn, and X. Handles posting, DMs, connection requests, lead scraping, and monitoring. Use when the user needs to navigate, interact with, or extract data from approved websites.

Best practices for working on the Harness books repo. Use this skill when editing, restructuring, building, or exporting the books under `book1-claude-code/` and `book2-comparing/`, especially for Honkit, print HTML, Pandoc/XeLaTeX PDF export, build cleanup, TOC issues, naming conventions, and keeping source assets separate from generated outputs.

Guidance for querying a Slackdump SQLite3 database directly via the sqlite3 CLI.

Explains the different Slackdump sources structure.

Prepare this repository for a release. Use when asked to do pre-release checks, summarize changes since a previous tag, update WHATSNEW.md or changelog entries, update CONTRIBUTORS.md, audit command long help or docs for release-visible features, or verify release documentation consistency.

Set up and use Gonzo, the open-source terminal log analysis tool. Use when the user wants to tail, watch, stream, or analyze logs. Detects deployment platforms, generates pipe commands, and configures AI analysis.

Search A-Share/HK/US finance stock tickers and retrieve finance stock price history. Use when user asks about finance stock codes, recent price changes, or specific company finance stock info.