MCP servers and skills: search, filter by where they run, and compare.
Free MCP servers + Claude Code Skills for MSP tools - PSA, RMM, backup, M365. Local-first: your data never leaves your network.
SkillLink only★ 59
Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.
in the skill textrelease (3.10–3.13 for v4.3). - The current `cuda-version` pin (v4.3 → `13`). `rmm` and `ucxx` are distributed via the `rapidsai` channel; `holoscan`, `libholoscan`, and `libholoscan-dev
OfficialSkillApache-2.0★ 3.6k in collectionNo key
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.
in the skill textcudf.set_option("spill", True) # spill to host RAM when GPU is full ``` **RMM async allocator** (can reduce allocation overhead in pipelines with many allocations). Configure
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
in the skill textoperations stream-ordered - Follow existing RAFT/RMM patterns - No raw `new`/`delete` - use RMM allocators ## Build & Test ### Pre-flight Checks (Required Before First Build or Test) Skipping
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Who stands behind it
Who stands behind it
