Install
npx skills add NVIDIA/skills --skill doca-pcc
Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.
What does the doca-pcc skill do?
Description from the SKILL.md in the source repository.
Questions about doca-pcc
What does the doca-pcc skill do?
Use this skill when the user is doing hands-on host-side DOCA PCC work to load a CUSTOM Programmable Congestion Control algorithm onto a BlueField DPU — creating per-port `doca_pcc` contexts, loading a `dpacc`-compiled `doca_pcc_app` onto the `doca_dev` for the RoCE-bearing port, parameterizing it, walking triple-axis capability discovery (DOCA cap-query + DPA-capable BlueField + firmware custom-PCC slot enabled), or debugging `DOCA_ERROR_*` from `doca_pcc_*`. Trigger even without explicit "DOCA PCC" phrasing — implicit forms include "loading my own congestion control onto a BF port", "DOCA_ERROR_NOT_PERMITTED on algorithm load", "DOCA_ERROR_DRIVER when I attach my custom algorithm", "my custom rate-update isn't affecting RoCE traffic", or "load succeeds but no on-wire change". Refuse and route elsewhere for DPA-side algorithm-body design, the `pcc_counters` CLI, default factory PCC in ConnectX firmware, or setting up the RDMA / RoCE traffic — those belong to other skills.
How do I install doca-pcc?
In a terminal: npx skills add NVIDIA/skills --skill doca-pcc. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.
Which agents can use doca-pcc?
Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.
Is doca-pcc safe to use?
Our automatic check found no risky patterns (piped shell scripts, hidden characters, secret access, prompt overrides). It is not a full audit – read the SKILL.md and any scripts before installing.
More skills from NVIDIA/skills
Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small launches, host fallbacks, or large intermediates. …
Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on wp.Tape gradients, so treat any misbehavior of such a workflow …
Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or …
Add agent-ready vision capabilities — dense captioning, detection, search, alerting, summarization — to an agent or application through a customizable, self-contained vision stack built on the NVIDIA VSS Blueprint.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models.
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging.
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels.
Related skills in Design & Media
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays.
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free …
Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML.
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI.
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI.
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable …