git clone --depth 1 https://github.com/NVIDIA/skills /tmp/doca-mgmt && cp -r /tmp/doca-mgmt/skills/doca-mgmt ~/.claude/skills/doca-mgmtSKILL.md
# DOCA Management **Where to start:** This skill assumes DOCA is already installed and the user is doing **hands-on management-plane work** against a BlueField / ConnectX device — typically a fleet-management or orchestration tool that needs to query or modify device-level state programmatically. Open [`TASKS.md`](TASKS.md) if the user wants to *do* something (install / configure / build / modify / run / test / debug / use); open [`CAPABILITIES.md`](CAPABILITIES.md) when the question is *what can doca-mgmt express on this version* — the management context model, the raw-command scope ladder, the sub-domain surfaces (caps-general, cc-global-status, diagnostics- data, icm-quota), version compatibility, and the safety overlay. If the user has not installed DOCA yet, route to [`doca-setup`](../../doca-setup/SKILL.md) first. ## Example questions this skill answers well The CLASSES of management-plane questions this skill is built to answer, each with one worked example. The agent should treat the *class* as the load-bearing piece — the worked example is a single instance. - **"Is `doca-mgmt` even the right surface, or do I want telemetry / bench / caps?"** — worked example: *"I'm building a fleet inventory tool — do I use doca-mgmt to query each BlueField's data-direct capability, or doca-telemetry, or doca_caps?"*. Answered by the *management-plane vs observability-plane vs read-only-CLI* selection rule in [`CAPABILITIES.md ## Capabilities and modes`](CAPABILITIES.md#capabilities-and-modes) surface-selection table. - **"How do I stand up a management context on a device (and a representor)?"** — worked example: *"open a `doca_mgmt_dev_ctx` on the device, then a `doca_mgmt_dev_rep_ctx` on a specific VF representor for caps-general programming"*. Answered by the management-context lifecycle in [`CAPABILITIES.md ## Capabilities and modes`](CAPABILITIES.md#capabilities-and-modes) + the configure walk in [`TASKS.md ## configure`](TASKS.md#configure). - **"How do I query a device capability — say, whether it supports data-direct?"** — worked example: *"create a caps-general handle, call `doca_mgmt_device_caps_general_get` on the representor context, read the data-direct flag"*. Answered by the capability-query pattern in [`CAPABILITIES.md ## Capabilities and modes`](CAPABILITIES.md#capabilities-and-modes) + the test step in [`TASKS.md ## test`](TASKS.md#test). - **"How do I modify a device-level feature flag safely?"** — worked example: *"toggle `data_direct` on a representor; capture pre-state, write, verify, prepare rollback"*. Answered by the apply-with-rollback workflow in [`TASKS.md ## modify`](TASKS.md#modify) layered on the bundle-wide hardware-safety meta-policy referenced from [`CAPABILITIES.md ## Safety policy`](CAPABILITIES.md#safety-policy). - **"What does the `doca_mgmt_raw_cmd` scope mean and which scope should I use?"** — worked example: *"I have a vendor- documented opcode for a `DEBUG_READ_ONLY` query — what scope does that need and what is the blast radius?"*. Answered by the command-scope ladder in [`CAPABILITIES.md ## Capabilities and modes`](CAPABILITIES.md#capabilities-and-modes) + the raw-command verb in [`TASKS.md ## use`](TASKS.md#use). - **"What does this `DOCA_ERROR_*` from a `doca_mgmt_*` call mean and which layer caused it?"** — worked example: *"`DOCA_ERROR_IO_FAILED` from `doca_mgmt_raw_cmd`"*. Answered by the mgmt overlay on the cross-library taxonomy in [`CAPABILITIES.md ## Error taxonomy`](CAPABILITIES.md#error-taxonomy) + the layered ladder in [`TASKS.md ## debug`](TASKS.md#debug) that escalates to [`doca-debug`](../../doca-debug/SKILL.md) and to [`doca-hardware-safety`](../../doca-hardware-safety/SKILL.md) when the cause is a device-state change. ## Audience This skill serves **external developers building fleet-management, orchestration, or device-administration tools that programmatically query and modify BlueField / ConnectX device-level state** — i.e., users whose code calls `doca_mgmt_*` (directly in C/C++, or through FFI/bindings from another language) to inspect device capabilities, toggle device feature flags, query diagnostics counters, set ICM quotas, or issue raw firmware-control commands. The canonical caller is a fleet-management agent that walks every BlueField in a data center and applies a desired-state diff. This skill is *not* for NVIDIA developers contributing to DOCA Management itself, and it is not the right surface for live performance benchmarking or stream-based observability — those belong to [`doca-bench`](../../tools/doca-bench/SKILL.md), [`doca-telemetry`](../doca-telemetry/SKILL.md), and [`doca-telemetry-exporter`](../doca-telemetry-exporter/SKILL.md). ## Language scope DOCA Management ships as a C library with the `pkg-config` module name `doca-mgmt`. The library's surface is C; the shipped samples on a real install (where present) are C. C and C++ consumers are the canonical case and the workflows in `TASKS.md` assume that path. Other-language consumers (Rust, Go, Python, …) consume the same `*.so` library through FFI or language-specific bindings; the skill's contribution in that case is to keep the management- context lifecycle, the command-scope ladder, the capability-query pattern, the version-handling rule, and the safety overlay language-neutral, and to route the agent to the public C ABI as the authoritative surface that any wrapper will eventually call. The skill does not author wrappers in any language. ## When to load this skill Load this skill when the user is doing **hands-on DOCA Management work** on a host with one or more BlueField / ConnectX devices. Concretely: - Standing up a `doca_mgmt_dev_ctx` on a `doca_dev` to inspect or modify device-level state. - Standing up a `doca_mgmt_dev_rep_ctx` on a `doca_dev_rep` (or via `doca_mgmt_dev_rep_ctx_create_by_pci_addr` when the representor is not available) to inspect or mod
>-
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.
|
|
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; VIOS records clips, AMC ingests them, then runs calibration.
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'.
Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when user has local MP4s and says 'calibrate my videos', 'run AMC on these videos', or similar. For RTSP/live streams, use amc-run-rtsp-calibration instead.
Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.