5,188 件 ・ 関連度順
概要と使いどころ
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.
日本語の概要は準備中です。原文の説明を表示しています。
Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence packs to MLflow. Use after inference, including NV-Generate runs; not for live training tracking, model registration, or clinical use.
日本語の概要は準備中です。原文の説明を表示しています。
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — translating the consumer's own application, job, or deployment config into an in-memory FabricConfig, choosing the single-invocation convenience API or an explicitly started runtime, validating with plan and doctor, and consuming normalized results, artifacts, and telemetry.
日本語の概要は準備中です。原文の説明を表示しています。
Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.
日本語の概要は準備中です。原文の説明を表示しています。
Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Use for Auto Setup; not for extraction or profile edits.
日本語の概要は準備中です。原文の説明を表示しています。
WARNING: guides IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets); every mutating step is governed by doca-hardware-safety (window, rollback). BlueField-4 only: BlueField-3 bring-up is doca-bf3-deployment. Use this skill for BlueField-4 (BF4) day-1 platform bring-up from the BMC: installing the BlueField/DOCA bundle ISO onto the DPU (Grace, the Arm complex) over UEFI HTTP Boot, PXE, or Redfish Virtual Media; the PLDM firmware-update flow (BMC, NIC firmware, SBIOS, ERoT) via the Redfish UpdateService and pldmtool; and a Grace Ubuntu image with optional cloud-init. Trigger on BlueField-4/BF4 bring-up phrasings even without "BF4": {bring up my new BlueField-4}, {the BlueField ISO will not boot over HTTP from the BMC}, {attach BF4 virtual media via Redfish}, {BF4 firmware Task stuck at Running}, {prepare a BlueField-4 host: platform support, version alignment, safest first smoke test}. Application launch and library APIs belong to other skills.
日本語の概要は準備中です。原文の説明を表示しています。
Operate NVIDIA DOCA Management Service on a BlueField, Arm/x86 host, or Kubernetes pod: from DOCA 3.5 the local `dms-cli` (one command per YANG path, no server), and the `dmsd` + `dmspe` service: choose deployment and authentication, configure `-allowed_users` and `dmsgroup`, use gNMI Get/Set/Subscribe, run supported gNOI workflows, and debug frontend/backend failures. Trigger even without "DMS" for "manage a remote BlueField over gRPC", "gNOI reboot from orchestrator", or fleet-management requests. SAFETY: reboot, OS install, factory-reset, and managed-file deletion are destructive and require target-bound explicit confirmation; never invoke them speculatively. Route installation and library/API build questions elsewhere, and route turnkey aggregation to the externally-productized DOCA Telemetry Service.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when the user is invoking the DOCA PCC Counters tool — the `pcc_counters.sh` bash script under the DOCA tools directory — to arm and read the fixed firmware/hardware PCC (Programmable Congestion Control) diagnostic counters (CNP, RTT, WRED-drop, etc.) on a ConnectX / BlueField device via mst + the mlx5 debugfs `diag_cnt` interface. The script takes two positional args — `set | query` and an mst device path — with no `--help` or subcommands. Trigger even without "pcc_counters.sh" or "PCC counters": "how do I read the CNP / RTT / WRED-drop counters", "PCC counter stuck at zero", "the script says Bad Device", or "is congestion control dropping packets on this port?". Route elsewhere for writing a custom PCC algorithm (doca-pcc), factory firmware PCC config, DOCA install, or fleet-wide CC tuning.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill for OpenFold3, NVIDIA's BioNeMo NIM microservice for biomolecular structure prediction. Invoke whenever the user mentions OpenFold3 or needs protein, protein-ligand, protein-DNA/RNA, or multi-chain complex prediction with the hosted NVIDIA API or local Docker NIM. Covers endpoint choice, auth, request payloads, output artifacts, confidence scores, and local container setup.
日本語の概要は準備中です。原文の説明を表示しています。
Create a reviewable Agent Skill package from mature curated wiki pages. Use when turning verified vault knowledge into a reusable skill. Reads the vault and writes only to a review directory; it does not install skills.
日本語の概要は準備中です。原文の説明を表示しています。
Convert user conversation into macro workflow requests and present curated clarification or final artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan, design-doc folder, roadmap tree, active implementation-status file, repo cleanup/filesystem plan, ADR/decision log, ideas inbox, or linked planning knowledge base; reconcile Done/In Progress/Next state; resume work from TODO/handoff state; move resolved questions into decisions; promote ideas into formal plan artifacts; or keep plan documents and file-structure planning internally consistent without making this project-specific.
日本語の概要は準備中です。原文の説明を表示しています。
Draft task-scoped detail artifacts and a detail packet as reply content for script-owned workflow import.
日本語の概要は準備中です。原文の説明を表示しています。
Verify a CCB execution round and produce a machine-readable round result artifact.
日本語の概要は準備中です。原文の説明を表示しています。
Diagnose CCB runtime, mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries. Use when the user asks what is broken, which agent is stuck, whether CCB is mounted, why a reply did not arrive, or what to check first.
日本語の概要は準備中です。原文の説明を表示しています。
Diagnose and recover CCB communication and reply delivery stalls. Use when a user reports a missing CCB_REPLY, stuck ask, agent stuck busy/delivering, queued work behind an active job, cancelled/incomplete reply, empty artifact, callback not continuing, duplicate retry after success, or a CCB mailbox/communication backend that appears stuck.
日本語の概要は準備中です。原文の説明を表示しています。
Golang concurrency design — goroutine lifecycle and leak prevention, channels and `select`, channel ownership and direction, `sync.Mutex`/`RWMutex`/`sync.Map`/`sync.Once`/atomics, `errgroup`, `singleflight`, worker pools, and fan-out/fan-in pipelines. Use when writing or reviewing concurrent Go code, when choosing between channels and mutexes, when protecting a shared map or counter, or when a goroutine has no clear exit. Not for defensive coding unrelated to concurrency such as nil panics, slice aliasing, or numeric overflow (→ See `samber/cc-skills-golang@golang-safety` skill), and not for debugging a specific hung, crashing, or racing program after the fact (→ See `samber/cc-skills-golang@golang-troubleshooting` skill).
日本語の概要は準備中です。原文の説明を表示しています。
Dependency injection in Golang using samber/do — service containers, lifecycle management, scopes, health checks, graceful shutdown, and module organization. Apply when using or adopting samber/do, when the codebase imports github.com/samber/do or github.com/samber/do/v2, or when refactoring manual constructor injection into a DI container.
日本語の概要は準備中です。原文の説明を表示しています。
Go (Golang) naming conventions — covers packages, constructors, structs, interfaces, constants, enums, errors, booleans, receivers, getters/setters, functional options, acronyms, test functions, and subtest names. Use this skill when writing new Go code, reviewing or refactoring, choosing between naming alternatives (New vs NewTypeName, isConnected vs connected, ErrNotFound vs NotFoundError, StatusReady vs StatusUnknown at iota 0), debating Go package names (utils/helpers anti-patterns), or asking about Go naming best practices. Also trigger when the user mentions MixedCaps vs snake_case, ALL_CAPS constants, Get-prefix on getters, or error string casing. Do NOT use for general Go implementation questions that don't involve naming decisions.
日本語の概要は準備中です。原文の説明を表示しています。
Golang project layout and workspace setup — cmd/internal/pkg directory conventions, module and package naming, go.work workspaces, and essential configuration files. Use when starting a new Go project, organizing an existing codebase, setting up a monorepo with multiple packages, creating CLI tools with multiple main packages, or discussing package restructuring, package splits, or module splits. Not for restructuring existing code without a layout change (→ See `samber/cc-skills-golang@golang-refactoring` skill).
日本語の概要は準備中です。原文の説明を表示しています。
[omh] Project fact to remember across future sessions: capture one bounded durable project or product memory candidate through explicit remember, refuse, or defer review; for a past decision use decision-recall. Use when the user says: memory-new, new memory, project memory, product memory, remember this project, remember this product, do not save, do not save this token.
日本語の概要は準備中です。原文の説明を表示しています。