330건 · 관련도순
Search stored learnings from past sessions by meaning or keywords. Retrieve relevant entries in full, along with their type, confidence, and session context, to revisit earlier findings about development patterns, installation, or errors.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Investigate how an existing codebase works and document its components, connections, and file references. Combine current code findings with historical notes to produce a research document grounded in specific paths and line numbers.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon online packing, and CP constraints.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Choose Megatron Bridge training configurations for a model, GPU allocation, and training goal. Get starting commands and parallel processing adjustments, with clear distinctions between changes that affect learning behavior, execution tuning, and benchmark-only settings.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Use this skill when the user is doing hands-on NVMe-over-Fabrics storage-target work on a BlueField DPU or ConnectX NIC with DOCA STA — standing up a doca_sta DOCA Core context that accelerates the target-side NVMe-oF data path over RDMA, defining doca_sta_subsystem targets (NQN + namespaces) backed by local NVMe-PCI backend disks (doca_sta_be), checking device support via doca_sta_cap_is_supported, sizing the per-connection I/O queues, or debugging DOCA_ERROR_* from a STA call. Trigger even when the user does not say "DOCA STA" — typical implicit phrasings include "my NVMe-oF Connect never completes", "Identify Controller times out over RoCE", "16 I/O queues at depth 1024 — does this BlueField support that", "offload the nvmf target onto the DPU", or "DOCA_ERROR_IO_FAILED on an NVMe read". Refuse and route elsewhere for DOCA install, raw RDMA data movement, raw packet I/O, flow-rule programming, or initiator-side / host NVMe stack work — those belong to other skills.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use this skill when the user is doing hands-on DOCA Management programming against BlueField / ConnectX devices — standing up a management or representor context (doca_mgmt_dev_ctx / doca_mgmt_dev_rep_ctx), querying device caps (data-direct, caps-general), toggling congestion-control global status, modifying diagnostics-data, setting ICM quotas, or issuing a raw firmware command via doca_mgmt_raw_cmd with the right scope (CONFIGURATION / DEBUG_READ_ONLY / DEBUG_WRITE / DEBUG_WRITE_FULL). Trigger even when the user does not say "DOCA Management" — typical implicit phrasings include "fleet tool that walks every BlueField and reads device state", "toggle data-direct on a VF", "set an ICM quota per representor", "send a raw firmware command from C", "DOCA_ERROR_IO_FAILED from raw_cmd", or "fwctl ioctl is failing". Refuse and route elsewhere for mlxconfig direct operation, BFB / firmware reflash, streaming telemetry, doca_caps CLI snapshots, or DOCA install itself — those belong to other skills.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object model, the GPU-side handle handoff (doca_gpu_gpi_channel*), attaching GPU memory to a GPI domain, the domain and channel attribute objects, and debugging DOCA_ERROR_* from doca_gpi_* calls. Trigger even when the user does not explicitly mention "DOCA GPI" — implicit phrasings include "my CUDA kernel needs to post RDMA directly from GPU memory", "DOCA_ERROR_* from doca_gpi_gpu_channel_get", "how do I hand a GPU handle to my CUDA kernel", "how many channels can a GPI domain hold", or "GPU kernel driving RDMA without the host CPU on the path". Refuse and route elsewhere for the doca-gpunetio Send/Receive surface, the doca-rdma queue lifecycle, DPA-side initiation (doca-rdmi), or the CUDA programming model — those belong to other skills.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build custom emulated PCIe devices that a host recognizes as peripherals while BlueField DPU code handles their operation. Get guidance on DOCA sub-library selection, capability checks, setup within an installed environment, and debugging device visibility or driver binding.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build and troubleshoot data transfers with DOCA RDMA, which accesses remote memory over a network adapter. Start from installed samples, choose connection methods and permissions, check device capabilities, and investigate missing completions or queue errors.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Load and configure a custom congestion control algorithm on a BlueField DPU from the host. The skill guides port attachment, capability checks, and troubleshooting when loading fails or the algorithm has no effect on RoCE traffic.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Find authoritative NVIDIA DOCA documentation, sample locations, installed library version references, and replacements for outdated documentation links. Use the topic map to identify the right source or specialist skill without needing the DOCA source tree.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Use this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type, sizing buffers via the doca_dma_cap_task_memcpy_* queries, setting LOCAL_READ_ONLY / LOCAL_READ_WRITE permissions on source / destination doca_mmap regions (plus doca_mmap_export_* for cross-peer copies), driving the progress engine, or debugging DOCA_ERROR_* returns. Trigger even when the user does not explicitly mention "DOCA DMA" or "doca_mmap" — typical implicit phrasings include "memcpy host buffer to BlueField without using the CPU", "offload a bulk copy to the DPU", "copy returns NOT_PERMITTED on first submit", "buffer too big for one DMA task", "task submitted but no completion", or "scatter-gather copy between two memory regions". Refuse and route elsewhere for cross-network copies (DOCA RDMA), producer/consumer messaging (DOCA Comch), DOCA Core / progress-engine internals, or DOCA install — those belong to other skills.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Set up and use ReMe as a file-native long-term memory system through the reme CLI. Use when an Agent needs to detect whether ReMe is installed or running, install and configure ReMe, start or verify its local service, retrieve prior context, or write and consolidate durable memory.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Assemble a minimal redacted Attio diagnostic bundle with request fingerprints, schema context, retry evidence, and environment metadata. Use when escalating an Attio integration failure without leaking CRM data or secrets. Trigger with "Attio debug bundle", "Attio support evidence", or "collect Attio diagnostics".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Diagnose Attio REST API failures from status, structured error fields, endpoint contract, and request context without exposing customer data. Use when an Attio request returns 400, 401, 403, 404, 409, 422, 429, or 5xx. Trigger with "Attio error", "Attio request failed", or "debug Attio API".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques. it is triggered when the user requests assistance with fine-tuning a model, adapting a pre-trained model to a new dataset, or performing... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Declare bankruptcy on a long-lived AI agent's accumulated memory — audit what it currently believes, separate ground truth from stale and wrong, purge deliberately, restate the truths that survive, and log what was lost. Use when an agent keeps acting on outdated facts, contradicts itself across sessions, 'remembers' things wrong, or after a reorg/pivot makes its worldview obsolete. Produces a belief audit, a keep/correct/purge ledger, a restated ground-truth file, and the bankruptcy record.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.