'mbr' 검색 결과

Expert-level cell biology knowledge. Use when working with cell structure, organelles, cell signaling, cell cycle, cell division, cytoskeleton, membrane biology, vesicular trafficking, apoptosis, or cell biology techniques. Also use when the user mentions 'organelle', 'mitochondria', 'endoplasmic reticulum', 'Golgi', 'cytoskeleton', 'cell cycle', 'mitosis', 'meiosis', 'apoptosis', 'signal transduction', 'membrane potential', 'endocytosis', or 'cell migration'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Renombrado evolutivo de archivos con archivos wrapper. Permite renombrar sin rupturas drásticas — las referencias se actualizan orgánicamente mediante el uso.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Erstellt und verwendet einen anbieterneutralen semantischen Routing-Graphen aus Personas, koordinierenden Rollen, Experten und aktiven Skill-Endpunkten. Verwenden, wenn ein LLM eine Anfrage von einer Leitrolle über einen Experten zu einem Skill routen, aus einem vorhandenen Agentensystem einen portablen Persona-Router extrahieren, eine semantische Domänenkarte mit einer lexikalischen Skill-Registry kombinieren oder fehlende Verbindungen zwischen Rolle und Skill sichtbar machen soll, statt still auf einen Ersatz zurückzufallen. Auslöser sind unter anderem semantisches Persona-Routing, Persona-Umbrella, Rollen-Router, Boss-Agent-Experten-Skill-Routing, Agentenrollen-Export oder die Wiederverwendung von Personas über mehrere LLM-Anbieter hinweg.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigate malware that survives OS reinstallation by checking UEFI firmware, boot files, and Secure Boot settings. Use chipsec and supporting tools to compare trusted baselines, identify bootkit indicators, and document findings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating reinfection after OS reinstallation
• Checking unexpected Secure Boot changes
• Comparing firmware against a trusted vendor baseline

Add or modify commands handled inside Crush's embedded shell before they reach the operating system. The guidance covers command routing, input and output streams, exit codes, and cancellation so commands work with pipes, redirection, and hook timeouts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a command to Crush's embedded shell
• Modifying an existing built-in command
• Supporting pipes and output redirection

Create, configure, and troubleshoot Crush hooks, commands that run before tool execution. Use them to block or approve calls, rewrite tool input, or add context for the agent, with guidance on configuration and troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Blocking destructive shell commands
• Automatically approving read-only tools
• Adding editing reminders for the agent

Configure Crush with Bash or JSON files to choose AI providers and models, connect external tools, set permissions, and adjust behavior. Understand how project and global settings combine when customizing your working environment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up AI providers and model selections
• Connect MCP servers and language servers
• Configure tool permissions and execution hooks

Extract fields, filter records, and reshape JSON from API responses, configuration files, or logs using Crush’s built-in jq. Get help writing and debugging transformations, constructing new JSON, and formatting output for other commands.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract selected fields from API responses
• Filter JSON arrays by conditions
• Reshape configuration data or construct JSON

Add or edit skills bundled with Crush, following guidance on file placement, required metadata, compile-time embedding, and discovery tests. It also explains how built-in skills are loaded and how user skills override them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a skill bundled with Crush
• Editing an existing built-in skill
• Understanding skill discovery and overrides

Create and render TanStack Table v9 tables in Ember using tracked data and dedicated rendering components. Covers table construction, template access, lifecycle cleanup, and guidance for reusing defaults and UI across tables.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a basic table in Ember
• Connecting tracked data updates to a table
• Rendering cells and headers in templates

Create narration that fits fixed video segments or a continuous long story using one selected voice. Check speech duration and pauses when local tools are available, and adjust wording through regeneration to meet timing requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Producing narration for fixed-length video segments
• Reading a long story in one consistent voice
• Regenerating takes with timing or pause problems

Turn business and product metrics into KPI updates for weekly, monthly, or quarterly reviews. Compares actual results with targets and prior periods, includes verified explanations for changes, and states what the findings mean for operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a weekly or monthly KPI review
• Check progress toward a time-bound target
• Summarize verified reasons for metric changes

Coordinate Cloud Claw workflows from launching an agent deployment to managing its virtual machine. It routes work to focused skills for setup, starting and stopping machines, viewing logs, renewing usage, and accessing dashboards through local altllm commands.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch an agent deployment and manage it afterward
• Inspect, start, or stop an existing virtual machine
• Review logs and access a deployment dashboard

Route document tasks to specialized skills for PDFs, Word files, spreadsheets, slides, or posters. Clarify the required format, sequence multiple outputs, preserve supplied templates, and report file locations with practical checks for reviewing the results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying the final format for a document task
• Turning paper tables into Excel and a PDF report
• Selecting a skill for scientific slides or posters

Configure Megatron-Bridge to overlap communication with computation during distributed training. Review settings for tensor, data, and pipeline parallelism, check activation requirements, and use included tests to investigate configuration issues or throughput regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enable communication overlap in distributed training
• Check why tensor parallel overlap is inactive
• Investigate slower training after configuration changes

Plan and tune training for vision-language models that use MoE, a mixture of expert networks, in Megatron Bridge. Compares FSDP and 3D parallel training, with guidance on memory use, batch sizes, and performance checks using realistic image inputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a parallel training approach for a new model
• Investigating training failures and out-of-memory errors
• Comparing performance with realistic image inputs

Guides hierarchical context parallelism in Megatron-Bridge, which splits input sequences across nested GPU groups. Covers configuration, implementation locations, constraints, and log checks to help enable the feature and investigate memory errors or performance regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure hierarchical context parallelism
• Scale context parallelism beyond KV head counts
• Investigate memory errors after configuration changes

Choose how to distribute tokens, the units a model processes, across MoE model experts during training. The guide compares alltoall, DeepEP, and HybridEP by GPU hardware, parallelism scale, memory needs, and optimization stage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a MoE dispatcher for specific GPU hardware
• Establishing an alltoall baseline for initial setup
• Comparing DeepEP and HybridEP under matching conditions

Enable Megatron FSDP in Megatron-Bridge to distribute model training state across GPUs. Follow configuration and checkpoint requirements, investigate memory failures or performance regressions, and verify the setup with an existing two-GPU functional test.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Switch from DDP to Megatron FSDP
• Investigate memory failures after FSDP configuration changes
• Check checkpoint formats and incompatible settings

Configure and validate CUDA graphs in Megatron Bridge training. Choose whole-iteration or module-level capture, which records GPU operations for replay, then check compatibility constraints and compare runtime and memory use against ordinary execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose whole-iteration or module-level CUDA graph capture
• Configure graph scopes for dense or MoE training
• Investigate crashes after CUDA graph configuration changes

Convert single-node training or inference commands into multi-node Slurm batch jobs. Choose an appropriate process launch method, configure shared storage and containers, and investigate communication timeouts, launch errors, and GPU memory shortages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting a single-node command into a multi-node sbatch job
• Investigating NCCL communication timeouts
• Estimating GPU memory needs for MoE models

Configure and validate communication overlap in Megatron-Bridge for MoE models, which distribute work among expert networks. Check compatibility, compare training speed, and investigate regressions across standard dispatch, DeepEP, HybridEP, and delayed weight-gradient computation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enable expert communication overlap in MoE training
• Check compatibility before using DeepEP or HybridEP
• Compare plain overlap and delayed weight-gradient computation

Diagnose GPU out-of-memory errors during Megatron Bridge training and choose memory reduction settings. Covers fragmentation, LoRA input storage, recomputation, parallelism changes, and CPU offloading, explaining compatibility limits and potential tradeoffs between memory use and training throughput.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating GPU out-of-memory errors during training
• Reducing retained inputs in LoRA training
• Estimating memory needs before a large training job

Configure fault detection and recovery for distributed training in Megatron Bridge. The skill covers slow GPU detection, automatic restarts, job interruption handling, and checkpoint saving, with configuration examples and guidance for investigating hangs or failed recovery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configuring automatic recovery after training failures
• Detecting slow GPUs in distributed training
• Preparing for scheduled job interruptions