“parallel”的搜索结果

[omh] Parallel tool-call capability in doubt: report the version and whether MCP parallel tool calls are enabled, then apply the diff for parallel tool calls only after approval; an update only on request. Use when the user says: parallel-tools, parallel tools, hermes parallel tools setup, update hermes for parallel tools, check parallel tool support, enable parallel tool calls, verify parallel tools capability, check hermes version for parallel tools.

中文简介正在准备中。当前显示原文说明。

在Parallels的macOS虚拟环境中，验证安装、Discord消息发送、主机回复及客户机读取的完整流程，确认双向通信是否成功。

• 检查全新macOS环境的消息收发
• 升级后验证双向通信
• 排查Discord往返通信失败

在Parallels虚拟机中验证OpenClaw的安装、初始设置和更新，检查macOS、Windows及Linux的基本运行情况，并通过日志定位失败原因。

• 检查三个操作系统上的全新安装
• 验证OpenClaw更新流程
• 从现有快照恢复并重新验证

Use Parallel from the terminal to search the web, extract page content, and conduct detailed research. Add researched fields to tables, discover matching companies or other entities, and monitor sources for changes.

中文简介正在准备中。当前显示英语简介。

• Comparing services through detailed web research
• Adding headquarters and revenue to company lists
• Discovering companies that match specific criteria

Gather scholarly evidence for a scientific manuscript or research brief. Organize supporting and conflicting findings into references, study comparison tables, and claim-to-source maps, with search records and coverage reports that help identify gaps requiring further review.

中文简介正在准备中。当前显示英语简介。

• Gather background literature for a manuscript
• Compare supporting, conflicting, and null findings
• Build study comparison tables and claim-to-source maps

Research current web information with Parallel CLI and organize findings with supporting sources. The skill covers search, page extraction, detailed reports, adding sourced fields to existing lists, finding matching entities, and recurring monitoring of web changes.

中文简介正在准备中。当前显示英语简介。

• Research current information and locate academic sources
• Extract content from public webpages and PDFs
• Add sourced information to company or product lists

Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor, scatter_tensor, domain parallelism, sequence/spatial sharding, ring attention, DeviceMesh + DDP/FSDP2 hybrid parallelism, or physicsnemo.domain_parallel. Do NOT use for generic PyTorch DDP/FSDP setup without domain parallelism, picking a PhysicsNeMo model or example (use physicsnemo-discover), or non-distributed training questions.

中文简介正在准备中。当前显示原文说明。

Transform sequential Python code into parallel/concurrent implementations. Use when asked to parallelize Python code, improve code performance through concurrency, convert loops to parallel execution, or identify parallelization opportunities. Handles CPU-bound (multiprocessing), I/O-bound (asyncio, threading), and data-parallel (vectorization) scenarios.

中文简介正在准备中。当前显示原文说明。

通过 dmux 将开发、研究、测试或评审分配给多个 AI 智能体并行推进，明确职责、隔离工作目录，并在检查成果后汇总。

• 并行开展研究与实现
• 分工开发数据库、API 和界面
• 分别负责测试监控与修复

Configure large language model training with NVIDIA Megatron-Core across multiple GPUs. This skill helps choose how to split computation, set training parameters, monitor GPU efficiency, and address memory limits or unstable training.

中文简介正在准备中。当前显示英语简介。

• Planning multi-GPU training for a LLaMA-style model
• Distributing MoE model experts across GPUs
• Tuning training throughput and GPU utilization

Configure large language model training across multiple NVIDIA GPUs with Megatron-Core. The skill helps choose how to split models and workloads, set training parameters, monitor performance, and address memory shortages or low GPU utilization.

中文简介正在准备中。当前显示英语简介。

• Planning distributed training for a LLaMA-style model
• Distributing MoE expert networks across GPUs
• Tuning GPU utilization and training throughput

Set up worker environment and per-worker state for parallel pools. Use when code needs paths, environment variables, database connections, loaded libraries, or expensive objects available on workers before parfor/parfeval runs. Teaches parallel.pool.Constant, parfevalOnAll, and parpool name-value pairs. Also use when refactoring existing code that uses spmd for side-effect setup (an anti-pattern). Triggers: worker setup, pool constant, per-worker state, non-serializable, loadlibrary on workers, database connection parfor, addpath workers, spmd before parfor, worker environment, reduce parfor overhead, parfor setup, resource creation in parallel loop, cannot serialize error, undefined function or variable on workers error, load data per worker, reduce data transfer, parallelize setup, improve parallel code.

中文简介正在准备中。当前显示原文说明。

Discover MATLAB Parallel Computing Toolbox clusters on the network and in the cloud, and manage their profiles — list, inspect, import, export, set default, validate, and delete. Use whenever the user asks what parallel computing resources, clusters, or cluster profiles they have or can use — e.g. "what parallel resources do I have", "show my cluster profiles", "list clusters", "what clusters can I run on", "where can I submit jobs" — and for any work with parcluster, parallel.listProfiles, parallel.defaultProfile, MJS / Generic / HPC Server / MJSComputeCloud clusters, .mlsettings files, or profile validation. Does NOT cover job submission, parpool, or parfor.

中文简介正在准备中。当前显示原文说明。

Report concurrency and parallelism for a session — how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes) — using the Agent Monitor workflow intelligence API. Use when checking whether a multi-agent session used parallelism efficiently.

中文简介正在准备中。当前显示原文说明。

実装計画・設計書からタスクを分解し、ファイル単位の依存関係を分析して 並列実行可能な Wave に自動グルーピングするスキル。 編集ファイルが被らないタスクは全て同時並列にし、 Mermaid 依存関係図 + ディレクトリ分割された TODO ファイル群を出力する。 team-plan の後工程、team-implement の前工程として使える。 Use when: 実装計画を並列タスクに分解したい、Wave 実行順序を設計したい、 タスクの依存関係を可視化したい、分業できる部分を洗い出したい。 Triggers: "タスク分解", "並列タスク", "parallel task", "Wave 設計", "依存関係を整理", "分業", "タスクリスト作成", "並列計画", "task breakdown", "parallel plan", "wave planning", "同時に進められる"

中文简介正在准备中。当前显示原文说明。

Wave-based parallel scheduling for DAG execution. Manages execution order, resource allocation, and parallelism constraints. Activate on 'schedule dag', 'execution waves', 'parallel scheduling', 'task queue', 'resource allocation'. NOT for building DAGs (use dag-graph-builder) or actual execution (use dag-parallel-executor).

中文简介正在准备中。当前显示原文说明。

Manages git worktrees for parallel agent isolation. Creates isolated worktrees for parallel agents on parallel/{name}-{timestamp} branches, merges results with conflict detection, prunes stale metadata, and reports health status. NOT for user-initiated feature branches — use git worktree directly for that.

中文简介正在准备中。当前显示原文说明。

Organize a task into parallel work streams with clear dependencies, separate places for changes, and explicit checks. Batch independent reads and tests, coordinate concurrent work, and report completed or blocked tasks with verification results.

中文简介正在准备中。当前显示英语简介。

• Batching independent file reads and searches
• Splitting implementation across multiple agents
• Separating changes with Git worktrees

Coordinate multiple AI agents for research, development, testing, and system analysis. It guides role assignment, communication structures, parallel and sequential tasks, shared memory, progress monitoring, and recovery, bringing separate contributions into reports or coordinated development workflows.

中文简介正在准备中。当前显示英语简介。

• Gather research in parallel and compile a report
• Coordinate application design, implementation, and review
• Run unit, integration, security, and performance tests in parallel

Split a large goal into clearly bounded tasks that can run in parallel. Coordinate existing agent and worktree tools, then combine and verify the results. The skill starts only when explicitly requested.

中文简介正在准备中。当前显示英语简介。

• Splitting a large goal into parallel tasks
• Coordinating work across multiple agents
• Running tasks in separate worktrees

Investigate complex bugs by assigning competing explanations to parallel agents. Compare code evidence, contradictory findings, and confidence levels to identify likely root causes, then check that a fix resolves the original failure and related edge cases.

中文简介正在准备中。当前显示英语简介。

• Investigating bugs with several plausible causes
• Tracing failures across multiple components
• Reassessing a debugging effort that has stalled

Organize feature development across multiple agents by dividing work, assigning one owner per file, and agreeing on interfaces before implementation. Provides strategies for shared files, branches, and integration so agents can build separate parts of the same system.

中文简介正在准备中。当前显示英语简介。

• Dividing a large feature among multiple agents
• Assigning file ownership to avoid conflicting edits
• Agreeing on APIs before parallel implementation

Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.

中文简介正在准备中。当前显示英语简介。

• Pretraining Llama 3.1 8B on eight GPUs
• Configuring multi-node training with SLURM
• Enabling Float8 training on H100 GPUs

Delegate coding, analysis, planning, and reviews from Codex to Claude Code through its command-line interface. Capture responses, resume sessions, or run independent tasks in parallel, then verify changed files and test results independently.

中文简介正在准备中。当前显示英语简介。

• Delegating implementation or refactoring from Codex
• Getting another model's review of code changes
• Continuing delegated work across multiple sessions