1,284 件 ・ 関連度順
概要と使いどころ
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
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。
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
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。
This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.
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。
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
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 live web and vertical-domain search, parallel batch search, and full-page URL extraction via AnySearch. Prefer vertical search for domain-specific or realtime queries (finance, academic, security, legal, code, travel, health, etc.); call get_sub_domains before vertical search; use batch_search when the query is ambiguous or multi-intent; use extract to turn a page into Markdown. Works anonymously with lower rate limits, or with ANYSEARCH_API_KEY for higher limits.
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。
Execute all plans in a phase with wave-based parallelization
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。
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents
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。
Scan a repo for mixed ADRs, PRDs, SPECs, and DOCs and bootstrap or merge the full .planning/ setup from them. Classifies each doc in parallel, synthesizes a consolidated context with a conflicts report, and routes to new-project or merge-milestone depending on whether .planning/ already exists.
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。
YOLO mode. Spawns 4 parallel C-suite agents (CEO, CTO, CFO, COO). Each analyzes the business from their perspective using ALL available data. Produces unfiltered Hard Truths report. After user types YOLO, autonomously runs the business for a day using /loop.
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 multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tasks, dispatches parallel agents (subagents or Agent Teams), audits completions, and ships PRs. Registry-driven — works for any user with a configured project registry.
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。
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
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。
Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, profiling, matched A/B tuning, and final validation.
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。
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
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。
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
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。
Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, comparing library and benchmark configs, resizing parallelism for a GPU allocation, or distinguishing convergence changes, semantics-preserving execution tuning, and benchmark-only shortcuts.
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 baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry, state, adaptive_hints, tool_parallelism, ACG, hint consumption, or measured rollout.
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。
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.
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。
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
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。
Generate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. Use for homolog search, UniRef30/ColabFold env searches, A3M or FASTA alignments, paired MSA search for complexes, PDB70 structural templates, hosted NVIDIA API calls, or local Docker deployment. For local deployment, download the databases in parallel with aria2c and launch via NIM_MODEL_NAME (the recommended default fast path, ~14 min vs over 80 min for the built-in downloader); a plain docker run uses the slow built-in downloader.
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。
Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".
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。
Functional programming helpers for Golang using samber/lo — 500+ type-safe generic functions for slices, maps, channels, strings, math, tuples, and concurrency (Map, Filter, Reduce, GroupBy, Chunk, Flatten, Find, Uniq, etc.). Core immutable package (lo), concurrent variants (lo/parallel aka lop), in-place mutations (lo/mutable aka lom), lazy iterators (lo/it aka loi for Go 1.23+), and experimental SIMD (lo/exp/simd). Apply when using or adopting samber/lo, when the codebase imports github.com/samber/lo, or when implementing functional-style data transformations in Go. Not for streaming pipelines (→ See `samber/cc-skills-golang@golang-samber-ro` 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。
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI, or debugging flaky/slow tests. For testify-specific APIs see `samber/cc-skills-golang@golang-stretchr-testify`; for measurement methodology see `samber/cc-skills-golang@golang-benchmark`.
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 when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.
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。
Ancient text restoration, attribution, dating, contextualization, and embedding via Aeneas (Latin) / Ithaca (Ancient Greek). Use when asked to "restore", "attribute", "date", "contextualize", "find parallels", "where was it written", "when was it written", "embed", or "analyze" an ancient text, inscription, or epigraphic document, or when the user mentions "Aeneas", or "Ithaca".
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。