スキルを探す

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

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。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

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。

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

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。

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

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。

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

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。

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

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。

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

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。

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

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。

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

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。

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

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。

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

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。

Calculate and maintain the required change-count header when creating or updating pull requests in this repository.

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。

Help clarify human bug reports, search for duplicates, and gather diagnostic evidence separately from a concise issue draft.

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。

OpenCreator 内部 Creator Agent 的稳定运行规则，仅由应用自动安装和激活。

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。

Set up and use portless for named local dev server URLs (e.g. https://myapp.localhost instead of http://localhost:3000). Use when integrating portless into a project, configuring dev server names, setting up the local proxy, working with .localhost domains, or troubleshooting port/proxy issues.

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 building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room 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。

Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria, and implementation checklists. Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs, PRDs, acceptance criteria, or requirement matrices.

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 building cross-platform applications with Flutter 3+ and Dart. Invoke for widget development, Riverpod/Bloc state management, GoRouter navigation, platform-specific implementations, performance optimization.

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。

Enforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes files from disk. MUST be followed for all delete operations.

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。

Persistent local memory for OpenClaw agents. Use when users say: - "install memos" - "install MemOS" - "setup memory" - "add memory plugin" - "openclaw memory" - "memos onboarding" - "memory not working" - "configure memory" - "enable memory" - "upgrade MemOS" - "update memory plugin"

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。

An advanced skill for L3 autonomous loops. When the token budget nears exhaustion, the agent analyzes its ROI and autonomously drafts a negotiation request for a budget increase rather than silently failing.

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 recent merges/PRs/commits for release note content. Structured output for drafter.

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。

Takes a structured list of changes from changelog-scan and produces a clean, categorized, user-facing release notes draft. Follows project voice and conventions. Never publishes — only proposes a draft file or section.

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。

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

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。