「mode」の検索結果

Modern Angular UI patterns for loading states, error handling, and data display. Use when building UI components, handling async data, or managing component states.

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。

Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns.

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。

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world 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。

Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.

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 the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

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 internal maintenance and feature work in the nuxt-ui-tools repository. It explains the repository operating model, exact placement rules, how runtime domains relate, how features should be structured and extended, how consumer skills must be maintained, and what to keep in sync when changing the library.

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 implementing, refactoring, or extending the internal table runtime inside this repository. Covers the current architecture layers, state model, composable flow, where different responsibilities live, how to add features cleanly, and what kinds of refactors are encouraged.

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 importing Excel, CSV, or pasted rows with nuxt-ui-tools as a package consumer. Covers defineSpreadsheetSchema (typed context, chained text/number/date/boolean/select columns, columns depending on the columns above (options, defaults, rules per row), groups and dynamic groups built from the context, exact matching, option sources shared with forms, unknown-value policies, rules and levels, validate, row identity with duplicates and stored records, output), useSpreadsheetImport (headless models, onSubmit with batches and rejections), the UiSpreadsheetImport* parts, useSpreadsheetSteps with custom steps, and the ready-made UiSpreadsheetImport wizard.

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 previewing files with nuxt-ui-tools as a package consumer. Covers mounting UiFilePreviewProvider, opening one file or a gallery with useFilePreview() or useNuxtApp().$filePreview, file descriptors (URL, File/Blob, or a function that returns a signed URL), options (index, mode, gallery, loop, pdf page, callbacks), the returned handle, the built-in renderers (image, video, audio, PDF, text/JSON, CSV, Markdown, Office and archive fallbacks), renditions, download and custom header actions, the markdown render hook, custom renderers with defineFilePreviewRenderer and UiFilePreviewTools, theming tokens, and how the upload field uses the preview.

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。

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

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。

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

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。

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

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。

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

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。

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

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。

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

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。

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

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。

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

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 run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual 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。

Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.

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。

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

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 PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

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 LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

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。