6,470 件 ・ 関連度順
概要と使いどころ
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。
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。
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。
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。
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
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。
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU 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。
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。
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
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。
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
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。
Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.
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。
Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.
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。
Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.
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。
Build premium scroll-driven web pages and product showcases inspired by high-end app, hardware, and product interaction patterns. Use for Raycast-like, Apple-like, NVIDIA-like, RTX/GPU, SaaS, AI browser, parallax, sticky scroll, pinned reveal, Three.js GLB model, Web Audio sound effect, responsive accessibility, and performance-safe frontend requests.
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。
Mantém coerência visual entre peças geradas por IA — seed, modelo fixo, referência de estilo e biblioteca de prompts da marca. Use quando o usuário disser "as peças não parecem da mesma campanha", "manter o estilo", "consistência", "cada imagem saiu diferente", "padronizar o visual gerado". É o problema mais difícil de geração por IA em escala.
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。
Review or refactor an existing SKILL.md and its bundled resources — a smaller always-loaded core, conditional references, preserved behavior, lean/guided consumer profiles, and an A/B protocol to compare a candidate with the previous version. Use when a skill repeats itself, loads references on every run, triggers too broadly or misses legitimate requests, or needs its efficiency measured across models. Do NOT use for writing a new skill from scratch, refactoring application code, translating a skill verbatim, or performing the target skill's own task.
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 the user wants to set up pwdev-feat in a project — 'inicializar o pwdev-feat', 'configurar o feat', 'init feat workspace' — choosing language, model profile and the optional audit trail, and creating the .planning/feat/ workspace. Do NOT use to analyze the codebase (feat-map), to write the project instructions file (feat-setup) or to create plans.
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 the user wants a backend-only action plan — API endpoints, services, models, migrations, jobs and their tests — 'plano de backend para o endpoint X', 'plan the orders API'. Writes .planning/feat/features/{slug}/plan.md with the PWDEVIA method. Do NOT use for UI work (feat-frontend), full features spanning backend and UI (feat-feature), writing code (feat-exec) or quick 1–3 file fixes (feat-quick).
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。
Build Model Context Protocol (MCP) servers and tools that extend Claude's capabilities with custom functions, data sources, and integrations. Use when creating custom MCP servers, implementing tools for Claude, building integrations with external services, creating data source connectors, implementing custom functions, or extending Claude's capabilities with domain-specific tools.
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。
Design scalable, normalized database schemas with proper relationships, indexes, constraints, and migration strategies for relational and NoSQL databases. Use when designing database schemas, planning table relationships and foreign keys, creating indexes for query optimization, defining constraints and validations, designing data models for scalability, planning database migrations, choosing between SQL and NoSQL, implementing sharding strategies, optimizing query performance, or establishing data integrity rules.
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。
Design clean, scalable, and maintainable REST and GraphQL APIs following industry best practices. Use when designing public or internal APIs, planning endpoint structures, defining request/response contracts, establishing versioning strategies, implementing authentication patterns, designing data models, creating API documentation, ensuring consistent error handling, optimizing for performance, or establishing service contracts between microservices.
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。
Architect scalable backend services using layered architecture, dependency injection, middleware patterns, service classes, and separation of concerns. Use when building API services, implementing business logic layers, creating service classes, setting up middleware chains, implementing dependency injection, designing controller-service-repository patterns, handling cross-cutting concerns, creating domain models, implementing CQRS patterns, or establishing backend architecture standards.
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。
Three-axis orchestrator: (1) clean section boundaries — naming, routes, views, ViewModels, DB ownership, cross-section access; (2) internal cohesion — no EF in service layer, caching in service only, proper interfaces, reusable ViewComponents, architecture-test coverage; (3) focused tests — grouped under the section, covering invariants/negatives/triggers, pruned of redundancy. Push-and-bot-review loop. Use when a sizable PR landed, a section shows arch drift, or /pr-review returned a non-trivial violation list. Camps is the gold-standard reference.
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。
Review a local diff or PR for unnecessary durable surface: new files, public types, interface methods, DTOs/view models, helpers, routes, DI registrations, services, repositories, and dependencies that should reuse existing owners 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。