5万 件 ・ 関連度順
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。
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale 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。
Create HTML-based video compositions, animated title cards, social overlays, captioned talking-head videos, audio-reactive visuals, and shader transitions using HyperFrames. HTML is the source of truth for video. Use when the user wants a rendered MP4/WebM from an HTML composition, wants to animate text/logos/charts over media, needs captions synced to audio, wants TTS narration, or wants to convert a website into a video.
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, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.
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。
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
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。
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
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。
Free meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.
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。
Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.
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。
Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime.
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 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.
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。
Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The 'don't do the work yourself' rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
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。
Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
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。
Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5: debugging, refactoring, changes across 2+ files, or unfamiliar code; and instruct a subagent on Opus/Sonnet/Haiku to read this skill with a non-trivial assignment. Triggers include "think like Fable", "fable-mode", "turn on discipline", "work carefully", dispatching a subagent on a weaker model, and repeated mistakes or rework in the session. NOT needed for trivial edits (rename, typo, one-liner) or purely conversational answers.
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。
Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5. Операционная дисциплина мышления Fable 5 для менее сильных моделей. Загружай в начале любой нетривиальной задачи (дебаг, рефакторинг, ≥2 файлов, незнакомый код), когда работаешь НЕ на Fable 5 — и указывай сабагенту на Opus/Sonnet/Haiku прочитать этот скилл вместе с нетривиальным заданием. Триггеры — «думай как Fable», «fable-mode», «включи дисциплину», «работай аккуратно», запуск сабагента на слабой модели, повторяющиеся ошибки/переделки в сессии. НЕ нужен для тривиальных правок (rename, опечатка, one-liner) и чисто разговорных ответов.
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。
Download media (images/videos/GIFs/audio) from Twitter/X using gallery-dl. Supports single tweet URLs, user timelines, date filtering, post count limiting, retweet filtering, video quality selection, and various media types. Use when users want to download media from Twitter/X accounts with proxy support (HTTP/SOCKS4/SOCKS5) and cookie authentication. Supports downloading tweet text with links alongside media.
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 prompts and offer depth / token-budget options BEFORE answering. Use this skill when the user wants to control token usage, tune response depth, choose between short and long answers, or optimize their prompt. Triggers on: "tokens", "token budget", "depth", "consumption", "short vs long answer", "how many tokens", "save tokens", "answer at 50%", "give me the short version", "I want to control how much you use", "tune your response", "presupuesto de tokens", "profundidad", "responde al 50%", "dame la versión corta", or any equivalent phrasing in English or Spanish. If the user wants to control length, detail or depth -- even without mentioning tokens explicitly -- this skill applies.
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 UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
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 working with Resend email platform - routes to specific sub-skills for sending, receiving, audiences, or broadcasts.
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 receiving emails with Resend - setting up inbound domains, processing email.received webhooks, retrieving email content/attachments, or forwarding received emails.
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 setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing security measures to prevent prompt injection attacks.
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 sending transactional emails (welcome messages, order confirmations, password resets, receipts), notifications, or bulk emails via Resend API.
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。