2,899 件 ・ 関連度順
概要と使いどころ
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
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。
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
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。
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
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。
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。
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
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。
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
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。
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot 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。
Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.
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 asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
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。
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
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。
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
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。
Required before calling image_generate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2 through the Hive image service, billed to the user's Hive credits like an LLM call (no API key needed). Teaches the exact call shape, the quality/cost tradeoff (quality="low" is the default and cheapest), reference-image editing, how to show the result to the user with attach_file, and the failure modes (out of credits, model unavailable, moderation).
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。
Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test / stress-test / benchmark Omnigent under concurrency ("load test omnigent", "stress test the server", "how many hosts/sessions/turns can it handle", "load test real agent turns / conversations", "run a load test"). The test makes each simulated user a real omnigent host that creates host-bound sessions and drives real multi-turn conversations with a mocked LLM; it boots its own local stack (dev/loadtest/run.py). Gather inputs, run it, then read the generated summary.md and explain the latency distribution (avg/median/p95/p99, throughput, failures). NOT for single-request latency micro-benchmarks (that is dev/benchmarks/).
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 and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.
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。
帮助用户了解 Octop、解答产品与使用问题，并配置当前实例。当用户提出以下类型的问题时使用此 skill： Octop 是什么、能做什么、有哪些功能或亮点；官网、帮助文档、安装、快速开始、Docker； 专家、人格、知识库、连接器、通道、定时任务、ACP、远程桌面等概念或求助； 配置或切换 LLM 模型与 Provider；添加或管理 IM 通道（飞书、企业微信、QQ 等）； 启用或禁用 Agent Skill；管理定时任务；备份与升级；询问「octop 怎么用」「怎么配置」、 「怎么接入 xxx」「怎么换模型」「怎么加通道」「CLI 怎么用」「有没有文档」等。 即使用户只是问「Octop 是什么」或「怎么配置 octop」，也应触发此 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。
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
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。
Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC. Use for: Python questions, Python interview preparation, debugging, performance optimization, async patterns, library examples, code review, best practices, MLOps workflows, distributed computing, security implementations, and any Python development 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。
Agent management expert. ALWAYS invoke this skill when you need to list available agents, download or reference agent source code, deploy agent code to the host, or query the LLM connector matrix. Do not guess agent structures — use this skill first.
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。
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
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。
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
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。
Dense description covering ARP spoofing, LLMNR/NBT-NS/mDNS poisoning, DNS poisoning, MITM attacks, VLAN hopping, DHCP attacks, 802.1X/NAC bypass, IPv6 attacks. Tools: Bettercap, Responder, mitm6, Ettercap, Wireshark. MITRE T1557, T1040. Use when conducting internal network assessments or testing Layer 2/3 attack surface.
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。
WPA/WPA2/WPA3-Enterprise (802.1X / EAP) attack methodology — EAP method identification (PEAP-MSCHAPv2, EAP-TTLS, EAP-TLS, EAP-GTC, EAP-PWD, EAP-FAST), evil-twin RADIUS attacks with eaphammer for credential capture, MSCHAPv2 challenge-response cracking, EAP-TLS client certificate theft paths (DPAPI, NDES, AD CS auto-enrollment), supplicant validation bypass (missing server cert validation, missing CN pinning, BYOD misconfigurations), and post-capture pivots into AD via cracked domain credentials. Use for corporate Wi-Fi engagements where the network is 802.1X authenticated.
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。
Active Directory attack methodology for internal network red team engagements. Covers reconnaissance (BloodHound, PowerView, ADExplorer), credential abuse (Kerberoasting, ASREProasting, NTLM relay, LLMNR/NBT-NS poisoning), privilege escalation (ACL abuse, GPO abuse, unconstrained/constrained delegation), lateral movement (Pass-the-Hash, Pass-the-Ticket, Overpass-the-Hash, WMI/WinRM/PsExec), persistence (Golden/Silver/Diamond Tickets, DCSync, DCShadow, AdminSDHolder, Skeleton Key), forest trust attacks, ADCS abuse (ESC1-ESC15), and modern MDI/Defender for Identity evasion. Use when assessing on-prem AD, hybrid AD/Entra ID environments, or ADCS deployments.
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。