2,868 件 ・ 関連度順
概要と使いどころ
Execute advanced LLM Jailbreaking techniques using roleplay, nested environments (virtual machines), and complex personas to completely bypass safety constraints and ethical alignments embedded in AI 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。
Systematically bypass LLM safety filters and content moderation systems using advanced jailbreaking techniques. Use this skill when testing AI systems for safety alignment robustness, evaluating content moderation effectiveness, or conducting authorized AI red team assessments. Covers role-play attacks, few-shot manipulation, encoding bypass, multi-modal exploitation, and automated jailbreak discovery methods.
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。
White-box source code security review structured around OWASP ASVS 5.0 (427 verification requirements across 16 chapters). Reads and understands application source code to build a security-aware knowledge base that enriches all downstream skills. Covers: tech stack identification, route/endpoint mapping, authentication and authorization architecture, dangerous function patterns, source-to-sink data flow tracing, IaC review, dependency analysis, ASVS compliance mapping, and LLM integration security (prompt injection, tool abuse, output handling, RAG poisoning, MCP server patterns). When LLM/AI framework usage is detected, automatically reviews OWASP LLM Top 10 patterns from source code and chains into /ai-redteam with white-box context for live endpoint testing. Chains into /pentester, /threat-modeling, /web-exploit, /api-security, /cloud-security, /analyze-cve, /credential-audit, and /ai-redteam — providing white-box context that transforms black-box testing into targeted, informed 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。
AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for issue filing.
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 or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
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。
Configure and manage NPSP Enhanced Recurring Donations (ERD): enable ERD mode, define schedule objects, configure installment behavior, set status automation thresholds, and interpret the Upcoming Installments UI. NOT for NPSP object and field reference — use data/npsp-data-model. NOT for payment gateways — use architect/fundraising-integration-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。
Education Cloud (EDA — Education Data Architecture) setup: student success hub, advisor workflows, enrollment management, academic data model. NOT for the EDA object model in depth (Affiliations, Course_Connection__c) — use data/eda-data-model-and-patterns. NOT for SIS enrollment sync — use integration/sis-integration-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。
Use this skill for Salesforce Order Management (OMS) tasks: order lifecycle, OrderSummary creation and status, FulfillmentOrder creation and routing, returns, exchanges, cancellations, and platform event subscriptions. Trigger keywords: order management, OrderSummary, FulfillmentOrder, ReturnOrder, ensure-funds, ensure-refunds, submit-cancel, submit-return, adjust-item-submit. NOT for split-order routing or Omnichannel Inventory design — use architect/order-management-architecture. NOT for loading historical orders — use data/commerce-order-history-migration.
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 custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
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 local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.
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。
环境安装与准备：把部署环境从零安装就绪——mindiesd 编译安装（本地昇腾直装 / SSH 推远端容器 / Docker 镜像直装）与三方推理框架全栈安装（vLLM-Omni 源码构建、DiffSynth-Engine 部署、 LightX2V editable 部署），并负责模型权重确认与下载（下载前先确认远端是否已存在）。不含特性使能与验证 （framework-integration）与 profiling（profiling-collect）；SSH 工具由 remote-access 提供。 当用户需要安装 MindIE-SD、源码构建/直装 vLLM-Omni 或 LightX2V（editable + PLATFORM=ascend_npu）、 或确认/下载模型权重时使用此技能； 即使用户只提到"把代码推到服务器""在容器里装 vllm 全栈""准备 lightx2v 调优环境"而未说昇腾， 只要上下文涉及环境安装与准备都应触发。由 model-auto-optimization S0 与 dev-workflow 部署阶段指引加载。
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。
Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.
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 production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
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。
Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.
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。
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python 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。
vLLM: high-throughput LLM serving, OpenAI API, quantization.
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。
Especialista em BullMQ para filas de jobs com Redis, processamento em background e execução confiável de operações assíncronas em aplicações Node.js/TypeScript. Use quando: bullmq, bull queue, redis queue, background job, job queue.
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。
Framework RLHF de alta performance com aceleração Ray+vLLM. Use para treinamento PPO, GRPO, RLOO, DPO de modelos grandes (7B-70B+). Construído em Ray, vLLM, ZeRO-3. 2× mais rápido que DeepSpeedChat com arquitetura distribuída e compartilhamento de recursos 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。
Implementa e treina LLMs usando LitGPT da Lightning AI com 20+ arquiteturas pré-treinadas (Llama, Gemma, Phi, Qwen, Mistral). Use quando precisar de implementações limpas de modelos, entendimento educacional de arquiteturas ou fine-tuning de produção com LoRA/QLoRA. Implementações em arquivo único, sem camadas de abstração.
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。
Plataforma de observabilidade para LLM com rastreamento, avaliação e monitoramento. Use ao depurar aplicações LLM, avaliar saídas de modelos em datasets, monitorar sistemas em produção ou construir pipelines de testes sistemáticos para aplicações de IA.
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。
Otimiza inferência de LLM com NVIDIA TensorRT para máxima vazão e latência mínima. Use para implantação em produção em GPUs NVIDIA (A100/H100), quando você precisa de inferência 10-100x mais rápida que PyTorch, ou para servir modelos com quantização (FP8/INT4), batching em voo e escalabilidade multi-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。
Plataforma de observabilidade de IA de código aberto para rastreamento de LLM, avaliação e monitoramento. Use ao debugar aplicações de LLM com rastreamentos detalhados, executar avaliações em datasets ou monitorar sistemas de IA em produção com insights em tempo real.
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。
Avalia LLMs em mais de 60 benchmarks acadêmicos (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use quando benchmarking de qualidade de modelo, comparação de modelos, relatório de resultados acadêmicos ou rastreamento de progresso de treinamento. Padrão da indústria usado por EleutherAI, HuggingFace e laboratórios principais. Suporta HuggingFace, vLLM, APIs.
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。
Analyzes and generates llms.txt files -- the emerging standard for helping AI systems understand website structure and content. Can validate existing llms.txt files or generate new ones from scratch by crawling the site.
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。