「ai safety」の検索結果

Azure AI Content Safety SDK for Java workflow skill. Use this skill when the user needs Build content moderation applications using the Azure AI Content Safety SDK for Java and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Azure AI Content Safety REST SDK for TypeScript workflow skill. Use this skill when the user needs Analyze text and images for harmful content with customizable blocklists and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Map current AI safety controls — filter inventory, coverage gaps, latency impact, incident history. Use when asked "what AI safety controls do we have", "find guardrail coverage gaps", or "map our filters".

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。

Martial arts as body discipline — the shared pedagogical structure across striking, grappling, and weapon arts (stance, distance, timing, ukemi, live partner work, graded ranking, and the ethical container the best schools enforce). Covers karate, judo, jiu-jitsu (Brazilian and traditional Japanese), aikido, kendo/kenjutsu, boxing, muay Thai, and wrestling at enough depth that an agent can place a user into a reasonable first-month practice and recognize the safety failures that matter most. Leans on Moshé Feldenkrais's judo background and Yang Jwing-Ming's martial scholarship for the internal-to-external bridge. Use for any query about beginning a martial art, training injury patterns, graded progression, or the ethics of combat 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。

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。

Bypass AI safety filters by encoding malicious prompts using ciphers and obfuscation techniques (e.g., Base64, ROT13, Leetspeak, Morse code). This skill exploits the gap where the LLM can decode the request, but intermediate keyword-based safety classifiers cannot.

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。

Adaption AI SDK for synthetic data augmentation and dataset adaptation. Use when building data pipelines with the Adaption Python SDK, uploading datasets (local files, Hugging Face, Kaggle), running augmentation/adaptation jobs, configuring brand controls (hallucination mitigation, safety categories, length), recipe specifications (reasoning traces, deduplication, preference pairs, prompt rephrase), evaluating dataset quality, downloading results, or any workflow involving `pip install adaption`, `from adaption import Adaption`, Adaptive Data, or the adaptionlabs.ai API. Also trigger when the user mentions synthetic data generation for fine-tuning, dataset augmentation pipelines, DPO preference pair generation, or grounding-based hallucination reduction on training data.

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 de segurança em runtime da NVIDIA para aplicações LLM. Com detecção de jailbreak, validação de entrada/saída, verificação de fatos, detecção de alucinações, filtragem de PII, detecção de toxicidade. Usa DSL Colang 2.0 para rails programáveis. Pronto para produção, executa em GPU T4.

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。

Knowledge base from the FAA Human Factors Design Standard (HF-STD-001B, 2016) — the FAA's consolidated human-factors / human-systems-integration design criteria for systems it manages, operates, or maintains. Use for requirement-level design rules on: general human-factors design principles; automation and function allocation; designing equipment for maintenance; displays, controls, and visual indicators; alarms, audio, and voice communications; the computer-human interface (information presentation, coding, interaction styles, windows, dialogue); keyboards, input devices, and workstation/workplace ergonomics; system security, personnel safety, environment, anthropometry, and user documentation; plus intended-use and tailoring guidance. It is a quantified, source-attributed synthesis (heavily citing MIL-STD-1472G, MIL-HDBK-759C, DOD-HFDG-ATCCS, NUREG-0700, NASA-STD-3000, ANSI, OSHA, ISO 9241). Complements nasa-hsi as a parallel HSI tradition from the civil-aviation domain. Scope limits: it is design criteria, NOT an HSI lifecycle/process model (use nasa-hsi, nasa-npr-7123, or dau-se-guidebook for process); it does NOT reproduce the third-party standards it cites; it is FAA-acquisition-oriented (ATC, towers, TRACONs, airway facilities), not a general consumer-UX guide; and it is thin on modern touchscreen/mobile, web, and AI-driven interface patterns and on quantitative human-reliability 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。

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)

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。

Autonomous AI code generation safety guardrail register: static AST analysis, forbidden import filters, and zero-day vulnerability checks.

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 AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.

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 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

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。

Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. Don't use for standard infrastructure monitoring unrelated to AI agents, or when the agent is not instrumented with OpenTelemetry (for Reliability, Cost, Safety, Security alerts). NOTE: Reliability, Cost, Safety, and Security alerts use generic OTel metrics and work across runtimes (such as Cloud Run, Vertex AI). Quality alerts rely on Vertex AI Online Monitors and are strictly bound to Vertex AI 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。

[omh] Agent or automation safety risks: review prompt, tool, secret, dependency, destructive-action, and explicit local plugin risks before agent or code execution. Use when the user says: security-safety-review, security safety review, ai coding safety, agent safety review, prompt injection review, tool permission review, secret exposure review, destructive action review.

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。

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification. Triggers: "azure-ai-contentsafety", "ContentSafetyClient", "content moderation", "harmful content", "text analysis", "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。

Configures AWS Application Recovery Controller (ARC) for operational resilience: routing controls with safety rules for cross-Region failover, and zonal shift / zonal autoshift for AZ-impairment recovery. Applies when setting up failover routing, configuring safety rules, enabling zonal shift, or configuring zonal autoshift with practice runs. Also applies when shifting traffic out of a specific Availability Zone (AZ) for an ALB/NLB or other resource. For a broader "an AZ is impaired, what is my response across services" question, see aws-resilience-lifecycle. Does not apply to Resilience Hub setup or FIS experiments.

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。

Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.

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。

Autonomous AI code generation safety guardrail register: static AST analysis, forbidden import filters, and zero-day vulnerability checks.

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 channels the reasoning of Yann LeCun, Chief AI Scientist at Meta and Turing Award winner. Use this skill whenever you are evaluating AI architectures, discussing the limitations of Large Language Models (LLMs), debating AI safety and regulation (anti-doomerism), or designing autonomous machine intelligence. It is highly relevant for topics involving self-supervised learning, open-source AI strategy, world models, physical grounding versus text-based learning, and objective-driven AI systems. Trigger this skill to apply his frameworks on abstract representation learning (JEPA) and energy-based models, even if the user doesn't explicitly name him.

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。

Applies the reasoning style of Geoffrey Hinton, deep learning pioneer and 2018 Turing Award winner. Use this skill whenever evaluating AI safety, existential risk, neural network architectures, cognitive science, or tech regulation. Reach for this when the user is discussing LLM capabilities (understanding vs. autocomplete), the biological vs. digital intelligence divide, AI alignment strategies, or the societal/economic impacts of automation. It is highly applicable when dealing with contrarian scientific ideas, hardware/software integration (mortal vs. immortal computing), or global cooperation on technological threats. Do not wait for the user to name Hinton; trigger this skill proactively for any deep learning or AI existential risk 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。

当需要为 AI 产品定义核心身份、角色声明和能力边界时调用此 skill。典型场景包括：设计新 AI 产品的 system prompt 首段、为不同场景创建差异化角色（如教学助手 vs 编程代理）、重新定义 AI 与用户的关系框架。 不适用于：纯人格风格调优（应使用 personality-system）、安全规则制定（应使用 safety-guardrails）、工具集成（应使用 tool-specification）。 关键 trigger 信号：产品需要 AI 有明确自我认知、多个角色共享底层能力但身份不同、需要限制 AI 在特定领域内运作、用户会问"你是谁"。

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。

Think and work like an expert Brain–Computer Interface Engineer. Use when a task calls for Brain–Computer Interface Engineer judgment. Reasons from modality–paradigm fit (EEG, ECoG, Utah arrays), CSP/Riemannian decoding (pyriemann, MOABB), BCI2000/OpenBCI pipelines, and charge-density stimulation safety; validates within- vs cross-session claims and treats muscle ICA, impedance drift, and IDE/IRB gates as first-class failure modes.

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。

GitHub 解封 — 账号封禁/限制/恢复的领域操作系统。覆盖：(a) GitHub 官方政策体系 (TOS / 可接受使用政策 / Trust & Safety 执行模式 / 公开申诉路径 / 受制裁地区解读)；(b) 封号原因诊断学 (spam / abuse / 制裁误标 / 2FA 丢失 / ToS 违规 / 账号劫持误判 / ban evasion 等子类型 + 症状→原因映射 + 自我分诊压测)；(c) 申诉实操 craft (写一封能让 T&S 快速判误伤的英文申诉信 + 升级阶梯 + 法务介入边界 + Don'ts)；(d) 制裁与合规硬边界 (OFAC SDN 名单 / 哪些国家或地区真不可达 / VPN 误判路径 / 中国大陆不是美国制裁地区的反复重申)；(e) 中国大陆开发者特别处境 (sanctioned region 误标 + SMS 验证不支持 +86/+852 + Gitee/GitLab/Codeberg/JihuLab 备用迁移 + 私有自托管 Gitea/Forgejo)；(f) 真实案例库 (~30+ 公开案例分类拆解：误伤 / 真违规 / 制裁误标三类各自赔率与申诉成功路径)。伦理锚绝不软化：不教 ban evasion / 不教撒谎式申诉 / 真违规承认改进 / 丢 2FA 无恢复因子则诚实告知 / 中国制裁误标靠申诉不靠换 VPN / 申诉 6 个月窗口必算清 / 约 3% (业内估) 真违规恢复 vs 约 79% (业内估) 误伤申诉成功率分层标。 (GitHub Account Reinstatement — the domain operating system for GitHub (and analogous platform) account suspension, restriction, appeal, and recovery. Covers: (a) GitHub official policy architecture (TOS / Acceptable Use Policies / Trust & Safety enforcement patterns / public appeals pathways / sanctioned-region interpretation); (b) suspension-cause diagnostics (spam / abuse / sanctions mis-flag / 2FA loss / ToS violation / account hijack false-positive / ban evasion taxonomy + symptom→cause mapping + self-triage pressure test); (c) appeal craft (writing an English appeal letter that gets T&S to fast-track a false-positive ruling + escalation ladder + legal-engagement boundary + Don'ts); (d) sanctions and compliance hard boundaries (OFAC SDN list / which countries/regions are truly unreachable / VPN false-positive paths / China is NOT a US-sanctioned region — repeated emphasis); (e) mainland China developer special circumstances (sanctioned-region mis-flag + SMS verification does not support +86/+852 + Gitee/GitLab/Codeberg/JihuLab fallback migration + self-hosted Gitea/Forgejo); (f) real-case library (~30+ public cases with categorized analysis: false-positive / genuine violation / sanctions mis-flag, each with win-rate and appeal success path). Ethical anchors absolutely not softened: do NOT teach ban evasion (creating new accounts turns a temp ban into a permanent one — the single biggest mistake); do NOT teach social engineering or lying in appeals (misuse + actually confirms violation); genuine violations: admit + improve beats denial; lost 2FA + no recovery factor → do not pretend recovery is possible; China sanctioned-region mis-flag → fix via appeal, not repeated VPN switching; appeal form 6-month window must be counted carefully; historical 约 3% (业内估) genuine-violation recovery vs 约 79% (业内估) false-positive appeal success rate stratification must be honestly labeled. Anti-samples (explicitly describe harm, never endorse): developer permabanned for ban evasion / open-source team org-banned for personal attacks in public issues / cases where repeated VPN switching escalated risk-control severity.) Master OS — automated mastery of GitHub Account Reinstatement — the domain operating system for GitHub (and analogous platform) account suspension, restriction, appeal, and recovery. Covers: (a) GitHub official policy architecture (TOS / Acceptable Use Policies / Trust & Safety enforcement patterns / public appeals pathways / sanctioned-region interpretation); (b) suspension-cause diagnostics (spam / abuse / sanctions mis-flag / 2FA loss / ToS violation / account hijack false-positive / ban evasion taxonomy + symptom→cause mapping + self-triage pressure test); (c) appeal craft (writing an English appeal letter that gets T&S to fast-track a false-positive ruling + escalation ladder + legal-engagement boundary + Don'ts); (d) sanctions and compliance hard boundaries (OFAC SDN list / which countries/regions are truly unreachable / VPN false-positive paths / China is NOT a US-sanctioned region — repeated emphasis); (e) mainland China developer special circumstances (sanctioned-region mis-flag + SMS verification does not support +86/+852 + Gitee/GitLab/Codeberg/JihuLab fallback migration + self-hosted Gitea/Forgejo); (f) real-case library (~30+ public cases with categorized analysis: fa

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。