「ai safety」の検索結果

Help users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological safety through proven frameworks like GAIN and Radical Candor.

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 for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first content changes, validation, cleanup proof, or durable workflow rules. Best when agents must prove the actual folder/module/scene/prefab/runtime owner before editing, especially runtime UI, generated assets, code graphs, tutorial/state flows, guided selection/action flows, overlay/dim source-bound mistakes, coordinate conversions, focus/highlight/marker/HUD alignment, predictive lead aiming, ballistic trajectories, spatial IoU verification, or repeated "fix still not visible" failures.

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 designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.

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。

Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.

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。

Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG/CYP/AMES endpoints, and PAINS / Lipinski / Ro5 / Veber / BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.

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 test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document.

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。

Depth assessment of whether an AI system is high-risk under Art. 6 of the EU AI Act, grounded in the Commission's draft Art. 6(5) classification guidelines (general principles + Annex I + Annex III). Covers the Annex I product-safety route, all eight Annex III areas with worked examples, the Art. 6(3) exception and its profiling re-exception, and the Art. 25 quasi-provider trap. Outputs a structured decision block, a practitioner memo, and a JSON interchange artefact.

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 knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with Azure OpenAI, AI Gateway, MCP tools, Entra auth, or BYO VNet networking, and other Microsoft Foundry related development tasks. Not for Content Safety in Foundry Control Plane (use azure-content-safety), Azure Content Understanding in Foundry Tools (use azure-content-understanding), Azure Speech in Foundry Tools (use azure-speech), Microsoft Foundry Classic (use microsoft-foundry-classic).

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 knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with Azure OpenAI, RAG, Azure AI Search, MCP tools, or multi-agent routing, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Local (use microsoft-foundry-local), Content Safety in Foundry Control Plane (use azure-content-safety), Azure Speech in Foundry Tools (use azure-speech).

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 knowledge for Content Safety in Foundry Control Plane development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Content Safety APIs, Docker containers, text blocklists, media provenance, or groundedness checks, and other Content Safety in Foundry Control Plane related development tasks. Not for Azure Content Understanding in Foundry Tools (use azure-content-understanding), Azure Security (use azure-security), Azure Sentinel (use azure-sentinel), Azure Defender For Cloud (use azure-defender-for-cloud).

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 knowledge for Azure Content Understanding in Foundry Tools development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when building Content Understanding analyzers, RAG document flows, agentic workflows, REST/SDK calls, or GA migrations, and other Azure Content Understanding in Foundry Tools related development tasks. Not for Content Safety in Foundry Control Plane (use azure-content-safety), Azure Speech in Foundry Tools (use azure-speech), Azure AI Vision (use azure-ai-vision), Azure AI Document Intelligence (use azure-document-intelligence).

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。

DO NOT INVOKE when the primary request explicitly asks to convert, migrate, modernize, or rewrite a legacy/old-style project to SDK style; use msbuild-modernization. Migration prompts often mention ToolsVersion, explicit Compile/Reference entries, packages.config, or Microsoft.CSharp.targets, but merely reviewing or auditing a file that contains those patterns remains in scope here. USE FOR broad review, audit, lint, or maintainability/correctness checks of project/build files, including custom targets; prioritized cross-cutting findings; discrete anti-patterns; F# ordering/FS0039; cross-platform paths; and focused Import safety verdicts. Review/audit is analysis-only unless fixes are requested. For concrete property/item defects use property-patterns/item-management; use target-authoring for implementation and extension-points for NuGet auto-import/layout discovery. Exclude non-MSBuild systems.

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。

Orchestrate multiple AI agents for construction workflows: estimator, scheduler, document, QA and safety agents coordinated by a supervisor agent, with human checkpoints. Use when automating end-to-end project processes with agentic AI.

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。

Select appropriate Ollama models for processing sensitive but legal content. Use when: (1) llama3.2 or deepseek-r1 refuses to process content with "I cannot assist" responses, (2) Local LLM returns generic safety disclaimers instead of following instructions, (3) Need to process adult content, sex work data, or other legal-but-sensitive material through a local LLM. Also covers using /api/chat vs /api/generate for system prompt support, and structuring prompts for consistent format compliance.

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。

Automatically repair C/C++ code violations detected by TLA+ model checking. Takes a program, TLA+ specification, and TLC counterexample trace as input, then generates minimal code modifications to eliminate the violation. Use when: (1) TLC model checker reports an invariant violation, deadlock, or temporal property failure, (2) You have a counterexample trace and need to fix the corresponding code, (3) You need to understand how a TLA+ violation maps to program-level bugs, (4) You want to validate repairs by re-running TLC. Supports safety properties (invariants), liveness properties (temporal logic), and deadlock detection.

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。

当需要在基础身份之上叠加可切换的人格风格层时调用此 skill。典型场景包括：为同一产品提供多种人格选项（如 GPT-5.1 的 friendly/professional/quirky 模式）、设计人格切换机制、防止人格泄露到用户内容中。 不适用于：定义 AI 的核心角色定位（应使用 persona-design）、设计安全规则（应使用 safety-guardrails）。 关键 trigger 信号：产品需要多种语气风格、用户可切换 AI 性格、需要防止 AI 人格污染用户文本、存在 "personality" 或 "tone" 配置项。

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。

Plan, prompt, execute, troubleshoot, and quality-control Black Forest Labs FLUX image generation and editing across the BFL direct API and licensed local/open-weight deployments. Use for FLUX.2 model selection, text-to-image, single- or multi-reference editing, typography, exact-color work, mask-based erase/inpainting, outpainting, API integration, reproducibility, deployment licensing, and production rights or safety decisions; also use when migrating or maintaining legacy FLUX.1/FLUX1.1 workflows.

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。

Provider-independent captions and media accessibility direction for AI agents producing or finishing generated videos, ads, social clips, explainers, avatar videos, documentaries, podcasts/video recuts, training media, and localized content. Use when planning, authoring, reviewing, localizing, burning in, exporting, or QAing captions, subtitles, SDH, transcripts, audio description, flashing/motion safety, caption readability, or accessible media handoff files.

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。

Predicts ADMET properties using ADMETlab 3.0 (119 endpoints with uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG/CYP/AMES gold-standard endpoints, and PAINS / Lipinski / Ro5 / Veber / BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.

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。

Test for regulatory compliance: GDPR/CMP consent verification, Google Consent Mode v2, Global Privacy Control (GPC), CCPA/US state opt-out, EU AI Act Article 50 transparency, Better Ads Standards, and cookie-inventory auditing. Covers automated consent-flow testing, third-party script blocking before consent, and cookie drift detection. Use when: "GDPR test," "compliance," "CMP test," "cookie consent," "consent mode," "CCPA," "GPC," "AI Act," "Better Ads," "privacy banner." Not for: WCAG/axe-core test authoring — use accessibility-testing. Not for: OWASP/vuln scanning — use security-testing. Not for: evaluating your LLM feature's quality or safety — use ai-system-testing. Related: accessibility-testing, security-testing, ai-system-testing, ci-cd-integration.

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-Friendly CLI Spec v0.1 workflow skill. Use this skill when the user needs Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description 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。

DevOps 与站点可靠性工程 (SRE) — 平台 / 基础设施 / 可靠性工程师的认知操作系统, 覆盖软件交付 + 运维全生命周期 (CI/CD 与发布工程 trunk-based + 渐进式发布 canary/blue-green/feature flag + GitOps Argo CD/Flux / 基础设施即代码 Terraform/OpenTofu/Pulumi/Ansible + policy-as-code OPA / 容器与编排 Docker/Kubernetes + Helm/Kustomize + service mesh Istio/Linkerd / 可观测性 Prometheus + Loki + OpenTelemetry + Honeycomb + eBPF + RED/USE / SLO-SLI-error budget 与可靠性工程 Google SRE 学科 + 容量规划 + 优雅降级 / 事件管理与 on-call 事件指挥 + PagerDuty + runbook + 无指责复盘 + MTTR / 云平台与 FinOps AWS/GCP/Azure + 成本优化 + 弹性伸缩 / 平台工程与开发者体验 IDP + Backstage + golden path + Team Topologies / DevSecOps 与供应链安全 shift-left + SBOM + SLSA + sigstore + Vault / 韧性与混沌工程 fault injection + game day + 安全科学 / DORA 指标与工程效能 部署频率 + 变更前置时间 + 变更失败率 + Accelerate 研究 / 数据库与有状态运维 schema 迁移 + 备份容灾) — 不含 通用应用开发 / 纯云销售认证速成 / 'DevOps = 跑 Jenkins 的岗位' 窄化误解 / ITIL 工单文化传统运维 (旧范式仅做边界) / 把手工运维 ClickOps 当稳态 (是 toil, 本 skill 核心反模式) (DevOps & Site Reliability Engineering — the cognitive operating system of platform / infrastructure / reliability practitioners who own the full software delivery + operational lifecycle, covering (a) CI/CD & release engineering (build pipelines, trunk-based development, progressive delivery — canary / blue-green / feature flags, GitOps with Argo CD / Flux), (b) Infrastructure as Code (Terraform / OpenTofu, Pulumi, CloudFormation, Ansible, Crossplane — module design, state management, drift, policy-as-code OPA / Sentinel / Checkov), (c) containers & orchestration (Docker / OCI, Kubernetes — scheduling, networking CNI, storage CSI, operators / CRDs, Helm / Kustomize, service mesh Istio / Linkerd), (d) observability (the three pillars + beyond — metrics Prometheus / VictoriaMetrics, logs Loki / ELK, traces OpenTelemetry / Jaeger / Tempo, high-cardinality observability Honeycomb, eBPF, RED / USE methods, SLO-based alerting), (e) SLO / SLI / error budgets & reliability engineering (Google SRE discipline — service level objectives, error budget policy, toil budgets, capacity planning, load shedding, graceful degradation), (f) incident management & on-call (incident command, PagerDuty / Opsgenie, runbooks, blameless postmortems, MTTR / MTTD, error budget burn), (g) cloud platforms & FinOps (AWS / GCP / Azure well-architected, multi-region, cost optimization, autoscaling), (h) platform engineering & developer experience (internal developer platforms, Backstage, golden paths, self-service, Team Topologies), (i) DevSecOps & supply-chain security (shift-left, SAST / DAST, SBOM, SLSA, sigstore / cosign, secrets management Vault), (j) resilience & chaos engineering (chaos experiments, fault injection, game days, resilience engineering / safety science), (k) DORA metrics & engineering effectiveness (deployment frequency, lead time, change failure rate, MTTR, the Accelerate research), (l) databases & stateful operations (schema migrations, backups / DR, replication); NOT generic software development / app feature coding (是 平行学科, DevOps/SRE 关注 delivery + operability 不是 product feature), NOT pure cloud sales / certification cram without operational depth, NOT 'DevOps = a job title that runs Jenkins' 的窄化误解 (DevOps 是 文化 + 实践, SRE 是 Google 对 reliability 的工程化具体实现), NOT ITIL-heavy 传统运维 工单文化 (是 被 DevOps 取代的旧范式, 仅做边界标注), NOT manual ops / ClickOps as a steady state (是 toil, 本 skill 的核心反模式).) Master OS — automated mastery of DevOps & Site Reliability Engineering — the cognitive operating system of platform / infrastructure / reliability practitioners who own the full software delivery + operational lifecycle, covering (a) CI/CD & release engineering (build pipelines, trunk-based development, progressive delivery — canary / blue-green / feature flags, GitOps with Argo CD / Flux), (b) Infrastructure as Code (Terraform / OpenTofu, Pulumi, CloudFormation, Ansible, Crossplane — module design, state management, drift, policy-as-code OPA / Sentinel / Checkov), (c) containers & orchestration (Docker / OCI, Kubernetes — scheduling, networking CNI, storage CSI, operators / CRDs, He

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 hazards in systems or AI agents: STPA, guardrails, safety cases, incident analysis. Use when an agent can take actions or send payments.

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。

Designs LLM, agent, responsible-AI, and multimodal evals. Use when measuring quality, fairness, grounding, safety, or judge reliability. Not for test harnesses (qa-agent-testing).

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。