「ai safety」の検索結果

Use when a task needs the judgment of an animal trainer — designing a behavior-modification plan for a specific problem behavior, choosing a reinforcement schedule and deciding when to raise criteria, structuring session length and frequency to avoid fatigue or frustration plateaus, or setting a handler/public safety protocol around a training animal.

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。

Writes, reviews, and debugs idiomatic Rust code with memory safety and zero-cost abstractions. Implements ownership patterns, manages lifetimes, designs trait hierarchies, builds async applications with tokio, and structures error handling with Result/Option. Use when building Rust applications, solving ownership or borrowing issues, designing trait-based APIs, implementing async/await concurrency, creating FFI bindings, or optimizing for performance and memory safety. Invoke for Rust, Cargo, ownership, borrowing, lifetimes, async Rust, tokio, zero-cost abstractions, memory safety, systems programming.

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。

Practice AI safety across the lifecycle — risk assessment, alignment concepts, evaluation, deployment safeguards, and governance. Use when building or deploying AI systems responsibly.

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 psychological safety in your team using Simon Sinek's Leaders Eat Last Circle of Safety model and Amy Edmondson's research. Use when a leader says "my team doesn't speak up", "people are afraid to fail", "nobody challenges bad ideas", "people only tell me what I want to hear", "I want my team to take more risks", "there's a blame culture", "people hide mistakes", or "I want to create a safe environment". Also trigger when someone describes a team where postmortems turn into blame sessions, where people stay quiet in meetings and then vent privately, where mistakes are hidden until they become crises, or where the same person speaks 80% of the time in every meeting. Psychological safety is not about comfort - it is the condition that makes high performance possible.

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。

Pre-landing PR review. Analyzes diff against main for SQL safety, LLM trust boundary violations, conditional side effects, and other structural 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。

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

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-level clinical engineering covering medical equipment management, hospital technology systems, healthcare IT integration, safety standards, and health technology 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。

Modelo de moderação especializado 7-8B do Meta para filtragem de entrada/saída de LLM. 6 categorias de segurança - violência/ódio, conteúdo sexual, armas, substâncias, automutilação, planejamento criminal. Precisão de 94-95%. Deploy com vLLM, HuggingFace, Sagemaker. Integra com 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。

Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.

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 NASA Probabilistic Risk Assessment Procedures Guide (NASA/SP-2011-3421, 2nd ed.). Use for quantitative PRA of aerospace and safety-critical systems: the risk triplet and scenario logic stack (MLD, ESD, event trees, fault trees, minimal cut sets), Bayesian data collection and parameter estimation, aleatory/epistemic uncertainty modeling and common-cause failure (Alpha Factor, beta-factor, CCBE), human reliability analysis (THERP, CREAM, NARA, SPAR-H), context-based software risk (CSRM), physics-based and structural/phenomenological models (stress-strength, limit states, FORM/SORM, NASGRO, range safety), uncertainty propagation and importance measures (F-V, RAW, Birnbaum, DIM), and launch-abort modeling with worked PRA examples. This is the QUANTITATIVE engine beneath NASA's risk doctrine — for the qualitative RIDM/CRM decision framework use the nasa-risk pack. Thin on programme management, organisational risk governance, and non-aerospace regulatory contexts; aerospace-focused and anchored to the 2011 second edition.

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 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-descriptio

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 AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.

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 text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual conten...

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。

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

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-level idiomatic Rust API design — the patterns that make illegal states unrepresentable and abstractions zero-cost. Type-state programming (PhantomData state machines), newtype + sealed + extension traits, typestate builders, RAII guards & Drop ordering, the interior-mutability decision tree (Cell/RefCell/Mutex/RwLock/Atomic/OnceLock), enum-driven state machines, error architecture (thiserror vs anyhow), dyn vs generic dispatch & object safety, the impl Trait / GAT / RPITIT toolbox, and Deref-for-smart-pointers (and its abuse). Use when designing a Rust library's public API, encoding invariants in the type system, choosing a dispatch or error strategy, or reviewing Rust for idiom. NOT for borrow-checker firefighting / toolchain / test-runner workflow (use rust-development-workflow), NOT for pd-console GPUI rendering/layout/panes (use gpui-rust-console), NOT for app packaging/notarization (use rust-app-distribution).

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。

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

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。

Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing practices, access controls, complexity, decentralization, documentation, MEV risks, low-level code, and testing, then produces a scorecard with evidence-based ratings and a priority-ordered roadmap. Use when assessing or scoring the maturity of a smart contract or blockchain codebase, producing a maturity scorecard or evaluation, or judging how mature, well-tested, or well-documented such a project is against a rubric.

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。

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: `这个 skill 安全吗`, `skill 安全扫描`, `检查 skill 安全`, `audit skill`, `scan skill`, `check skill safety`, `analyze skill`, `inspect skill`, `verify skill`, `skill security`, `skill supply chain`. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.

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。

Run the PAIDF Orchestration Event Video Generation DAG on Kubernetes - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for requests about event video generation, anomaly video generation, image-to-video synthesis, Cosmos3 image2video, anomaly dataset creation, safety/surveillance SDG, or generating person-falling, person-climbing, person-running, fighting, smoking/vaping, fire/smoke, or shoplifting video clips from a seed image. Runs environment setup first when controller readiness is unknown. Not for person-crop clothing/attribute augmentation (that is image-attribute-augmentation-workflow) and not for video style transfer.

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。

Implement content policy guardrails, input/output validation, and usage governance for Claude API integrations. Trigger with phrases like "anthropic guardrails", "claude content policy", "claude input validation", "anthropic safety rules".

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 when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interactive presentation, user-memory lifecycles, environment-adaptive tools, speculative tool execution, late-bound capabilities, permissions, system prompts, planning, goals, always-on agents and durable runtime, adaptive agent teams, context compaction, memory, skills, MCP/external connectors, public-board communications, hardware agents and board deployment, self-refining recursive harnesses, programmable context, continual refinement, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.

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。

Work through the first hours and days after a disaster — a fire, flood, storm, or evacuation — in the right order: safety and people first, then documenting for insurance and aid, then the immediate recovery steps, without missing the things that cost money or health later. Use when someone says 'my house flooded/burned', 'what do I do after the disaster', 'we just evacuated, now what', or 'the storm damaged everything'. Produces a triaged action plan (safety → document → claim → recover), the do-not-miss list, and where to get help. Not legal advice; routes to emergency services and official aid.

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。