「guard」の検索結果

Guide for managing consent for scientific research under GDPR Article 89 and Recital 33 broad consent provisions. Covers ethical review board coordination, purpose evolution management, appropriate safeguards including pseudonymization, and the interplay between consent and other lawful bases for research processing.

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。

Assessing privacy risks in large language model outputs including training data memorisation, PII leakage in generated text, prompt injection leading to data extraction, and hallucinated personal data. Covers output filtering, guardrails, and monitoring. Keywords: LLM privacy, output risk, memorisation, PII leakage, prompt injection, hallucinated PII.

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。

Conducts a Data Protection Impact Assessment for automated decision-making and profiling systems under GDPR Article 35(3)(a), covering algorithmic transparency, meaningful human oversight, contestation mechanisms, and Art. 22 safeguards. Activate for DPIA automated decision, profiling DPIA, algorithmic impact assessment, Art. 35(3)(a), ADM risk assessment queries.

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。

Guide for obtaining explicit consent for international data transfers under GDPR Article 49(1)(a). Covers informed consent requirements including risks of transfers without adequacy decisions or appropriate safeguards, specific destination country disclosure, and the narrow scope of derogation-based transfers.

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。

Implements profiling restrictions for children under GDPR Recital 71, Article 22, UK AADC Standard 12, and COPPA. Covers prohibition of behavioural advertising to children, recommendation algorithm limitations, nudge technique prohibition, and automated decision-making safeguards. Keywords: profiling, children, behavioural advertising, recommendation algorithm, AADC, automated decision.

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。

Guides assessment and application of GDPR Article 49 derogation conditions for international data transfers in the absence of adequacy decisions or appropriate safeguards. Covers explicit consent, contract necessity, public interest, vital interests, public register, and compelling legitimate interests with restrictive interpretation per EDPB Guidelines 2/2018. Keywords: Art. 49, derogations, transfer exceptions, explicit consent, compelling legitimate interests.

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 agy-auto PreToolUse security gate to run Antigravity CLI (agy) unattended with layered policy controls instead of --dangerously-skip-permissions.

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。

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

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-description.

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 DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s 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。

Adds, changes, or reviews a screen, sheet, dialog, or destination slice (endpoint to repository to ViewModel to UI to navigation to DI to tests) in a Compose or CMP project. Use when adding a screen, building a new feature, adding a ViewModel or destination, wiring list/detail or a form screen, scaffolding a slice, or reviewing a feature change. Covers Contract.kt, launchGuarded wiring, SavedStateHandle drafts, the state matrix, and new-feature.sh. Do NOT use for routing or architecture (compose-architecture), pure refactors, Gradle work (compose-project), recomposition or styling (compose-ui), repository or persistence work (compose-data), or expect/actual splits (compose-platform).

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 professional, consultant-grade PowerPoint presentations from scratch using MckEngine (python-pptx wrapper) with McKinsey-style design. Use when user asks to create slides, pitch decks, business presentations, strategy decks, quarterly reviews, board meeting slides, or any professional PPTX. AI calls eng.cover(), eng.donut(), eng.timeline() etc — 67 high-level methods across 12 categories (structure, data, framework, comparison, narrative, timeline, team, charts, images, advanced viz, dashboards, visual storytelling), consistent typography, zero file-corruption issues, BLOCK_ARC native shapes for circular charts (donut, pie, gauge), production-hardened guard rails for spacing, overflow, legend consistency, title style uniformity, dynamic sizing for variable-count layouts, horizontal item overflow protection, chart rendering, and AI-generated cover images via Tencent Hunyuan 2.0 with professional cutout, cool grey-blue tint, and McKinsey-style Bézier ribbon decoration.

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。

OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.

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。

当用户用 Claude 写小红书、公众号、视频脚本等内容时，输出出现翻译腔、英文思考、西式框架，导致“像外国人假装写中文”时使用。 典型触发语句： - “Claude写小红书翻译腔太重”“英文思考输出灾难” - “帮我把这个笔记改成纯中文网感”“去除Claude翻译腔” - “公众号文章中途变英文了”“50 Skills内容生成翻车” - “强制Claude用中文思考写笔记”“小红书情绪化表达润色” 始终保护用户原有的 CLAUDE.md / AGENTS.md 中的人设与语气要求，只做最小必要干预。优先与 xiaohongshu 技能组合使用。

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。

Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs_2.sqlite, logs_2.sqlite-wal, block_log_inserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.

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, AI safety frameworks, and deep learning principles of Yoshua Bengio (Turing Award winner, Mila). Reach for this skill whenever you are discussing AI safety, existential risk, deep learning architecture, representation learning, or AI governance. Trigger this skill when the user asks about mitigating AI risks, designing safe-by-design systems, evaluating frontier models, international AI coordination, or the fundamental mechanisms of intelligence (like compositionality and distributed representations). Use it to shift the focus from agentic reward-maximization to non-agentic 'Scientist AI', apply the precautionary principle to catastrophic risks, and emphasize mathematically rigorous 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。

Use this skill when reasoning about generative AI, adversarial machine learning, neural network security, algorithmic fairness, or deep learning fundamentals. This skill channels the thinking of Ian Goodfellow, inventor of Generative Adversarial Networks (GANs). Trigger this skill when the user asks about model robustness, mitigating bias, evaluating AI guardrails, designing generative models, or defending against adversarial attacks. Apply his frameworks of minimax games, adversarial feature learning, and worst-case robustness analysis to shift the user's perspective from average-case optimization to adversarial resilience.

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。

Before removing code that looks redundant, wasteful, or "wrong" based on log observations or code review instinct, grep the test suite for tests whose names describe the exact behavior you're about to remove. A test whose title literally describes the "weird" thing (e.g. "calls play() even when player reports playing", "retries even when first call succeeded", "skips cache even when fresh") is a load-bearing workaround, and the production log you're reacting to is probably the workaround working as designed — not a bug. Use when: (1) Tempted to remove a function call that "looks redundant" based on a production log, (2) About to "simplify" a conditional that seems to always take the same branch, (3) Reviewing code and thinking "why would anyone write this?", (4) A log line shows a state that seems impossible or contradictory (e.g. playing=true but positionMs=0 for seconds), (5) CI surfaces a failing test whose name describes exactly what your fix removed.

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。

Fix Dart/Flutter services where calling start() after stop() is a silent no-op because stop() sets a _disposed (or similar) flag that start()'s guard short-circuits on. Use when: (1) A repository/service/controller has startListening/stopListening, subscribe/unsubscribe, open/close, or similar lifecycle methods, (2) Re-opening the service after closing it appears to do nothing — no subscription, no events, no error, (3) Unit tests that only exercise a single mount/open/start cycle pass while the real app breaks on the second visit to a screen, (4) A boolean flag is used both for "in the middle of tearing down this instance forever" AND for "currently stopped, can be re-started". Common in Riverpod/Bloc-driven screens that wire startListening() in initState and stopListening() in dispose — the second time the user visits the screen, nothing happens.

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。

Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and tests before final verification.

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。

Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.

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 设计记忆存储、检索、应用和更新机制时调用此 skill。典型场景包括：设计持久化记忆架构（用户偏好、历史上下文、项目知识）、定义记忆的创建/读取/更新/删除生命周期、实现静默记忆应用（不在回复中透露记忆内容）、管理敏感记忆边界。 不适用于：定义工具接口（tool-specification）、定义安全规则（safety-guardrails）、定义人格风格（personality-system）。 关键 trigger 信号：AI 需要跨会话记住用户信息、记忆内容可能敏感、需要在回复中隐式应用记忆而非显式引用、用户要求"记住这个"。

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 定义工具接口、设计调用规范、实现工具发现与编排机制时调用此 skill。典型场景包括：设计 AI agent 的工具集、定义 JSON Schema/XML/TypeScript 格式的工具描述、实现工具权限控制与并行调度、设计子代理委托架构。 不适用于：定义 AI 身份（persona-design）、安全规则（safety-guardrails）、记忆存储（memory-system）。 关键 trigger 信号：AI 需要调用外部 API 或服务、工具数量超过 10 个需要发现机制、需要区分工具权限层级、需要子代理并行执行、工具调用涉及敏感操作需要审批。

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。