「init」の検索結果

Initialize GitHub repositories with standard files and configuration. Generates LICENSE, CONTRIBUTING.md, SECURITY.md, issue/PR templates, CI config, and .gitignore. Detects project type and adapts templates accordingly.

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 a Xiaohongshu posting calendar, weekly review board, first-10-post launch plan, 10-20-post positioning test, or data-based next-step plan. Trigger phrases: "排期", "复盘", "30 天计划", "前10条", "10-20条测试", "发了没数据", "weekly review", "content calendar", "XHS schedule". Do not use for first-draft editing or initial account positioning.

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 has an AI-generated Xiaohongshu draft and wants it to sound more personal, concrete, platform-appropriate, and stronger in hook, retention, and interaction value. Trigger phrases: "去 AI 味", "不像我", "合规检查", "改得像真人", "开头不抓人", "没停留", "humanize draft", "platform check". Do not use for initial positioning or topic generation.

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。

v2.4.0 · Dungeon Master assistant for running persistent D&D 5e campaigns. Handles campaign creation/loading, character management, combat tracking, NPC generation, dice rolling, and session state — all persisted across sessions. Invoke with /dm:dnd followed by a subcommand, or just speak naturally once a campaign is loaded.

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 cloud backend applications with Encore — type-safe backend framework with built-in infrastructure. Use when someone asks to "build a backend", "Encore", "type-safe API framework", "backend with built-in infra", "auto-provision cloud resources", or "backend framework with databases built-in". Covers API definition, databases, pub/sub, cron, and auto-provisioned infrastructure.

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。

Define runtime-validated types with ArkType — TypeScript's 1:1 validator. Use when someone asks to "validate data in TypeScript", "runtime type checking", "ArkType", "type-safe validation", "alternative to Zod", "faster validation library", or "validate with TypeScript syntax". Covers type definitions, validation, morphs (transforms), scopes, and comparison with Zod.

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。

When the user wants to perform load testing or performance testing using Artillery with YAML-based scenario definitions. Also use when the user mentions "artillery," "YAML load test," "WebSocket testing," "Socket.io load test," "scenario-based load testing," or "artillery run." For JavaScript-based load testing, see k6.

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。

Model Context Protocol expert for building MCP servers, tools, resources, and client integrationsUse when "mcp server, model context protocol, claude code extension, building ai tools, tool definition, mcp transport, stdio transport, sse transport, resource provider, prompt template, mcp, model-context-protocol, claude-code, ai-tools, llm-integration, anthropic, server, protocol" mentioned.

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。

The craft of weaving story into interactive systems where the player is both audience and author. This skill covers the unique challenges of game narrative: branching structures that respect player agency, environmental storytelling that rewards exploration, dialogue systems that feel alive, and the delicate balance between authored experience and emergent narrative. Unlike linear media, games don't tell stories TO players - they create the conditions for stories to emerge WITH players. The narrative designer's job is to build the scaffolding that supports infinite player-authored moments while maintaining coherent themes and emotional arcs. This skill synthesizes lessons from Disco Elysium's internal monologue as gameplay, Hades' death-as-narrative-engine, interactive fiction's branching mastery (Inkle, Twine), and procedural narrative pioneers like Dwarf Fortress. It addresses ludonarrative harmony, bark systems, cinematics that respect agency, and the "and therefore" test that separates plot from story. Use when "narrative design, game story, game writing, dialogue system, branching narrative, player choice, environmental storytelling, bark system, quest design, lore delivery, ludonarrative, interactive fiction, inkle, twine, dialogue tree, player agency, cinematic design, voice direction, localization, procedural narrative, narrative, game-writing, dialogue, branching, player-agency, environmental-storytelling, quest-design, voice-acting, localization, interactive-fiction, procedural-narrative, ludonarrative" mentioned.

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 in designing and implementing intelligent game AI systems including behavior trees, finite state machines, GOAP, utility AI, pathfinding, steering behaviors, and perception systems. Specializes in creating believable, performant NPC behaviors that enhance player experience. Use when "game AI, NPC behavior, behavior tree, state machine for game, enemy AI, pathfinding, A* algorithm, navmesh, steering behavior, GOAP, utility AI, AI perception, combat AI, companion AI, boss AI, crowd simulation, flocking, game-ai, behavior-trees, pathfinding, npc, state-machines, goap, utility-ai, steering, perception" mentioned.

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 in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when "crewai, multi-agent team, agent roles, crew of agents, role-based agents, collaborative agents, crewai, multi-agent, agents, orchestration, roles, collaborative-ai" mentioned.

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 in entertainment industry concept art workflows, from initial ideation through final production-ready deliverables. Combines traditional art fundamentals with modern digital workflows used at AAA studios and film production houses. Draws from methodologies of industry masters: Feng Zhu's efficient design process, Scott Robertson's perspective and vehicle design systems, Sparth's graphic shape language, and Syd Mead's industrial design thinking. Use when "concept art, visual development, vis dev, keyframe, color script, production design, mood board, thumbnail sketch, environment concept, character concept, prop design, callout sheet, orthographic views, design exploration, photobash, speedpaint, concept-art, visual-development, game-art, film-art, pre-production, ideation, design" mentioned.

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。

The art and science of narrative-driven brand communication. This skill transforms brand messages into compelling stories that connect emotionally, build memory, and drive action. In a world of infinite content, story is the only thing that cuts through. Great brands don't sell products—they tell stories. Apple tells the story of creative rebels. Nike tells the story of human potential. Patagonia tells the story of environmental stewardship. This skill teaches you to find, craft, and tell your brand's story across every touchpoint. AI amplifies storytelling capability—generating variations, adapting across channels, maintaining consistency—but the human insight that identifies the true story remains essential. This skill bridges narrative craft with AI execution. Use when "story, storytelling, narrative, brand story, origin story, hero journey, emotional connection, customer story, testimonial, case study, brand film, about us, storytelling, narrative, brand-story, emotional, hero-journey, content" mentioned.

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。

The ultimate brand asset: a consistent, explorable universe generated by AI. This skill covers creating coherent brand worlds, consistent characters, architectural spaces, and visual universes that serve as the foundation for all marketing content. Traditional brand building creates guidelines. AI world building creates explorable realities. Characters with consistent personalities across thousands of images. Environments that feel like real places. Visual languages so coherent that any new asset feels like it belongs. This is where AI generation meets universe design. The practitioners of this skill don't just create images—they create the DNA that generates infinite consistent images. They build the source code for visual worlds. Use when "world building, brand world, universe, consistent character, character design, visual language, brand universe, style bible, world bible, coherent assets, character sheet, environment design, world-building, universe, character-design, consistency, visual-language, brand-world, style-guide" mentioned.

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。

Generates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input). Seeds corpus from existing fixtures and runs initial pass. Use when implementing or changing a parser, or any code that ingests user input, webhook payloads, API responses, or file formats.

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 the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers, comparisons, scope, method, baselines, citations, captions, table cells) into claims.json. An OPTIONAL additive cross-model pass ADDS span-anchored semantic claims — method, theorem statements with their assumptions, definitions, proof/derivation steps and equations, scope, baselines, conclusions, the motivation span, and reproducibility-artifact references (the proof, derivation, and structure anchors the family B/D/G auditors need) — it never invents a number, emits a finding, or computes a verdict. Run FIRST, before any audit skill. Triggers: "build the ledger", "extract claims", "prep for integrity audit", "evidence ledger", "建证据账本".

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 Hosted Agents (Python) workflow skill. Use this skill when the user needs Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry 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。

Prioritize roadmap initiatives with tradeoffs. Use when a senior developer needs help ranking projects.

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。

产品设计 / UX 设计 (产品设计 / UX 设计 (Product Design / UX Design) — 数字产品的用户体验设计：从用户研究 → 信息架构 → 交互设计 → 视觉/UI → 可用性测试 → 设计系统的认知操作系统，面向 UX designer / product designer / interaction designer / UX researcher / design systems engineer / design lead，以及想入行、转岗、服务这行(设计外包、设计工具厂商、研究平台)的视角。覆盖: (a) 第一性张力 — **用户中心/研究驱动 (user-centered, 'you are not the user', research before pixels, observe behavior not opinions) ⇄ 商业目标/约束/交付 (business goals, north-star metrics, ship it, designer 服务于产品成功不是个人作品集)**; **设计直觉/品味/craft (taste, aesthetics, 'attractive things work better' — Norman 情感化设计) ⇄ 数据/实验/A-B 测试 (data-driven, metrics, experimentation, 'opinions are not data')**; **用户说的 (stated preference, 访谈里说喜欢) ⇄ 用户做的 (revealed behavior, 行为观察 > 自陈, usability test 看人真实卡在哪)**; **一致性/设计系统/规范 (consistency, design system, Jakob's law 用户带着别处的习惯来, 复用组件) ⇄ 创新/打破模式 (innovation, 该不该破规范)**; **减法/简化 (simplicity, Krug 'Don't Make Me Think', less but better — Dieter Rams) ⇄ 功能丰富/利益相关者塞需求 (feature creep, stakeholder pressure)**; **UX(体验/流程/研究) ⇄ UI(视觉/像素/组件)** 的职责之争, **designer 该不该写代码 (design engineer / 'should designers code')**; (b) 核心工作流 / pipeline (最标准、最易蒸高质量+CLI 化) — Double Diamond (发现 discover → 定义 define → 开发 develop → 交付 deliver) / Design Thinking (共情 empathize → 定义 → 构思 ideate → 原型 prototype → 测试 test) / Design Sprint (Jake Knapp 5 天冲刺); 完整链: 用户研究 (访谈/问卷/可用性测试/卡片分类) → persona / journey map / JTBD → 信息架构 IA + 用户流 user flow → 线框 wireframe (低保真) → 交互/原型 prototype (高保真) → 视觉 UI / 设计系统落地 → 可用性测试 usability testing → handoff 给开发 → 度量迭代 (北极星 / HEART 框架); (c) 工具栈 — 设计/原型 (Figma 绝对主导 / Sketch 衰退 / Adobe XD 已停更 / Framer 高保真+建站 / Penpot 开源 / Principle / ProtoPie 微交互); 协作白板 (FigJam / Miro / Mural); 用户研究 (Maze / UserTesting / Lookback / Dovetail 研究库 / Optimal Workshop 卡片分类树测试 / Hotjar / Microsoft Clarity 热图); 设计系统/交付 (Storybook / 蓝湖(中) / Zeplin / design tokens / Tokens Studio); 度量 (Amplitude / Mixpanel / 北极星指标); AI 新兴 (Figma AI / v0 by Vercel / Galileo AI / Uizard / Cursor 给 design engineer); (d) 知识正典 — Don Norman《The Design of Everyday Things》(affordance/signifier/mapping 圣经)、Steve Krug《Don't Make Me Think》(可用性入门)、Alan Cooper《About Face》《The Inmates Are Running the Asylum》(交互设计/persona 起源)、Jakob Nielsen 10 Usability Heuristics + NN/g 文章库、Jake Knapp《Sprint》、Jeff Gothelf《Lean UX》、Teresa Torres《Continuous Discovery Habits》、Erika Hall《Just Enough Research》、Julie Zhuo《The Making of a Manager》、《Refactoring UI》(Adam Wathan/Steve Schoger)、《Universal Principles of Design》、Laws of UX (Jon Yablonski)、《100 Things Every Designer Needs to Know About People》(Susan Weinschenk)、IDEO/Stanford d.school 设计思维材料; (e) figures/流派 — 认知心理/人因派 (Don Norman 认知科学奠基、Susan Weinschenk 行为心理、Kathryn Whitenton); 可用性工程派 (Jakob Nielsen 启发式/折扣可用性、Steve Krug、Jared Spool UIE); 交互设计/目标导向派 (Alan Cooper goal-directed/persona、Kim Goodwin); 设计思维派 (IDEO Tim Brown、David Kelley d.school); 精益/持续探索派 (Jeff Gothelf Lean UX、Teresa Torres continuous discovery、Marty Cagan《Inspired》产品发现); 设计系统/系统化派 (Brad Frost Atomic Design、Nathan Curtis design tokens、Alla Kholmatova); 视觉/UI craft 派 (Adam Wathan & Steve Schoger Refactoring UI、Dieter Rams 'less but better' 工业设计遗产); 设计领导/职业派 (Julie Zhuo、Aarron Walter 情感化设计、John Maeda); 移动优先 (Luke Wroblewski 'Mobile First'); (f) 行业话术/黑话 — affordance 可供性 / signifier 意符 / mental model 心智模型 / IA 信息架构 / heuristic evaluation 启发式评估 / usability 可用性 / a11y accessibility 无障碍 / WCAG / persona 用户画像 / journey map 用户旅程 / JTBD jobs-to-be-done / north-star metric 北极星 / HEART 框架 / wireframe 线框 / mockup / prototype 原型 / fidelity 保真度 (lo-fi/hi-fi) / design system 设计系统 / design token 设计令牌 / atomic design 原子设计 / component library 组件库 / handoff 交付 / red routes 关键路径 / dark pattern 暗黑模式 / Fitts's law / Hick's law / Jakob's law / Miller 7±2 / progressive disclosure 渐进披露 / above the fold / hamburger menu / skeuomorphism vs flat / micro-interaction / empty state / edge case / happy path / design debt 设计债 / dogfooding / dot voting / affinity mapping 亲和图 / card sorting 卡片分类 / tree testing / A/B test / NPS / SUS (System Usability Scale); (

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。

亚马逊管理之道 (亚马逊管理之道 (The Amazon Way — Amazon 自身的领导力与运营操作系统) — 这个 master skill 蒸馏的不是『在亚马逊平台上开店卖货』(那是跨境电商运营,已由 cross-border-ecommerce 另蒸),也不是 AWS 云技术架构;而是亚马逊这家公司『怎么运营自己、怎么做决策、怎么招人、怎么创新、怎么规划』的一整套可迁移的管理机制(mechanisms)与心智操作系统。面向想在自己团队/公司引入亚马逊式机制的创始人/CEO/高管/运营负责人(COO)、产品经理与技术产品经理(PM/PMT)、组织与流程设计者(chief of staff / ops)、以及在亚马逊工作或准备面试亚马逊(著名的 LP 行为面试 + Bar Raiser)的人。覆盖: (a) 第一性张力 — 亚马逊 OS 的核心世界观分歧: **机制 > 良好意图(Good intentions don't work, mechanisms do:问题不能靠『下次更努力』修复,要装一个带检查闭环的自我强化流程) ⇄ 可控输入指标 vs 滞后输出指标(管你能控制的 input 如选品/价格/在库/配送速度,而非 revenue/股价这类滞后又不可控的 output) ⇄ 长期主义 vs 季度业绩(Day 1、willing to be misunderstood、用现金流+飞轮长期投入,宁可牺牲短期利润) ⇄ 客户执念 vs 竞争对手执念(working backwards 从客户倒推,而非从竞品或『我们能造什么』正推) ⇄ 叙事备忘录 vs PPT(6-pager + 开会前静默阅读、动手前先写 PR/FAQ;写作逼出清晰思考,禁 PowerPoint) ⇄ 单线程负责人/两个披萨团队 vs 协调税(separable、autonomous、one owner per initiative,砍掉跨团队依赖) ⇄ 高标准可学习可传递 vs 与生俱来(insist on the highest standards + Bar Raiser 招聘门,标准是 domain-specific 且能教的) ⇄ 节俭催生创造力 vs 血汗文化(frugality/约束驱动发明 —— 但 frugality + 高压 bar + URA 强制淘汰 = 文化阴暗面批判) ⇄ 两类决策(Type 1 不可逆/单向门 慎重 vs Type 2 可逆/双向门 高判断力个人快速决策,别用重流程拖慢))**; (b) 核心机制(mechanisms,本行的『工具栈』其实是一套运营机制而非软件) — Leadership Principles(14 条→2021 增至 16 条,是一套运营语言和决策仲裁器)、Working Backwards(从客户倒推:动手前先写新闻稿+常见问答 PR/FAQ)、叙事备忘录(6-pager narrative / 1-pager + silent reading 静默阅读、禁 PPT)、Weekly Business Review(WBR + metrics deck 指标看板)、input/output metrics(可控输入指标体系、DMAIC 式指标选择)、年度规划(OP1/OP2 + S-Team goals)、Bar Raiser(招聘机制,独立于用人经理的抬杠者拥有一票否决)、Two-Pizza Team / Single-Threaded Leader STL / separable teams、Correction of Errors(COE 事故复盘 + 5 Whys 五问法)、Andon Cord(安灯绳,借自丰田,一线可拉停)、Flywheel(飞轮:低价→更多客户→更多卖家→更多选品→更低成本结构→更低价)、Type 1/Type 2(单向门/双向门决策分级)、Regret Minimization Framework(遗憾最小化,贝索斯创业决策法); (c) 心智模型层 — customer obsession(客户执念是所有 LP 之首)、long-term thinking / Day 1(第二天就是停滞衰亡)、invent and simplify、ownership(主人翁,不说 that's not my job)、bias for action(可逆决策就快,speed matters)、disagree and commit(充分反对后即便不同意也全力执行)、frugality、dive deep(深入细节、不靠代理指标脱离一线)、think big、are right a lot(用强判断力和证伪自己的能力多做对的判断)、earn trust、deliver results; (d) 工作流/SOP — 用亚马逊方式发起一个新产品/业务(先写 PR/FAQ→评审→倒推着造)、如何跑一场 WBR、如何写和评审一份 6-pager(叙事流程 + 静默阅读)、Bar Raiser 招聘 loop、年度规划(OP1/OP2→S-Team goals→输入指标追踪)、事故后的 Correction of Errors; (e) 知识正典(en-primary,极其丰富且可取一手) — 贝索斯致股东信 1997-2021(1997 首封是奠基文本,每年附在信末;Day 1、遗憾最小化、long term)、《Working Backwards》Colin Bryar & Bill Carr(2021,运营机制圣经)、《The Everything Store》Brad Stone(2013,公司史)、《Amazon Unbound》Brad Stone(2021,权力与阴暗面续作)、《Invent and Wander》贝索斯文集(2020)、《The Amazon Way》/《Think Like Amazon》John Rossman(前亚马逊高管)、Amazon 官方 Leadership Principles 页(amazon.jobs,一手)、HBR『The Institutional Yes』(2007 贝索斯访谈); (f) 行业大佬/figures — Jeff Bezos(创始人,源头教义)、Andy Jassy(现任 CEO,OS 超越创始人的证据 + AWS 缔造者)、Colin Bryar(前贝索斯影子/TPM,《Working Backwards》作者)、Bill Carr(前数字媒体 VP,《Working Backwards》作者)、Jeff Wilke(前全球消费者 CEO,运营架构师)、John Rossman(前亚马逊、机制布道者/顾问)、Brad Stone(记者/编年史作者,批判性外部视角); (g) 争议/批判(必须保留,不能洗白) — 文化阴暗面(NYT 2015『Inside Amazon: Wrestling Big Ideas in a Bruising Workplace』揭露高压职场)、仓储与一线劳工争议、URA(unregretted attrition 强制淘汰)与 stack-ranking 的残酷、frugality + 高 bar = 燃尽(burnout);机制能否迁出亚马逊(cargo-culting:在初创或非科技公司照搬 PR/FAQ/输入指标/Bar Raiser 常失败);是贝索斯个人天才(personality)还是制度化机制(institution)—— OS 在贝索斯卸任后于 Jassy 治下延续,是机制派的证据; (h) 流派/思想谱系 — **信徒/机制布道派(Bryar & Carr《Working Backwards》+ 前亚马逊 operator 顾问圈,信 mechanisms 可移植、任何公司可安装)** vs **批判派(Brad Stone《Amazon Unbound》+ NYT + 劳工视角,认为 OS 与高淘汰的残酷机器不可分割,不该被浪漫化)** vs **情境/规模怀疑派(机制之所以有效是因为亚马逊特定的规模/现金流/创始人权力,照搬到小公司=cargo cult)** vs **创始人中心 vs 制度中心之争(是贝索斯个人 vs 可传承的机制)**。不含: 在亚马逊开店卖货/选品/PPC/FBA 的卖家运营(=cross-border-ecommerce)、AWS 云技术架构与运维、通用 MBA 管理理论泛泛而谈、把普通商业常识包装成『亚马逊独家秘诀』。) Master OS — automated mastery of 亚马逊管理之道 (The Amazon Way — Amazon 自身的领导力与运营操作系统) — 这个 master skill 蒸馏的不是『在亚马逊平台上开店卖货』(那是跨境电商运营,已由 cross-border-ecommerce 另蒸),也不是 AWS 云技术架构;而是亚马逊这家公司『怎么运营自己、怎么做决策、怎么招人、怎么创新、怎么规划』的一整套可迁移的管理机制(mechanisms)与心智操作系统。面向想在自己团队/公司引入亚马逊式机制的创始人/CEO/高管/运营负责人(COO)、产品经理与技术产品经理(PM/PMT)、组织与流程设计者(chief of staff / ops)、以及在亚马逊工作或准备面试亚马逊(著名的 LP 行为面试 + Bar Raiser)的人。覆盖: (a) 第一性张力 — 亚马逊 OS 的核心世界观分歧: **机制 >

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。

Generate navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all page-anchored. Produces _MAP.md (progressive disclosure), .symbols.json (definition index), .anchors.json (claim references), and a _USAGE.md snippet for CLAUDE.md. Use when analyzing papers, specs, or legal docs; when asked to "map this document", "index this PDF", "what does this paper say"; or when a coding agent needs grounded reference material from a PDF source. Analogous to tree-sitting but for prose documents.

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。

REQUIRED for all skill development. Automatically version control every skill file modification for rollback/comparison. Use after init_skill.sh, after every str_replace/create_file, and before packaging.

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。

Index and entry point of the Pixi'VN skill set — start here for any task on a @drincs/pixi-vn project, then follow the skill map to the right skill (narration, canvas, characters, assets, sound, storage, saves, history, ui, minigames, testing, migration). Use when setting up a new or existing project, wiring the main.ts entry point, or calling the top-level Game API (Game.init, Game.start, Game.onEnd, Game.addOnError, Game.onNavigate, Game.clear) — every Pixi'VN project needs this before touching canvas, narration, sound, storage, or history.

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。

The lifecycle gate for a local Codespace-equivalent sandbox. Routed to when the user invokes /ca-sandbox:sandbox to pull an untrusted repo into an ephemeral, host-FS-isolated Docker container, or any of the interaction commands (/ca-sandbox:sandbox-shell, /ca-sandbox:sandbox-exec, /ca-sandbox:sandbox-cp, /ca-sandbox:sandbox-destroy) against an existing box. Five gated phases — pre-flight, clone+build, isolated run, interact, teardown. The load-bearing invariant is structural: untrusted code in the box can never reach the host filesystem (no bind mount, no docker socket, never --privileged, cap-drop ALL, non-root, read-only root). Network defaults to offline; egress out is host-initiated only. Every object is labeled ca.sandbox=1 and torn down on exit.

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。