「eal」の検索結果

Reviews audio DSP code for numerical correctness. Use when the user asks to review, audit, or check DSP code for correctness issues — filters, feedback loops, fixed-point arithmetic, accumulation loops, or any numeric computation in audio code. Trigger on "check this filter for NaN", "why does my reverb blow up?", "is this numerically stable?", "why do I hear DC in my output?". Pairs with audio-dsp-review (realtime safety); this skill covers numeric correctness. Flag issues proactively.

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。

Skill体系自洽性审查 Skill（由用户主动触发，不被其他组件调用）。主动检查整个Skill/Agent/Rule体系的内部一致性：触发词冲突、孤立组件、版本漂移、SKILL-INDEX与实际文件不一致、alwaysApply Rule叠加矛盾等。对应产品侧的 project-closeout。注意：与 skill-system-destroyer（子智能体，只读审查新组件冲突）不同——本 Skill 审查整个体系的历史一致性。触发词：「检查Skill体系」「Skill体系有没有问题」「Skill体系自检」「Skill体系自洽性」「Skill健康检查」。

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。

元级闭环验证编排器。读取五域形式化描述（DOMAIN-REGISTRY + NODE-IO-CONTRACTS），两阶段（Phase 1预想/Phase 2实际）执行沙盘验证，调用 skill-domain-health-check 检查传播完备性，调用 skill-domain-self-optimizer 生成修复方案，输出带证据链的全系统闭环验证报告。这是整个Skill体系自我验证的最高入口。触发词：「运行元验证」「闭环验证」「验证Skill体系传播完备性」「系统闭环检查」「全域验证」「元系统运行」。

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。

三大闭环日常健检（v2.0）。快速读取系统状态文件（约1分钟），从三个层次输出健康仪表盘：①运营指标层（PENDING-EXPERIENCES/碎片积压/一致性检查日期/cascade/PENDING-SKILLS）②沙盘状态层（sandboxes/目录的 validated/draft/gap-found 分布）③D0覆盖率层（role-* Skills 有多少已有认知根行）。触发词：「三大闭环健康检查」「全系统健康报告」「整体系统健康」「三个闭环都健康吗」「三大闭环状态怎么样」。⚠️ 本 Skill 为快速只读健检，无 Full 模式。深度场景沙盘验证→skill-closure-verifier-meta；生成场景沙盘→scenario-sandbox-builder；单一Loop专项→对应专项Skill。

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。

Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.

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。

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

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 a complete feature module with folder structure, Assembly Definition (.asmdef), test assembly, and namespace. Use when adding a new feature, system, or module to a Unity project. Triggers on requests like "create a new feature", "scaffold a module", "add a combat system", "I need a health system", "set up inventory", "create a new module for X", "add a new system", "new feature folder", or any task requiring new folders, assemblies, or namespaces for a gameplay feature — even when the user just names a system they want to build from scratch. Reads ProjectConfig.yaml for folder_strategy and MCP availability.

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 EditMode and PlayMode tests using NUnit, mapped from GDD Gherkin scenarios. Use when writing tests, validating features, ensuring code quality, or verifying behavior after changes. Triggers on requests like "write tests for this", "test the health system", "add unit tests", "verify this works", "add PlayMode tests", "test this feature", "write integration tests", "make sure this doesn't break", "add test coverage", "TDD this feature", or any task involving test creation, test-driven development, or quality assurance. Maps Given/When/Then scenarios directly to test methods using NUnit assertions.

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 networking boilerplate adapted to the project's chosen networking package (NGO, Mirror, Photon). Use when setting up multiplayer systems, syncing state, writing RPCs, building lobbies, or designing an authority matrix. Triggers on requests like "add multiplayer", "sync player health", "create an RPC", "set up lobbies", "make this networked", "add co-op", "replicate this across clients", "spawn networked objects", "handle player disconnect", "create a matchmaking system", or any task involving network state synchronization, remote procedure calls, or client-server architecture. Always reads ProjectConfig.yaml -> networking before generating code. If networking is "none", do NOT generate networking code.

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 Unity 6+ UI Toolkit Runtime Data Binding code using MVVM pattern with [CreateProperty], DataBinding, and PropertyPath. Use when creating UI screens, HUDs, menus, inventories, settings panels, or any data-bound UI elements with UI Toolkit. Triggers on requests like "create a health bar", "build the HUD", "make a settings screen", "bind data to UI", "create an inventory UI", "add a pause menu", "show player stats on screen", "build a shop UI", "create a dialogue box", or any task involving runtime UI layout, styling, or data display. Also use when the user mentions UXML, USS, ViewModel, or UI bindings. Only activates when ProjectConfig.yaml -> ui_system is "UIToolkit" or "Mixed". Requires Unity 6.0+.

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。

Unity 6 lighting and visual effects guide. Use when working with lights, baked/realtime/mixed lighting, light probes, reflection probes, Adaptive Probe Volumes (APV), global illumination, Particle System, VFX Graph, or post-processing effects. Based on Unity 6.3 LTS documentation.

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 creating, maintaining, debugging, or reviewing real-browser end-to-end tests with Playwright or Cypress, including Page Object models, CI artifacts, traces, flaky tests, cross-page visual regression, and critical user journeys such as login, payment, permissions, or CRUD. For layer planning or tests close to UI components, choose the matching testing workflow first; Chinese triggers include E2E, end-to-end testing, Playwright, Cypress.

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 setting up or reviewing Storybook component documentation, design-system presentation, isolated component state previews, stories, addons, decorators, MDX docs, component-state interaction checks, visual baselines, or Chromatic. For real-browser cross-page journeys or broader coverage planning, choose the matching testing workflow first; Chinese triggers include Storybook, component documentation, Design System, visual regression.

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 authoring or reviewing frontend unit, component, or light integration tests close to UI code, including React Testing Library, Vue Test Utils, hooks/composables, props/emits, callbacks, accessible queries, user-event interactions, mocks, loading/error/empty states, and regression coverage. For layer planning, real-browser journeys, or existing validation failures, choose the matching testing or validation workflow first; Chinese triggers include component testing, Component unit testing, unit testing, lightweight integration 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。

Use when a task needs the judgment of an Epidemiologist — investigating a disease outbreak and identifying its source, designing a case-control or cohort study to test an exposure hypothesis, calculating attack rates/odds ratios/relative risk from surveillance data, evaluating whether a surveillance system is sensitive and timely enough to catch a real signal, or judging whether an observed case cluster is a true outbreak or expected background variation.

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 a task needs the judgment of an Energy Auditor — running a blower-door/duct-leakage diagnostic sequence on a home or light-commercial building, testing combustion appliances for worst-case backdraft risk before recommending air sealing, reconciling utility billing history against walkthrough findings, ranking retrofit measures by savings-to-investment ratio (SIR) for a weatherization or utility rebate program, or writing the prioritized scope of work an install crew executes without the auditor on site. Distinct from an energy-engineer (industrial/commercial capital planning, IPMVP measurement and verification, calibrated simulation) — this role owns the field diagnostics and the residential/light-commercial audit-to-scope handoff.

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 a task needs the judgment of an Embedded/Firmware Engineer — analyzing worst-case execution time for a hard real-time deadline, choosing static over dynamic memory allocation to avoid fragmentation on a long-uptime device, keeping an interrupt service routine minimal and deferring work to the main loop, synchronizing a variable shared between an ISR and main context to prevent a torn read, or verifying a hardware register interaction against the datasheet's exact timing rather than observed bench behavior.

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 a task needs the judgment of an Emergency Management Director — activating and staffing an EOC for a developing hazard, sequencing a disaster declaration and FEMA Public Assistance/Individual Assistance request, sizing shelter and resource needs against real population and capacity numbers, designing or critiquing a tabletop exercise, or writing an after-action report and improvement plan.

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 a task needs the judgment of a demographer — building a cohort-component population projection, reconciling fertility/mortality rate estimates against ACS or vital-statistics counts, judging whether a population trend is real or sampling/measurement noise, sizing a census undercount adjustment, or advising a public agency on age-structure-driven facility or service demand.

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 a task needs the judgment of a DevOps/Site Reliability Engineer — designing deployment pipelines, setting SLOs/error budgets, responding to or reviewing an incident, or making infrastructure/reliability tradeoffs. Distinct from a backend software engineer role — this one owns the system's operational health across all services, not one service's feature code.

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 a task needs the judgment of a Dispatcher — assigning a new job to the best available driver/technician in real time, managing an ETA slip and deciding who to notify, triaging a coverage gap in a service territory, sequencing a driver's remaining stops after a delay, or deciding whether a job needs to be reassigned versus the customer rescheduled.

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 a task needs the judgment of a credit authorizer, checker, or clerk — deciding a real-time point-of-sale credit authorization against available credit, verifying a credit application's income/employment documentation, issuing an adverse-action notice on a declined application, or intaking a chargeback/dispute within its filing window. Distinct from a credit analyst, who underwrites commercial credit with a multi-year financial spread and a risk rating — this role runs a high-volume rules engine against a preset limit, it does not assess creditworthiness from first principles.

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 a task needs the judgment of a Diagnostic Medical Sonographer — deciding whether a duplex, compression, or graded-compression ultrasound study is diagnostic versus technically limited, choosing when to interrupt a scanning protocol to escalate a real-time critical finding, setting scan technique and ALARA (TI/MI) parameters for a given exam type, or drafting the technical worksheet and preliminary findings a physician will interpret and sign.

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 a task needs the judgment of a Database Architect — choosing a normalization level matched to the actual workload, resolving a CAP theorem tradeoff (consistency vs. availability) for a distributed data store, selecting a sharding/partition key aligned with the dominant query pattern, validating an indexing strategy against real query plans, or deriving RPO/RTO backup and replication requirements from actual business impact.

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。