「spot」の検索結果

Use when a task needs the judgment of a construction laborer — determining which OSHA-mandated protective system (sloping, benching, shoring, or shielding) a trench needs given its soil classification and depth, working as spotter/signal person on a crane or heavy-equipment lift, staging material and equipment on an active multi-trade site, or reading which hazard zone (excavation, crane swing, electrical rough-in) is live as work moves across the site.

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 retail/grocery cashier — reconciling a till at shift close, deciding whether to accept a large bill or flag it, handling a no-receipt return, de-escalating a price dispute at the register, or spotting a shortage pattern that looks like theft versus error.

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 Broadcast Program Director — diagnosing a ratings-book decline into cume vs. TSL causes, deciding whether a format flip is warranted versus a clock/rotation fix, setting spot-load and stopset structure against sales pressure, or clearing content through standards-and-practices and FCC compliance review.

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 Application Security Engineer — checking whether an endpoint verifies object-level authorization (not just authentication), running threat modeling at design time rather than deferring security review to the end, triaging a dependency vulnerability by actual reachability rather than CVSS score alone, combining SAST/DAST/SCA tooling to cover their distinct blind spots, or applying context-specific output encoding to untrusted input. Distinct from an information security analyst — this role works inside the SDLC to prevent vulnerabilities before they ship, not detect and respond to intrusions in production.

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 Aircraft Cargo Handling Supervisor — verifying a built ULD against its type's certified max gross weight before it's spotted for loading, running a hazmat item through the segregation table against its actual compartment neighbors, reconciling an actual cargo build against the dispatcher's load plan and deciding whether it clears a last-minute-change threshold or needs a reissued loadsheet, calling a ULD's lock/net restraint good or rejecting it, or running ramp FOD and ground-equipment clearance discipline around an aircraft during turn.

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。

Invoke a Rubber Duck Reviewer subagent to independently critique plans and implementations before proceeding. Use when the agent is about to implement a non-trivial plan (multi-file changes, architectural decisions, security-sensitive logic, database schema changes), after completing a self-contained unit of work (module, endpoint, feature), when stuck or facing repeated failures (same test fails 2+ times, unexpected results), or when the agent wants independent validation of assumptions and design decisions. Triggers on any non-trivial implementation task where independent critique would catch blind spots before they become costly mistakes.

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 discernment habits: nudges and checklists for evaluating claims, spotting manipulation, and thinking clearly under pressure. Use when you want better judgment about what to believe and share.

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 a monthly money check-in with an AI assistant: categorize spending, spot leaks, set one savings target, and view it through the 50/30/20 lens — judgment-free. Use once a month to stay aware of where your money goes. General educational information, not financial advice.

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。

Inventory and prioritize all technical debt in a codebase. Scans for TODO/FIXME/HACK markers and stale comments, outdated and deprecated dependencies with CVE detection, high-churn files and cyclomatic complexity hotspots, duplicated code blocks.

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。

Computes development quality and velocity metrics from git history and tracks improvement over time. Measures fix ratios, rework hotspots, test coverage, DORA metrics, and code churn.

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。

Deliver feedback using Kim Scott's Radical Candor framework - care personally while challenging directly. Use when a leader needs to give difficult feedback, says "I need to tell someone something hard", "how do I give feedback without hurting them", "I've been avoiding a conversation", "my direct report isn't performing", "someone on my team has a blind spot", "I keep sugarcoating things", or "how do I be honest without being a jerk". Also trigger when someone describes being too nice (ruinous empathy) or too harsh (obnoxious aggression), or when they describe avoiding a conversation they know they need to have.

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。

**WORKFLOW SKILL** — Structured context analysis before acting. USE FOR: questioning assumptions, mapping dependencies, identifying blind spots, validating scope of any task or subject. Use to contextualize, question, analyze before implementing, review premises, prevent hallucination, structured assessment. DO NOT USE FOR: simple tasks where task-intent suffices, direct implementation, code review.

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 and updates secure, production-ready Kubernetes YAML manifests optimized for GKE Autopilot and GKE Standard clusters. Use when creating or modifying GKE deployment manifests, configuring container security contexts, setting CPU/memory resource limits, defining readiness/liveness/startup probes, mounting secrets and volumes, configuring GKE Gateway API routes, targeting Spot VMs, or deploying AI model inference workloads (vLLM, TGI, Gemma). Don't use for live cluster operations, pod troubleshooting (use gke-workload-troubleshooting), or cluster infrastructure provisioning (use gke-cluster-creation).

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。

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto Provisioning configuration or general GKE cluster creation.

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。

Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or non-JobSet application 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。

Assists in provisioning instances/tables, designing performant schemas, and querying data in Bigtable. Use when designing Bigtable row keys, configuring column families, writing SQL queries or client library code (Java, Go, Python) for Bigtable, or diagnosing performance/hotspotting issues. Also use when provisioning Bigtable clusters using gcloud or cbt CLIs. Don't use for generic Cloud SQL administration.

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。

Spot patterns appearing in 3+ domains to find universal 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。

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews 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 building a frontend and the user wants a distinctive / animated / "wow" UI element in React + Tailwind - e.g. a laptop-opening-on-scroll, 3D tilt card, spotlight hero, animated beams/background, marquee, bento grid, interactive globe, meteor/particle background, shimmer button, or scroll/reveal motion. Fetches the showpiece component LIVE at build time from code libraries (Aceternity, Magic UI, Cult UI, ReactBits, 21st.dev) via their shadcn registry command (or WebFetch fallback), then adapts it to brand tokens. Also covers plain components (button, form, modal, table, etc.) as a fallback. Triggers on "make it pop", "something flashy", "animated [X]", "like [cool site]", "build a [showpiece] section". NOT for non-React stacks. Inspiration galleries (Dribbble/godly) are visual reference only - never 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。

Track every dollar, enforce budgets, spot spending patterns, and build wealth — all through natural conversation with your AI agent.

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。

**精度验收标准**：凡是"改动不应改变结果"的场合（等价替换、算子/子模块融合、并行切分、 编译与图下发、拷贝消减），都按本标准判"合格 / 不合格"——等价分层（L1 逐位 / L2 数值门 / L3 有损门）+ 三级验收序（① 同配置重跑逐位 → ② 跨配置数值门 + 产物 md5 不变 → ③ 质量门）+ 判据不达标时的排障入口。当用户说"这个算子能不能换个写法/换个 kernel/等价实现/ 无损替换""替换后结果会不会变""怎么证明逐位一致""结果不对""花屏""尾部塌了" "CPU 跑对 NPU 跑不对"，或发现某个 hotspot 占了大头（例如某类算子在阶段里占 90% 以上）想动手时， 都应触发；即使用户只说"这样改有没有把结果改坏""能不能判它是无损的"也应触发。 覆盖：等价分层与判据、满足本标准的实现约定（per-shape 对拍写进实现，把索引/相位/顺序类重写 错误在首次调用抓住）、per-shape 条件性等价（同一改动在不同形状下结论可能不同）、 判据不达标 → `references/silent-failure-localization.md` 排障入口、否决案例的形态学 （换写法未换 kernel / 差异极小仍非逐位 / 等价但 OOM）、以及收益口径的归属（性能数字一律交 `perf-gate`）。 **近义分流**：选量化档 / 特性选档（要不要开量化、开哪一档）→ `dit-perf-opt`； 并行选型（USP / CP / TP 怎么切）→ `dit-parallel-opt`；本技能只判"结果是否被改变"， 不负责选档与选型。

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。

Transforms police body camera transcripts into structured 10-section legal summaries with timestamp-cited verbatim statements, constitutional issue spotting, evidence inventory, and probable cause articulation. Maintains strict neutrality for all parties. Use when analyzing BWC footage for discovery, pre-trial prep, or trial. Trigger: body camera, BWC, body worn camera, officer footage, use of force review, incident summary.

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。

Assigns pathogen lineages (SARS-CoV-2 Pangolin UShER mode; Nextclade clade + QC; pango-designation alias resolution) and tracks variant frequencies over time using Nextstrain (Augur + Auspice), wastewater deconvolution (Freyja, COJAC, alcov, lineagespot), lineage-fitness modelling (multinomial logistic), and recombinant detection (3SEQ, RDP4, Bolotie). Covers Pangolin pangolin-data and Nextclade dataset version pinning (mandatory; lineage-defining mutations change with dataset), Freyja barcode forward-only date constraint, ARTIC primer scheme churn (V3/V4/V4.1/V5.3.2/Midnight) with dropout regions, and recombinant X-prefix designation lag. Use when assigning Pango lineages and Nextclade clades to viral consensus sequences, building Nextstrain Augur surveillance pipelines, deconvolving wastewater into lineage frequencies with Freyja, tracking lineage frequencies over time, handling ARTIC primer dropouts, or running surveillance for SARS-CoV-2/influenza/Mpox/RSV/H5N1/measles.

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。

Plot per-gene mutation distributions on a protein-domain map (lollipop / needle plots) showing mutation position, recurrence count, and variant classification with maftools, g3-lollipop, trackViewer, and ProteinPaint. Use when visualizing recurrent mutation hotspots on a single gene's protein, marking domain boundaries from UniProt/Pfam, comparing missense vs truncating distributions, or contrasting two cohorts on the same lollipop.

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。