1,272 件 ・ 関連度順
概要と使いどころ
Used by the Developer agent during Phase 8 (Implement) when building web components, pages, or UI features. Provides strict aesthetic guidelines to create distinctive, production-grade frontend interfaces that avoid generic 'AI slop' aesthetics.
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。
host / 辅助段优化模块（L3）：把**非 DiT、非解码段**的固定开销落成可复验的优化—— ① 交付与搬运（mp4/图片编码、worker→API 通路、落盘、异步化）； ② 装载与预热（权重加载、编译与图下发预热、镜像/容器预热）。 当用户说“mp4 编码/传输/落盘慢”“交付这段占了不少时间”“模型加载慢”“首启编译太久” “固定开销占比高”“每个请求都要重新编码/重新写盘”时使用。 **入口条件**：占比已达门限（瓶颈标签 `非DiT-host段`；标签枚举、门限与测点口径的单一真源在 model-auto-optimization/references/bottleneck-labels.md，本技能只消费不定义）。 near-miss（看似相关但不属本技能）： - **并发 / 吞吐 / 批处理调度 / 队列深度与限流** → **不属本技能**（会改变所有性能口径与 SLO 语义， 未来独立立项；本技能只在**不改变请求并发模型**的前提下压固定开销）； - VAE/TAE 解码段（计算或通信）→ `vae-opt`；DiT 计算 → `dit-perf-opt`； 多卡并行 / 通信掩盖 → `dit-parallel-opt`； - **装库 / 下载权重 / 构建镜像 / 创建容器** → `env-install`（本技能只优化装载与预热**过程本身**）； - 编译与图下发的**机制本体**（pattern / Inductor / NPUGraph / 图 pool / 缓存条目）→ `pattern-dev` / `aclgraph-dev`（本技能不另做一套缓存）； - 产物一致性与精度判据 → `accuracy-gate`；收益口径 → `perf-gate`； - 瓶颈未定位 / 没有占比锚点 → `model-auto-optimization`。
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 structured U.S. aviation-law summaries by synthesizing FAA, DOT, and TSA rules, treaties, and precedent into actionable legal analysis. Use when briefing on air traffic rights, aircraft operations, airworthiness, carrier liability, or incident/compliance exposure. Trigger: aviation law, FAA, DOT, TSA, 14 CFR, Part 121/125/135, Montreal Convention, Warsaw Convention, ICAO, route authority, code-sharing, slot allocation, accident liability.
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。
Deep Vue 3 best-practices review and authoring workflow: built-in components (Teleport, Suspense, KeepAlive, Transition), animations, slots, directives, render fns, perf pass. Complements mk:vue.
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。
Reviews a GitHub PR with a shallow correctness/security/breaking/AI-slop checklist and emits a verdict; optionally posts via gh. NOT for own-diff audit (mk:review); NOT for replying (mk:respond-pr).
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。
Reviews a GitHub PR with a single shallow correctness/security/breaking/AI-slop checklist and emits a verdict; optionally posts it via gh pr review. Use to review an external or teammate PR. NOT for deep pre-landing audit of your own diff (see mk:review); NOT for responding to received review comments (see mk:respond-pr).
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。
Read-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against the model context window. NOT for monetary cost tracking — that's /mk:budget. NOT for transcript size monitoring — long-session continuity defers to Claude Code native compaction. NOT for runtime context decisions (what to read, when to compact) — see mk:context-engineering. Use when planning to add context capacity, diagnosing perceived slowdowns, or auditing health.
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。
Investigate reviewed Grafana APM evidence for request rate, error rate, and operational latency. Use when an application is slow, erroring, dropping traffic, regressing against a baseline, or needs a bounded request-rate, error, and p95 latency health 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。
Use when optimizing Docker builds with BuildKit, designing multi-stage Dockerfiles, leveraging cache mounts, building multi-arch images, choosing distroless vs alpine, or signing images with cosign. Triggers: docker build slow, layer cache not hitting, npm install / pip install reruns, multi-stage final image bloat, glibc vs musl issues, RUN --mount=type=cache, BUILDKIT_INLINE_CACHE, registry cache exporters, qemu emulation for arm64, COPY ordering for cache. NOT for Docker daemon admin, Kubernetes-specific image policies, container security scanning workflows, or Buildpacks (different paradigm).
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。
Detect syntenic blocks and structural rearrangements between genomes using MCScanX (Wang 2012), JCVI/MCScan (Tang 2008 Python), GENESPACE (Lovell 2022) for orthology-anchored riparian visualization, SyRI for structural variation, AnchorWave for sequence-level synteny, i-ADHoRe 3.0 for highly diverged species, SynNet for synteny networks, and ntSynt for multi-genome macrosynteny. Use when identifying collinear gene blocks across species, distinguishing macrosynteny from microsynteny, detecting inversions/translocations/duplications, anchoring orthology in WGD lineages, producing publication riparian plots, computing synteny block age via Ks (cross-references whole-genome-duplication), or running synteny-aware ortholog inference in polyploids.
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。
Bulk-query Ensembl BioMart (and other BioMart instances) for cross-database ID mapping, gene/transcript/exon coordinates, and ortholog tables. Use when batch-converting Ensembl IDs to other namespaces (HGNC, RefSeq, UniProt, Entrez), pulling gene coordinate tables for thousands of genes, building ortholog wide-tables across species, or replacing slow Ensembl REST loops with one-shot bulk export. Encodes BioMart's XML query format, R biomaRt vs Python pybiomart trade-off, mart-vs-dataset hierarchy, and the URL endpoint that's BioMart-specific (separate from rest.ensembl.org).
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。
Performs subgroup and heterogeneous treatment effect (HTE) analyses for clinical trials. Covers Mantel-Haenszel pooling, Breslow-Day, interaction tests in regression, RERI for additive interaction, modern data-adaptive HTE methods (STEPP, SIDES, causal forests, X/R-learners), Bayesian shrinkage (Dixon-Simon, MAP, EXNEX), graphical multiplicity (Bretz-Maurer), and credibility frameworks (Sun BMJ, EMA 2019). Use when analyzing treatment effects across patient subgroups for regulatory submissions or precision-medicine claims.
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。
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.
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。
Review a written plan or design doc through a designer's lens before implementation - seven passes over information architecture, interaction states, emotional arc, AI-slop risk, design-system alignment, responsive and accessibility coverage, and unresolved decisions. Each dimension is rated 0-10 with an explicit statement of what would make it a 10, then the plan is edited to get there. Use when a plan has a UI surface and you want the design gaps closed before code is written. Not for auditing a live 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。
Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.
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。
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
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。
Measure real frontend performance — Core Web Vitals (LCP, CLS, INP), page-load traces, CPU and network throttling, Lighthouse accessibility/SEO scores, and heap growth — using chrome-devtools-mcp against a live browser. Trigger when asked "is the page fast enough", "measure Core Web Vitals", "why is this route slow", "run Lighthouse", "check for a memory leak", before any performance-gated certification (Built for Shopify, Core Web Vitals thresholds, store listing review), and before any launch or traffic-multiplier event. Measurement only — this skill never drives functional journeys.
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。
Measure, root-cause, fix, verify and record performance contention on a developer machine: cloud-sync daemons (iCloud Drive, OneDrive, Dropbox, Google Drive), file indexers, AI-tool MCP server fleets, and automation browsers left behind by tests and browser skills. Trigger when the machine is slow, apps freeze, browser or MCP tool calls time out, load exceeds the core count, or before and after any UI/UX/performance test run. Includes the L0–L4 optimisation scale and the test-hygiene contract.
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。
Shaping a UI component tree — composition vs inheritance, slot patterns, prop API design, controlled vs uncontrolled, polymorphic — on 'split this component'. Feeds react-shadcn-ui.
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 adding/installing any dependency the agent named — verify the package exists (slopsquatting: ~1 in 5 AI suggestions are hallucinated), isn't typo-adjacent, is pinned + locked, and CVE-scanned
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 writing raw SQL — MariaDB/MySQL syntax, parameterization, raw migrations, seeders with `DB::statement`; fires even on a pasted query asking 'why is this slow'.
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 shaping employee onboarding — time-to-productivity, role-by-role program, mentor pairing, 30/60/90 milestones. Triggers on 'design our onboarding', 'why are new hires ramping slow'.
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 establishing what observability a project actually has — the four Golden Signals, required signal to detected implementation to evidence, and SLI/SLO provenance.
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 qualifying or disqualifying a single deal — MEDDIC slots with evidence, inversion test, disqualification heuristic. Triggers on 'is this deal real', 'should we walk away'.
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。