「ml」の検索結果

Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for training orchestration, builds feature store schemas with Feast, deploys model registries, and automates retraining and validation workflows. Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, managing experiment tracking systems, setting up DVC for data versioning, tuning hyperparameters, or configuring MLOps tooling like Kubeflow, Airflow, MLflow, or Prefect.

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。

This skill covers causal machine learning methods in applied economics and quantitative social science. Use when implementing or choosing between modern ML-based causal estimators — including double machine learning, DML, partially linear models, interactive regression models, cross-fitting, Neyman orthogonality, debiased ML, causal forests, generalized random forest, GRF, honest causal trees, AIPW with machine learning, doubly robust with machine learning, DR-Learner, T-Learner, S-Learner, X-Learner, meta-learners, heterogeneous treatment effects, conditional average treatment effect, CATE, HTE, high-dimensional controls, LASSO controls, post-LASSO, post-double selection, Belloni-Chernozhukov-Hansen, Riesz representer, Chernozhukov, sample splitting, econml, DoubleML package, or any combination of machine learning and causal inference.

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。

Direct-invocation specialist for low-fidelity, self-contained HTML wireframes that test information hierarchy, content, navigation, task flow, and responsive structure before visual design. Use when the user explicitly invokes html-wireframe or the broad html skill routes a wireframe request here. Do not activate independently from a general request. Do not use for polished mockups or production-like interaction; use html-prototype for those.

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。

Call copy number variants with the GATK best-practices workflows — the somatic CNV pipeline (CollectReadCounts, DenoiseReadCounts with tangent normalization, ModelSegments, CallCopyRatioSegments) and the germline GATK-gCNV pipeline (DetermineGermlineContigPloidy, GermlineCNVCaller cohort/case mode, PostprocessGermlineCNVCalls). Covers panel-of-normals construction, AnnotateIntervals/FilterIntervals, allelic-count integration, and QS-based filtering. Use when integrating CNV calling into a GATK variant pipeline, calling rare germline CNVs from an exome cohort, deciding between the somatic and germline GATK workflows, or diagnosing why tangent normalization removed a real event or why gCNV output has low precision.

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。

Strategic guidance for operationalizing machine learning models from experimentation to production. Covers experiment tracking (MLflow, Weights & Biases), model registry and versioning, feature stores (Feast, Tecton), model serving patterns (Seldon, KServe, BentoML), ML pipeline orchestration (Kubeflow, Airflow), and model monitoring (drift detection, observability). Use when designing ML infrastructure, selecting MLOps platforms, implementing continuous training pipelines, or establishing model governance.

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 HTMLHint in .NET repositories that ship static HTML output or standalone frontend templates. USE FOR: static HTML files; generated frontend output; standalone templates under wwwroot, dist, or other web folders; HTML structure checks. DO NOT USE FOR: raw .cshtml or .razor source with server-side directives; JavaScript or TypeScript linting. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

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 QML best practices when producing or working with QML source code. Use whenever QML code is the primary subject: writing, reviewing, fixing, refactoring, optimizing, or debugging QML files, components, or bindings. Do NOT trigger for purely conversational QML questions where no code is produced or examined (e.g. "explain how anchors work").

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。

Extract component metadata from a Figma design system and generate production-ready QML controls. Use this skill whenever someone wants to turn Figma components into QML files — whether they say "generate components from Figma", "create QML controls based on a design system", "convert Figma components to QML", "build the component library", "extract button/input/checkbox from Figma", or anything similar. Requires design-tokens.json and QML design system singletons to already exist (from the token extraction skill). Uses Figma MCP to inspect components one at a time and maps variants, states, sizing, and token usage to idiomatic Qt Quick Controls 2 patterns. Trigger this skill at the component generation step of any QML design-system workflow.

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。

Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover. Each of those installs one backend; none of them help you DECIDE which backend fits your stack/scale/budget, nor give you a one-line autolog that turns it on fast. Use when starting any LM project, before the first deploy, or the moment someone asks "why did it do that?" and there are no traces to answer with. The skill picks a backend by stack (LangSmith for LangChain/LangGraph; Phoenix for OSS/local OpenTelemetry; MLflow for ML-shops already on MLflow; Langfuse for self-host), wires one-line autolog, verifies traces land, and adds eval hooks — instrumenting BEFORE you need it. Cross-links the first-debug-move skill [[agentsop-prompt-history-inspect]]. Do NOT activate to re-teach a backend you already chose (defer to its own skill), or for non-LM ML experiment tracking with no LLM calls (that is plain MLflow).

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。

Chart.js を使ったインタラクティブなHTMLダッシュボードを構築するスキル。 「ダッシュボードを作って」「インタラクティブなレポート」「HTMLチャート作成」等のリクエストで発動。 フィルター・グラフ・プロフェッショナルなスタイリング付きのスタンドアロンHTMLを生成。

Use BentoML to author model-serving Services, build and containerize Bentos, run HTTP/gRPC servers and clients, manage models, operate the CLI and BentoCloud, and configure observability or production runtime behavior. Use when tasks mention BentoML, bentoml service.py, bentofile.yaml, Bento build/serve/deploy, BentoCloud, or BentoML model stores.

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。

Convert a stakeholder summary markdown file into a single self-contained HTML executive report — bottom line and decision asks up front, supporting detail later — styled with a Test Double-derived palette and self-contained mermaid diagrams. Use when the user wants to turn a stakeholder summary, executive summary, or business summary into an HTML report, generate an HTML version of a summary doc, or produce a shareable HTML file from a summary markdown. Produces an HTML sibling file only; does not publish anything.

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 interactive web applications using HTML/JavaScript interfaces with MATLAB computational backends via the uihtml component. Use when creating HTML-based MATLAB apps, JavaScript MATLAB interfaces, web UIs with MATLAB, interactive MATLAB GUIs, or when user mentions uihtml, HTML, JavaScript, web apps, or web interfaces.

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。

语音转文字 (ASR) (语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。) Master OS — automated mastery of 语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on 语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「语音转文字」「语音识别」「asr」「speech to text」「stt」

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。

コミュニケーション診断ツール（commu-checker）の各タイプ向け、90日トレーニングコンテンツを生成するスキル。 ユーザーが「D1型のトレーニングを作って」「〇〇型の90日プランを作りたい」「training-data.jsに追加したい」 「コミュ診断のトレーニングページ」などと言ったときに必ず使う。 タイプ定義・観察メモを受け取り、既存サイト（M PLUS Rounded 1c・グリーン基調・Material Icons）に合わせた インタラクティブなチェックリスト用HTMLコンテンツを training-data.js の TRAINING_PAGES オブジェクトに追加する形で出力する。 トレーニングは trainings/index.html + trainings/training-app.js + trainings/training-data.js の3ファイル構成。 個別の <type>.html は存在せず、URL の ?type=d1 などのパラメータで表示タイプを切り替える。

Client-ready HTML presentation builder for Kai audit and report folders. Converts weekly audits, monthly audits, marketing reports, scorecards, findings, data-source notes, and action plans into a polished single-file HTML deck with sourced metrics, executive slides, speaker notes, and delivery-ready styling. Use when "HTML presentation", "HTML deck", "client-ready audit deck", "turn this audit into slides", "present the weekly audit", "present the monthly audit", or any request to deliver Kai reports as HTML slides.

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。

AI-PLC Stage 1 Collection。GoalとModeからExecution Contextを確立し、Context Store、intent.yaml、context.yaml、backlog.yamlを生成する。

AWS の構成図を draw.io の XML（.drawio）で描く。公式の AWS4 アイコンを使い、タイトルや凡例や番号バッジのような装飾を足さず、どのサービスがどこにあって何とつながっているかだけで読める図にする。AWS 構成図、アーキテクチャ図、インフラ構成図、ネットワーク構成図、VPC の図を描いてほしいとき、draw.io で AWS の図を作りたいとき、既存の構成図を直したいときは必ずこの Skill を使う。Use this whenever the user asks for an AWS architecture diagram, cloud infrastructure diagram, VPC diagram, or a draw.io file of AWS resources, even if they don't say "draw.io". Mermaid、PlantUML、Python の diagrams ライブラリなど、ほかの形式を指定されたときは使わない。Do not use it when the user explicitly asks for Mermaid, PlantUML, or the Python diagrams library.

Used when the user asks to "create HTML slides", "generate an HTML presentation", "make animated slides", "build interactive slides", "create web slides", "GSAP presentation", "browser-based slides", "convert PPTX to HTML", "animated deck", "reveal.js slides", or when the output format is HTML for any presentation task. Also triggers on "single-file presentation", "CSS animations in slides", "scroll-based slides", or "web presentation". Generates self-contained, single-file HTML with viewport fitting, CSS/GSAP animations, and curated style presets.

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 stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Zero dependencies — single HTML files with inline CSS/JS. Use when the user wants a presentation, pitch deck, conference talk slides, HTML slideshow, slide deck, investor deck, demo day slides, keynote-style presentation, or says 'make slides', 'presentation', 'pitch deck', 'conference talk', 'convert my PPT', 'HTML slides', 'talk slides', or wants beautiful animated slides without PowerPoint. Also use when someone needs to present something and doesn't have a tool — this replaces Keynote, Google Slides, and PowerPoint with a single HTML file. Includes 12 curated style presets and PPT-to-HTML conversion.

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。

Convert PDF presentations to HTML slide templates using a visual reproduction approach. Pipeline: PDF → slide screenshots → Claude writes HTML matching each screenshot. Use when the user wants to convert a PDF to HTML slide templates, reproduce a presentation as HTML, or create reusable templates from existing decks. Triggers: 'pdf to html', 'convert pdf to template', 'reproduce this deck as html', 'create template from pdf'.

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 polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Also use for Archify, interactive or animated HTML diagrams, インタラクティブ図, 動く構成図. When an editable .drawio file is required, use the draw.io workflow instead and treat Archify HTML only as a supplement.

Call copy number variants with the GATK best-practices workflows — the somatic CNV pipeline (CollectReadCounts, DenoiseReadCounts with tangent normalization, ModelSegments, CallCopyRatioSegments) and the germline GATK-gCNV pipeline (DetermineGermlineContigPloidy, GermlineCNVCaller cohort/case mode, PostprocessGermlineCNVCalls). Covers panel-of-normals construction, AnnotateIntervals/FilterIntervals, allelic-count integration, and QS-based filtering. Use when integrating CNV calling into a GATK variant pipeline, calling rare germline CNVs from an exome cohort, deciding between the somatic and germline GATK workflows, or diagnosing why tangent normalization removed a real event or why gCNV output has low precision.

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。

Interactive Domain-Driven Design modeling sessions based on DDD Distilled (Vaughn Vernon) and Domain Modeling Made Functional (Scott Wlaschin). Guides users through strategic and tactical design via 13 phases: discover, storming, contexts, mapping, aggregates, events, validate, glossary, workflows, types, simulate, publish, sync. Phase 13 (sync) reconciles divergences found by --analyze between the domain model and the implementation — judging whether the model or the code is authoritative, then planning and implementing the fix and re-aligning the model. Phases 9-11 take the conceptual model from phases 1-8 and produce workflow pipeline designs, compilable type definitions (TypeScript, Kotlin, Scala, Rust, C#, F#), workflow verification via type-level tests, and automatic UI field enumeration from the domain model. Phase 12 (publish) renders all docs/domain artifacts into one self-contained, cross-linked HTML site (separate files joined by a shared nav). Each phase is an interactive dialogue where AI acts as facilitator and domain expert challenger. Use when: "DDD", "ドメイン設計", "ドメインモデリング", "Event Storming", "Bounded Context", "集約設計", "ユビキタス言語", "コンテキストマップ", "ワークフロー設計", "パイプライン設計", "ステップ分割", "中間型", "型駆動フロー", "型駆動設計", "Domain Modeling Made Functional", "Railway Oriented Programming", "入力画面項目", "フォーム項目洗い出し", "UI 項目抽出", "HTMLにまとめる", "ドキュメントサイト化", "成果物を1つのHTMLに", "publish", "モデルと実装の差異", "差異解消", "実装との乖離", "モデルとコードを一致", "差異の実装計画", "sync", "複数フェーズを逐次実行", "フェーズをまとめて実行", "/ddd run", "サブコマンド一覧", "/ddd list", "/ddd", "ドメイン分析したい", "モデリングしたい", or any domain design / type modeling activity.