674 件 ・ 関連度順
概要と使いどころ
Patterns for running AI models locally in browsers using WebGPU, Transformers.js, WebLLM, and ONNX Runtime. Zero API costs, full privacy. Use when "on-device AI, browser AI, WebLLM, Transformers.js, WebGPU, edge inference, offline AI, client-side ML, ONNX web, " 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。
Semantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-to-definition, find-references, hover types, type diagnostics, file symbol outlines, and project-wide symbol search — name resolution and type inference that tree-sitter and ripgrep cannot do. Use when you need to follow an import to a definition, find all real uses of a symbol (excluding same-named-but-unrelated ones), get an inferred type, surface type errors, outline a file, or search symbols across a project. Triggers on "go to definition", "find references", "what type is", "resolve this symbol", "symbol outline", "find symbol in project", "pyright", "type-check this file".
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。
Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Activate when users provide time series data and request forecasts, predictions, or extrapolations. Supports Reverso Small (550K params). Triggers on "forecast", "predict", "time series", "Reverso", or when tabular data with a temporal dimension needs future-value estimation.
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 a fully structured SEO content **outline** (not a finished brief) and exports it as a formatted .docx Word document. The output is a skeleton for a writer to fill in — section headings, topic prompts, angles — not pre-written paragraphs. Use this skill whenever a user provides a blog title, focus keyword, domain URL, or any combination of those and asks to generate an outline, brief, blog brief, SEO brief, article structure, or content plan. Also trigger when the user says "create a brief for X", "generate an outline for [topic]", "make a content brief", "I need a brief for [URL or keyword]", or pastes a title and asks what the structure should look like. This skill handles input validation, domain analysis, keyword enrichment, audience inference, archetype-aware section selection, and full .docx generation — always use it rather than writing ad-hoc outlines.
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 Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions. Reach for this skill whenever Claude encounters questions about causal inference, structural causal models, the limitations of deep learning, AGI, experimental design, covariate selection, or personalized decision-making. Trigger this skill for topics involving Bayesian networks, the do-calculus, the Ladder of Causation, or when a user tries to answer 'what if' or 'why' questions using purely observational data. Pearl's principles are essential for moving beyond probability calculus into true causal understanding.
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 expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered features.
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。
Tests whether changes caused a metric move without a clean A/B test: DiD, synthetic control, IV, RDD. Use when asking did a launch cause lift.
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。
Tests whether data supports a claim: A/B significance, peeking, sample size, eval error bars, multiple comparisons. Use when deciding if results are significant.
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。
LLM serving for latency, batching, caching, quantization, and routing. Use when tuning vLLM or SGLang, sizing KV cache, adding speculative decoding, or cutting serving cost.
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。
Submit protein folding tasks to the AlphaFold3 C550 inference platform. Use when the user needs to run AlphaFold3 predictions with pre-prepared JSON input files on the AI4S Kubernetes cluster.
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。
Design and configure model serving infrastructure — endpoint scaling, batching, GPU allocation. Use when asked to "serve this model", "design an inference endpoint", or "size GPU allocation for serving".
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。
Design cost reduction strategies — model tiering, prompt compression, caching, batch inference. Use when asked to "reduce our AI costs", "set up model tiering", or "cut LLM spend".
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 analysis, ANOVA, generalized linear models, Bayesian methods, and model selection. Covers the full modeling workflow from problem formulation through diagnostics -- linear regression, logistic regression, Poisson regression, mixed-effects models, prior specification, posterior inference, AIC/BIC comparison, cross-validation for model selection, and assumption checking. Use when fitting models, testing hypotheses, or selecting among competing statistical explanations.
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。
A/B testing, randomization, sample size calculation, confounding control, and causal inference for data science. Covers the full experimental lifecycle from hypothesis formulation through power analysis, randomization strategies, blocking, factorial designs, sequential testing, and the potential outcomes framework for causal claims. Use when designing experiments, planning A/B tests, calculating sample sizes, or reasoning about causation from data.
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。
MLOps and the production ML lifecycle -- model packaging and serving, CI/CD for ML, experiment tracking, model registries, reproducibility, production monitoring for data and concept drift, retraining pipelines, A/B and shadow deployment, and rollback. Covers batch vs online/real-time inference, REST endpoints, feature stores, data and version pinning, deterministic pipelines, performance-decay detection, and retraining triggers. Use when deploying models to production, serving predictions, monitoring for data or concept drift, setting up ML CI/CD, tracking experiments, managing a model registry, or planning retraining, shadow rollout, and rollback.
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。
Core programming concepts from variables through recursion. Covers data types (integers, floats, strings, booleans, arrays, objects), variables and scope (lexical, dynamic, block, function, global), control flow (conditionals, loops, pattern matching), functions (parameters, return values, closures, higher-order functions), recursion (base cases, call stack, tail recursion, mutual recursion), type systems (static vs dynamic, strong vs weak, type inference, generics), and error handling (exceptions, Result types, defensive programming). Use when teaching, reviewing, or diagnosing issues with fundamental programming constructs.
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 the moment a request is underspecified and you are about to act on an ASSUMED goal. Enumerate the candidate goals the request could mean, project the action or artifact each one implies, and check whether they diverge: if two or more plausible goals lead to materially different actions or artifacts, ask exactly ONE targeted clarifying question; otherwise proceed on the most-likely goal and state the assumption in one line. Clarification is an evidence-producing action, not a delay — but one question, never an interrogation. Distinct from gsd-spec-phase (GSD-phase-bound, emits a heavy SPEC.md) and intent-router (fetch strategy, not goal disambiguation). Backed by agent goal-state inference (arxiv 2606.16813v1). Triggers on acting under an assumed goal when the request admits more than one materially different reading.
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。
Compressive Vasomotion Hypothesis (CVH) — vasomotion as a fast compression sweep that collapses ambivalent neural resonances (the Bayesian-blur problem) into a definite state. Use when modeling the ~100ms taṇhā 'grab', precision-weighting as compression forcefulness, or the generative collapse step of vasocomputational active 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。
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
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。
Hypothesis-Test Loops via REPL for Exploratory Abductive 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。
Design pattern for converting rule-following, checklist, or rubric skills into a fan-out map-reduce ensemble of parallel rigid sub-agents with corroboration-weighted merge; worker model tier and diversity are knobs matched to inference load and stakes, not fixed values. Apply when creating or refactoring a skill or agent that applies 10+ independent criteria in a single pass. Triggers on: 'review against a checklist', 'fan out', 'map reduce review', 'ensemble', 'split the rules', 'apply rubric', or any large ruleset being applied by one agent in one pass. NOT for tight single-pass transforms or rulesets under 5 criteria.
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 setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.
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 an existing conjoint study for threats to inference and returns severity-ranked findings on design, estimation, measurement error, external validity, and interpretation. Use when checking whether a conjoint design or analysis holds up, or answering referee comments on one.
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 an existing conjoint study for threats to inference and returns severity-ranked findings on design integrity, estimation, measurement error, external validity, and interpretation, including the guardrail against reading an AMCE as majority preference. Use when the user asks whether a conjoint design or analysis holds up, has referee comments on a conjoint, or wants a second opinion on estimation or interpretation. New designs go to conjoint-design, reshaping to conjoint-cleaning.
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。