「inference」の検索結果

Separate a strategy return series into declared baseline exposure and residual edge with returns-based OLS attribution, HAC inference, rolling stability, alternate-baseline sensitivity, and regime breakdowns. Use when evaluating whether backtest, out-of-sample, or live returns contain independent alpha beyond market, equal-weight, momentum, sector, or user-supplied factor returns; when explaining whether a drawdown came from baseline exposure or strategy-specific behavior; or when a strategy needs an attribution quality gate after backtesting. Do not use for holdings-based Brinson attribution, feature-level Shapley explanations, or analysis from summary metrics without a dated return series.

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。

Selects, deploys, and customizes AI models on Amazon SageMaker. Training or Processing jobs, fine-tuning (SFT/DPO/RLVR/RLAIF), model selection, dataset preparation, evaluation, SageMaker or Bedrock deployment, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing which base model to customize, fine-tune, or deploy from SageMaker JumpStart or Hub, SageMakerPublicHub, or the SageMaker public model catalog, transforming or validating training data, evaluating model quality, deploying or optimizing endpoints, configuring IAM/S3 for training, or managing SageMaker Managed MLflow. Use for endpoint health, failures, latency, logs, metrics, errors. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.

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。

Troubleshoots and debugs AWS Clean Rooms collaboration issues related to IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging for custom ML model training and inference jobs. Use when a customer reports permission failures, access errors, or log publishing issues in Clean Rooms.

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。

Organization-grade identity-fabric mapping: tenant/federation fingerprinting and the pre-auth user-ENUMERATION oracle methodology — enumeration and fingerprint only, never credential submission. Covers domain-to-tenant resolution (Microsoft getuserrealm.srf Managed/Federated namespace check, Entra OIDC metadata tenant-GUID extraction, Autodiscover v2), keyless Microsoft tenant-federation mapping (GetFederationInformation SOAP -> sibling-domain discovery, discover-only ROE, FEDERATED_WITH provenance edge held out of attack-path pivoting), Okta org-slug derivation + OIDC fingerprint + governed custom-domain enumeration, ADFS passive/active fingerprint + version inference, Google Workspace MX-correlated detection, generic OIDC (Auth0/Keycloak/Ping Identity/OneLogin/Duo) discovery, SAML metadata (5 paths), Azure AD Seamless-SSO Negotiate-challenge detection, Microsoft Defender for Identity (MDI) sensor-API presence check, the user-enumeration oracle methodology for Microsoft GetCredentialType (IfExistsResult semantics: exists / doesn't-exist / exists-in-federated-tenant / throttled) and Okta /api/v1/authn (errorCode differential), Medium-detectability discipline with a hard 20-candidate-per-tenant cap and admin/role interest-based ranking, and name x confirmed-email-pattern login-candidate synthesis that FAILS CLOSED with zero output when no org pattern is confirmed. Grounded directly in a production ASM implementation's sso_idp.py, tenant_recon.py, and core/email_patterns.py modules. Deepens — does not duplicate — offensive-osint skill's Identity Fabric endpoint reference with the tenant-federation MAP, the oracle WORKFLOW, and the candidate-SYNTHESIS methodology that reference lacks. Use when fingerprinting an organization's identity provider, mapping its tenant/federation boundary, running an authorized pre-auth user-enumeration pass, or synthesizing login candidates from harvested names to feed that oracle — never for password spray, credential submission, or auth bypass.

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/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.

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 and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.

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。

Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, token/cost accounting, per-episode artifacts, plus terminal viewers and a run-comparison report. Platform-agnostic: one small adapter covers OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, vLLM, or any custom inference stack, and the same tooling then works unchanged. Use this skill whenever the user wants observability, tracing, logging, or run tracking for model experiments; asks why an agent failed a task or wants to replay/debug/diff an episode; wants to compare models, arms, or ablations; wants to instrument a new folder, repo, or platform ("add observability here", "do the same for Tinker/Gemini/OpenAI"); wants to import or tie in existing experiment results so old runs show up alongside new ones; or wants eval runner scripts where many models share one protocol. Reach for this even when they only say "log what the model is doing", "I can't tell what happened in this run", or "set up traces for this experiment".

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 AI videos using ByteDance Seedance models via Volcengine Ark API. Supports text-to-video, image-to-video (first frame, first+last frame), multimodal reference (images+videos+audio), video editing, video extension, web search enhancement, audio generation, draft mode, offline inference, and continuous video chaining. Use when user wants to generate, create, edit, or extend AI videos from text prompts, images, videos, or audio.

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 epidemiological analyses including disease modeling (SIR/SEIR), outbreak investigation, risk factor identification, incidence/prevalence estimation, and causal inference from observational data; trigger when users discuss disease spread, public health data, or populat...

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 complete two-sample Mendelian randomization research designs from a user-provided outcome, exposure or exposure family, and robustness direction. Use when a study centers on summary-statistics causal inference with instrument selection, harmonization, IVW-primary estimation, complementary estimators, sensitivity analyses, optional multivariable upgrades, and conservative evidence interpretation. Covers five study patterns and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.

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 complete bidirectional multi-phenotype Mendelian randomization research designs from a user-provided exposure family and outcome family. Always use this skill whenever a user wants to design, plan, or build a genome-wide causal-inference study based on publicly available GWAS summary statistics, especially when the article logic includes multiple exposures, multiple outcomes or subtypes, bidirectional MR, IV filtering, IVW as the main estimator, weighted median / MR-Egger / MR-PRESSO sensitivity analyses, leave-one-out testing, heterogeneity / pleiotropy checks, and multiple-testing control with FDR. Covers five study patterns (single-family bidirectional MR, multi-phenotype screening MR, subtype-resolved MR, phenome-style bidirectional causal map, mechanism-prioritized MR follow-up) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version...

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。

Induce visual patterns from examples — few-shot visual reasoning, grid-based pattern recognition, and ARC-style inductive 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。

Hugging Face transformer model fine-tuning and inference for intent classification

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。

Apply general knowledge reasoning across diverse domains — trivia, commonsense inference, analogy, and factual question answering.

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。

WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero 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。

Replay an LLM inference request trace (Mooncake / vLLM / SGLang hash_ids format) against a block-level KV prefix cache and compute hit statistics. Use when given a request trace plus cache configuration and asked for hit rate, hit tokens, or final cache contents. Covers the longest-contiguous-prefix semantics that distinguishes KV prefix caching from full-prompt prompt caching, the policy-specific residency and eviction rules (LRU, LFU, S3FIFO), and the partial-last-block accounting rule.

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。

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.

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。

Master TypeScript with advanced types, generics, and strict type safety. Handles complex type systems, decorators, and enterprise-grade patterns. Use PROACTIVELY for TypeScript architecture, type inference optimization, or advanced typing patterns.

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 production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

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 or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this for "design a landing page", "build a settings screen", "make me a website", "design the onboarding", "ออกแบบหน้าเว็บ", "ทำหน้า landing", "ออกแบบ UI", "ทำแอป". It runs the pipeline no single skill covers: the house doctrine, a written Brief Inference so the result is not the statistical mean, a committed visual direction, tokens, build, the objective gates, then an adversarial critic. Hands off to data-dashboard for dense data screens, redesign for existing UI, and image-to-code when a reference image is given.

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。

Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when user says "preregister", "draft a preregistration", "OSF preregistration", "AsPredicted", "AEA RCT registry", "PAP", "preanalysis plan", or before launching an experiment / data collection / analysis on data the analyst has not yet seen. NOT a registry submission tool — produces a document the user uploads to OSF / AsPredicted / AEA themselves.

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。

Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation. WHEN: pod crashes or Pending, CrashLoopBackOff, OOMKilled, ImagePullBackOff, node NotReady, DNS or ingress failure, connectivity timeout, network policy, SNAT exhaustion, node-pool scaling blocked by QuotaExceeded or InsufficientVCPUQuota, upgrade stuck, spot or zone disruption, a bare VMExtensionProvisioningError or AllocationFailed wrapper, an uncataloged capacity symptom, or 'investigate my AKS cluster'. DO NOT USE FOR: packet capture (use aks-network-capture); GPU or model-serving issues (use aks-gpu-inference); cluster creation or provisioning (use azure-kubernetes); cost (use cost-analysis from the optional azure-cost plugin); pod rightsizing (use azure-kubernetes); a fully qualified documented AKS signature with every required nested qualifier (use aks-known-issues); standalone failures on non-AKS Azure resources (use azure-diagnostics). Unqualified errors and open-ended incidents stay here only for AKS.

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。

Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).

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。

Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on AKS", "run LLM on AKS", "vLLM on AKS", "set up model serving on AKS", "AI Runway controller".

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。