344 件 ・ 関連度順
概要と使いどころ
Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.
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 this skill when building, reviewing, or refreshing a RACI (Responsible / Accountable / Consulted / Informed) matrix for a Salesforce project so that every Salesforce-specific decision — data model change, automation tier choice, security model, integration boundary, deployment, license/edition — has exactly one accountable owner and a documented escalation path that downstream agents can route to. Trigger keywords: RACI matrix salesforce project, stakeholder authority salesforce, escalation path salesforce decisions, who approves data model change, salesforce decision rights, REFUSAL_NEEDS_HUMAN_REVIEW routing. NOT for the change advisory board operating model itself (use admin/change-management-and-deployment). NOT for end-user training rollout plans (use admin/change-management-and-training). NOT for the technical mechanics of permission set assignment authority (use admin/permission-set-architecture). NOT for pure stakeholder requirements elicitation (use admin/requirements-gathering-for-sf). More trigger keywords: who approves a sandbox refresh, who signs off a data load, release update activation owner, delegated admin authority vs RACI, multi-org decision rights, escalation time-box.
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。
Curação de dados acelerada por GPU para treinamento de LLM. Suporta texto/imagem/vídeo/áudio. Recursos incluem deduplicação fuzzy (16× mais rápida), filtragem de qualidade (30+ heurísticas), deduplicação semântica, redação de PII, detecção NSFW. Escala em GPUs com RAPIDS. Use para preparar datasets de treinamento de alta qualidade, limpar dados web ou deduplicar grandes corpora.
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。
Prepare and launch LoRA, LoKr, or T-LoRA training through lora-scripts-next (SD-Trainer), Anima-first. Use when the user asks to train a character, style, or concept LoRA, choose parameters or repeats and epochs, start a run, or monitor training on Anima, SD1.5, SDXL, or Flux. Organize and caption the dataset, run dataset-doctor, choose a documented starting preset from image count and VRAM, show one confirmation card, then call the mikazuki API and monitor its log.
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。
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
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。
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
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。
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
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。
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
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 Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
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。
文章をAIが扱う小さな単位に分け、大量のテキスト処理や独自の語彙学習を支援するスキル。分割結果と元の文章の位置対応、入力の長さ調整も扱います。
Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service — even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a library name, debugging that involves library-specific behavior, setup instructions, and CLI tool usage. Use even when you think you know the answer — do not rely on training data for API details, signatures, or configuration options as they are frequently outdated. Always verify against current docs. Prefer this over web search for library documentation and API details.
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。
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a library name, debugging that involves library-specific behavior, setup instructions, and CLI tool usage. Use even when you think you know the answer. Do not rely on training data for API details, signatures, or configuration options — they are frequently out of date. Prefer this over web search for library documentation.
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 evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.
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 time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Supports both basic forecasting and advanced covariate forecasting (XReg) with dynamic and static exogenous variables. Automatically checks system RAM/GPU before loading the model, validates dataset fit before processing, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model and handle your specific dataset.
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。
Systematic claim-by-claim verification for any content before it ships. Modeled on professional fact-checking desks (The New Yorker, ProPublica, IFCN standards): extract every verifiable claim, check each against live citable sources (never training data), assign a 6-level confidence status, apply corrections, and produce a scored pass/fail report. Includes a data-derived-claims gate for outputs produced FROM the brain or a database: PRODUCER ≠ VERIFIER (re-derive each claim via a different query path) and AFFILIATION ≠ AUTHORSHIP (person→thing claims resolve through typed edges), with delivery hard-blocked on unsupported 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。
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。
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
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。
Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count, failure_count, pixel-intensity histogram) across NVFLARE sites via FedStatsRecipe — automatic and non-interactive from the dataset, feature names (header or supplied), and optionally a README or notes declaring which statistics to compute; do not use for model training conversion, hierarchical statistics, deployment, POC/production lifecycle, or failed-job diagnosis.
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 cell type annotation for IMC data. Covers napari-based annotation, marker-guided labeling, training data generation, and annotation validation. Use when manually annotating cell types for training classifiers or validating automated phenotyping results.
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。
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.
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 engineering or selecting the best features for single-response classification or regression in MATLAB, whatever the data's modality — for non-tabular data it routes extraction to a domain skill, then selects, assesses, and delivers on the resulting table. Not for multi-response problems, model training, or raw data acquisition.
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。
Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.
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 code that transforms datasets between ML schemas for model training or evaluation. Use when the user says "transform", "convert", "reformat", "change the format", or when a dataset's schema needs to change to match the target format — always use this skill for format changes rather than writing inline transformation code. Supports OpenAI chat, SageMaker SFT/DPO/RLVR/RLAIF, HuggingFace preference, Bedrock Nova, VERL, and custom JSONL formats from local files or S3.
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。
Collaboration platform configuration methodology for legal matter sites. Site architecture, workflow identification, dashboard design, data quality governance, and user adoption for SharePoint, Teams, and equivalent platforms. M365 is the reference implementation — outputs are platform-agnostic enough to brief IT or build simple automations without becoming a Power Automate manual. Use when setting up a matter site, identifying workflows to automate, designing reporting dashboards, managing platform data quality, or driving user adoption. Trigger on: 'set up the matter site', 'configure SharePoint', 'build a dashboard', 'what should we automate', 'brief IT on this workflow', 'nobody is using the platform', 'data quality is poor', 'set up Teams channel', 'matter site structure', 'alerts and notifications', 'user training', 'platform governance', 'status dashboard', 'what workflows can we automate', 'matter site template'.
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。