'training' 검색 결과

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Micro-decision analysis. Catalog the border radii, spacing scales, type sizes, and state coverage that most people miss. Use when auditing design systems, evaluating craft quality, or training granular perception.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Precise language for design feedback. Ban vague words. Name what you actually see. Use when giving design feedback, running critiques, or training teams to communicate about quality.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

15-minute daily taste exercises. Monday through Friday. Compound effect over time. Use when building personal practice habits, training a team's design eye, or adding structure to professional development.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up and run Direct Preference Optimization (DPO) training on preference datasets using the Tinker API. Use when the user wants to train with preference data, chosen/rejected pairs, or DPO.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up and run the full RLHF pipeline (SFT, reward model training, RL from reward model) using the Tinker API. Use when the user wants to do RLHF, train a reward model, or run the full preference-based RL pipeline.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide for defining RL environments — the Env protocol, EnvGroupBuilder, RLDataset, and custom environment creation. Use when the user asks about RL environments, reward functions, or how to define custom tasks for RL training.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reference for Tinker SDK types — Datum, ModelInput, TensorData, SamplingParams, response types, error types, and helper functions. Use when the user needs to build training data, construct model inputs, understand response objects, or handle errors.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide for hyperparameter selection — learning rate formulas, LoRA rank, batch size, group size, schedules, and model-specific tuning. Use when the user asks about learning rate, batch size, hyperparameter tuning, or how to configure training parameters.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up and run reinforcement learning with verifiable rewards (RLVR/GRPO) for math, code, or custom environments using the Tinker API. Use when the user wants to do RL training, GRPO, reward-based optimization, or train with verifiable rewards.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide for the Tinker CLI — managing training runs, checkpoints, downloading weights, and publishing to HuggingFace. Use when the user asks about CLI commands, listing runs, managing checkpoints from the terminal, or uploading to HF Hub.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Speed up long-sequence transformer training and inference.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fast BPE/WordPiece tokenization and custom vocab training.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapt

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Search the public web and crawl URLs via the Unique AI Platform's `unique-cli web-search` command, with automatic per-turn citation tracking so cited web facts render as clickable external reference chips and `<sup>N</sup>` footnotes on the Unique platform. ALWAYS use this skill when the user asks to search the public web, research a topic online, look up news/articles/regulations, fetch the contents of one or more URLs, or perform any "two-phase" web research (search → review snippets → crawl selected URLs for full content). Routes through the Unique AI Platform's `/web-search-api` endpoints, so the engine (Google, Brave, Tavily, Jina, Firecrawl, …) and crawler are resolved server-side from the current environment — you never need to manage engine API keys yourself. Use this instead of fabricating answers from training data whenever fresh / source-cited information is needed. Do NOT use this skill for the internal knowledge base (`unique-cli search`) or for arbitrary tool execution (`unique-cli mcp`).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when helping users configure LoRA training — select presets, understand parameters, and pick the right settings for their model type. Covers SD1.5, SDXL, SD3, and Flux1 with real-world presets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Busabase-backed project-based PPT production App-in-Skill. Use when the user invokes $kelly-ppt-factory or /kelly-ppt-factory, mentions PPT factory, 规模化 PPT, bulk PPTX, batch decks, reusable PowerPoint style systems, presentation production workflows, pitch decks, sales decks, training decks, report decks, slide-card/storyboard planning, style-consistent deck generation, PPTX QA, or wants to manage many PPTX files through project to deck to slide card to review to generate to render QA.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design and execute a social engineering penetration test including phishing, vishing, smishing, and physical pretexting campaigns to measure human security resilience and identify training gaps.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train Physics-Informed Neural Networks (PINNs) using DeepXDE. Solve forward and inverse PDE problems by embedding physics equations into the neural network loss function. Supports 1D/2D/3D, time-dependent, and parametric PDEs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.