「training」の検索結果

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

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 and deploy neural networks in distributed E2B sandboxes with Flow Nexus

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 turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics, process flows, timelines, benchmarks, waterfall charts, or data-backed visual specs for any audience.

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。

Builds end-to-end predictive modeling pipelines on tabular datasets—data exploration, preprocessing, baseline modeling, and mandatory optimization—producing valid saved predictions in the required output format. Use for any supervised machine learning or data modeling task, including classification and regression on tabular data, Kaggle-style competitions or submission-file challenges, training a model to predict a target from features, or requests to fit/tune/evaluate models with scikit-learn, XGBoost, Random Forest, Logistic Regression, and similar non-deep-learning methods. Runs fully automated end-to-end without asking the user for intermediate 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。

Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.

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。

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

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。

Use when writing or changing PyTorch code — model, Dataset/DataLoader, training and evaluation loops, determinism, mixed precision, torch.compile, checkpoints with safetensors, Hugging Face models, ONNX export, and tests that run on CPU

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 building or changing features, preprocessing, encoders, resampling or train/validation/test splits — keep every fitted transform inside a Pipeline fitted on training folds only, and build time and group features without seeing the future or the same entity twice

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。

Tmux skill for running background tasks. Use this skill when: 1. Before any tasks that can potentially run for more than 2 minutes (e.g.: package install, many tests, model training) 2. Before any tasks that are expected to run indefinitely in background (e.g.: web servers, port forwarding) 3. Bash tool reports `timeout after 120000ms` 4. User request to run tasks in background

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。

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.

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。

Chooses DPO, GRPO/RLVR, reward models, and over-optimization controls. Use when adapting a pretrained or SFT model with preference or verifiable reward signals.

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。

Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.

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。

Configure the project's game engine and version. Pins the engine in AGENTS.md, detects knowledge gaps, and populates engine reference docs via webfetch when the version is beyond the LLM's training 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。

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

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。

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

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。

Search the live web and read full pages with You.com. Use whenever a task needs information newer than training data or from outside the codebase: current library docs and API references, changelogs and release notes, breaking changes, error messages, package versions, pricing, news, or any claim to verify with cited sources. Works keyless through the free MCP profile when no You.com credentials are configured.

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。

Detect and search for similar utility/invention patents based on product information. Trigger when users mention utility patent detection, patent infringement risk, patent similarity search, patent screening, invention patent search, patent risk assessment, TRO (Temporary Restraining Order) risk analysis, utility patent, invention patent detection, patent infringement risk, patent search, TRO risk, Ruiguan. Even if the user does not explicitly say "utility patent", trigger this skill whenever their need involves checking whether a product may infringe existing utility/invention patents before selling in a target market.

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。

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.

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 a hyperparameter tuning strategy for a model — search space, method, and budget. Use when asked to "tune hyperparameters", "define a search space", or "set a tuning budget".

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。

Deliberate practice as a rigorous training method distinct from ordinary repetition. Covers Ericsson's four conditions (specific goals, full attention, immediate feedback, repetition at the edge of current ability), the role of mental representations, coach-directed vs. self-directed practice, the plateau escape pattern, and practical drill design for procedural skills. Use when designing practice sets, diagnosing why practice is no longer producing gains, or distinguishing productive effort from busywork.

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。

Sound systems of human language -- phoneme inventories, the International Phonetic Alphabet, articulatory and acoustic phonetics, phonological rules, suprasegmental features (stress, tone, intonation), and ear training for non-native sound perception. Covers place and manner of articulation, voicing contrasts, vowel space, minimal pair analysis, allophonic variation, phonotactic constraints, connected speech phenomena (assimilation, elision, liaison), and prosody across language families. Use when analyzing pronunciation, teaching sound systems, performing phonemic transcription, or diagnosing intelligibility problems in any language.

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。

Yoga practice with an emphasis on alignment, props, and staged progression as the Iyengar lineage teaches it, alongside enough context about the broader lineage landscape (Krishnamacharya's three students, modern Hatha, Ashtanga vinyasa, restorative, Yin, and chair yoga) that a routing agent can place a user correctly before giving instruction. Covers asana families, alignment heuristics, prop use, sequencing, and the non-negotiable injury-prevention rules. Use for any query about yoga postures, home practice design, teacher-training-level questions, or whether a given pose is safe for a given body.

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。

Implement affective valence as directional derivative of interoceptive energy landscapes for AI alignment. Use when building alignment-aware RL agents, validating GF(3) conservation in reward signals, training Langevin-based policies, or analyzing fold-change detection signals in POMDP environments.

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。