「training」の検索結果

Drafts a standalone API Acceptable Use Policy (AUP) for incorporation by reference into a master API license or terms-of-service agreement. Produces a publication-ready template with prohibited-use matrix, developer security checklist, graduated enforcement framework, AI/ML training restrictions, and versioning playbook. Trigger when a user needs to draft or update an API AUP, separate behavioral rules from core API terms, define prohibited API uses, add enforcement or change-management mechanics, or mentions acceptable use policy, developer security requirements, or API enforcement.

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。

Drafts an Adverse Event Reporting Policy compliant with 21 CFR 312.32 (IND safety reporting), 21 CFR 314.80 (postmarketing), and ICH E2A, with multi-jurisdictional overlays (EMA, PMDA, Health Canada). Covers seriousness/causality frameworks, expedited reporting timelines, roles, documentation standards, training mandates, and QA mechanisms. Use when drafting or updating an adverse event reporting policy, pharmacovigilance policy, AE/SAE reporting SOP, or safety reporting framework for a pharmaceutical company, CRO, biotech, or clinical research institution.

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。

Retrieve current library, framework, and API docs via Context7, Context Hub, and web fallback. Use whenever docs are needed for a library, SDK, or internal spec instead of stale 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。

Retrieve up-to-date library, framework, and project documentation using scripts + MCP tools (Context7, Context Hub) with intelligent fallback. Use this skill whenever the user or agent needs documentation for any library, framework, API, SDK, or internal project spec. Triggers on "docs for [X]", "how does [library] work", "find documentation", "API reference for", "look up [feature] in [library]", "latest docs", "what's the API for", "find our [internal spec]", or any request that requires current, accurate documentation rather than relying on training data. Always prefer this skill over raw WebSearch for documentation retrieval — it returns structured, context-efficient 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。

Annotate speech/TTS datasets with per-clip quality metrics (MOS, SNR, STOI, pitch, bandwidth, speaking rate, WER/CER, gender/emotion), multi-ASR consensus transcription and speaker labeling using the audiogear pipeline; then filter clips by quality and build listenable HTML QA reports. Use when asked to compute audio dataset metrics, build extended_metadata.csv, transcribe unlabeled audio, select clean TTS training data, or QA a speech 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。

Up-to-date Zig programming language patterns for version 0.17.0-dev (0.16.0 stable APIs plus the 0.17 deltas). Use when writing, reviewing, or debugging Zig code, working with build.zig and build.zig.zon files, or using comptime metaprogramming. Critical for avoiding outdated patterns from training data - especially std.net→std.Io.net (requires Io instance), std.time timestamps removed (use clock_gettime), std.Thread.Mutex/Condition/sleep removed (use pthreads), std.crypto.random removed, build system APIs (root_module, Compile methods→Module methods), I/O APIs (buffered writer pattern), container initialization (.empty/.init), allocator selection (DebugAllocator), ArrayList now unmanaged by default, @typeInfo lowercase fields (.@"struct" not .Struct), and removed language features (async/await, usingnamespace). Also covers 0.17.0-dev deltas: b.args→run_cmd.addPassthruArgs(), std.gpu→std.spirv, @bitCast logical-bit (endian-agnostic) semantics, build configurer/maker split, and the zig-pkg/ package directory. Also covers quality tooling Zig does not ship: coverage with kcov (and why in-file tests wreck the denominator), detecting unused private functions (neither the compiler nor zlint's unused-decls finds them), duplicate detection with jscpd, zlint (NOT the same-named X.509 linter in Homebrew), and the built-in fuzzer whose testOne now takes *std.testing.Smith rather than []const u8.

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 deployment-focused distillation systems that balance model size, accuracy, calibration, and cascade escalation under real resource limits. Best for teacher-student compression, threshold design, and failure-aware deployment. Activate on "model compression", "teacher- student", "distillation score", "cascade model", "edge deployment", or "model calibration". NOT for generic deep-learning overviews, prompt optimization, or training work without a concrete distillation objective.

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。

Choose what kind of knowledge to transfer between teacher and student models: response, feature, or relational, and decide among offline, online, self, or cross-modal distillation schemes. Best for distillation strategy selection, capacity-gap diagnosis, and transfer planning. Activate on "knowledge distillation", "teacher-student", "soft labels", "feature distillation", "online distillation", or "cross-modal transfer". NOT for generic compression checklists or unrelated training work.

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 image generation pipelines with Stable Diffusion, FLUX, ControlNet, LoRA, and ComfyUI workflows. Activate on: image generation pipeline, ComfyUI workflow, ControlNet, LoRA training, diffusion model. NOT for: video generation (ai-video-production-master), image classification (computer-vision-pipeline).

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 rapport-based elicitation to resistant or semi-cooperative humans and agents. Use when coercive prompting or brittle handoffs damage cooperation. NOT for routine cooperative tasks, pure technical debugging, or already reliable exchanges.

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 data engineer for ETL/ELT pipelines, streaming, data warehousing. Activate on: data pipeline, ETL, ELT, data warehouse, Spark, Kafka, Airflow, dbt, data modeling, star schema, streaming data, batch processing, data quality. NOT for: API design (use api-architect), ML training (use ML skills), dashboards (use design skills).

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 methodology for eliciting, representing, and operationalizing expert cognitive skills—pattern recognition, situation assessment, mental simulation—from practitioners without requiring research training. Bridges academic rigor and practical usability.

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。

Predict RBP binding from RNA sequence using deep learning models (RBPNet sequence-to-signal, RNAProt RNN, GraphProt2 GCN with structure, DeepCLIP, DeepRiPe multi-modal CNN) for variant-effect prediction, in silico binding-site discovery, model interpretation, and transfer learning from CLIP and RBNS datasets. Use when computational prediction of RBP binding from sequence is needed, evaluating variant effects on binding without further wet-lab experiments, comparing model performance, or training a custom model on ENCODE eCLIP 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。

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.

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。

Recommends real-time CGM with confirmatory POC-BG for insulin dosing adjustments in insulin-treated hospitalized adults at high risk of hypoglycemia when resources and training are available. Triggers include: "Should we use CGM for insulin adjustments?" or "Is CGM appropriate for this patient?

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。

Workflow Phase 3 — Research and Solution Exploration. Surfaces 2–4 candidate solution approaches with concrete tradeoffs, grounded in current library docs (fetched through the provider named in `.claude/docs-provider.json`) — never in training-data recall. Output lives at `docs/research/<slug>.md`. Candidate ranking and the memo execute in main context; doc/source gathering MAY be delegated to read-only advisory subagents (seed.md §4.2-A).

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。

Talk to your Garmin data — ask questions about your activities, training load, VO2 Max, heart rate zones.

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。

Retrieve current documentation, API references, and code examples for any library, framework, SDK, CLI tool, or cloud service — including well-known ones like React, Next.js, Prisma, Django, or Spring Boot. Use for API syntax, configuration options, version migrations, setup instructions, and library-specific debugging, even when you already think you know the answer: training data on API details and signatures is frequently outdated. 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。

Adaption AI SDK for synthetic data augmentation and dataset adaptation. Use when building data pipelines with the Adaption Python SDK, uploading datasets (local files, Hugging Face, Kaggle), running augmentation/adaptation jobs, configuring brand controls (hallucination mitigation, safety categories, length), recipe specifications (reasoning traces, deduplication, preference pairs, prompt rephrase), evaluating dataset quality, downloading results, or any workflow involving `pip install adaption`, `from adaption import Adaption`, Adaptive Data, or the adaptionlabs.ai API. Also trigger when the user mentions synthetic data generation for fine-tuning, dataset augmentation pipelines, DPO preference pair generation, or grounding-based hallucination reduction on 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。

Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance validation.

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。

Fornece orientação para treinamento RL de nível empresarial usando miles, um fork pronto para produção do slime. Use ao treinar grandes modelos MoE com FP8/INT4, necessitando alinhamento treino-inferência ou exigindo RL especulativo para máxima taxa de transferência.

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。

Fornece orientação para treinamento RL agentico nativo do PyTorch usando torchforge, biblioteca da Meta que separa infraestrutura de algoritmos. Use quando você quer abstrações limpas de RL, fácil experimentação de algoritmos, ou treinamento escalável com Monarch e TorchTitan.

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。

Ajuste fino de LLMs usando reinforcement learning com TRL - SFT para ajuste de instruções, DPO para alinhamento de preferências, PPO/GRPO para otimização de recompensas e treinamento de modelo de recompensas. Use quando precisar de RLHF, alinhar modelo com preferências ou treinar a partir de feedback humano. Funciona com HuggingFace Transformers.

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。

Quantização pós-treinamento em 4-bits para LLMs com perda mínima de precisão. Use para implantar modelos grandes (70B, 405B) em GPUs de consumo, quando você precisa de redução de memória 4× com <2% de degradação de perplexidade, ou para inferência mais rápida (aceleração de 3-4×) vs FP16. Integra com transformers e PEFT para fine-tuning QLoRA.

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。