「train」の検索結果

Think and work like an expert Geodynamics & Tectonics Scientist. Use when a task calls for Geodynamics & Tectonics Scientist judgment. Reasons from plate kinematics, lithospheric rheology, and interseismic-versus-coseismic strain partitioning through GAMIT/GLOBK and MintPy geodesy, Okada/viscoelastic slip inversion, OxCal paleoseismic chronologies, ASPECT mantle modeling, and OpenQuake/USGS NSHM hazard while treating InSAR atmospheric delay, monument instability, unmodeled postseismic afterslip, and incompatible-timescale rate stacking as first-class failure modes.

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。

Think and work like an expert Energy Systems Engineer. Use when a task calls for Energy Systems Engineer judgment. Reasons from exergy, load duration curves, capacity factor, and grid boundary constraints through pinch analysis, hourly dispatch models (PLEXOS, HOMER Pro, SAM, PVsyst), spark-spread CHP screening, and IPMVP M&V while treating nameplate-vs-utilization confusion, average-vs-marginal grid emissions, unrealistic arbitrage spreads, and demand-charge ratchet resets as first-class failure modes.

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。

Think and work like an expert Edge / Embedded AI Engineer. Use when a task calls for Edge / Embedded AI Engineer judgment. Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates—treating train–serve preprocessing skew, float thresholds on quantized outputs, and NPU operator fallback as first-class failure modes.

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。

Think and work like an expert Finite Element Analyst. Use when a task calls for Finite Element Analyst judgment. Reasons from discretization error, element technology, and constraint physics; runs mesh convergence and Richardson studies, Nastran/Abaqus/ANSYS workflows, RBE2/RBE3 and contact discipline, and ASME V&V 10 verification-before-validation reporting on governing QoIs.

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。

Think and work like an expert Flavor & Fragrance Chemist. Use when a task calls for Flavor & Fragrance Chemist judgment. Reasons from odor activity values, threshold perception, matrix release, and degradation kinetics through GC-MS with retention indices, GC-O/AEDA, chiral GC authentication, ISO 8586 trained sensory panels, and IFRA/FEMA regulatory limits while treating aldehyde oxidation, citral cyclization, top-note fade, and allergen exceedance as first-class failure modes.

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。

Think and work like an expert Energy Storage / Battery Scientist. Use when a task calls for Energy Storage / Battery Scientist judgment. Reasons from interfacial thermodynamics, ion transport, SEI/CEI dynamics, and cell engineering constraints (N/P and E/S ratio, mass loading) through galvanostatic cycling, dQ/dV, GITT and EIS/DRT, operando XRD, and PyBaMM/Newman models, while treating Li plating, lithium-inventory loss, transition-metal crossover, and coin-cell artifacts as first-class failure modes.

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。

Think and work like an expert Data Scientist. Use when a task calls for Data Scientist judgment. Reasons from CRISP-DM business estimands, leakage-safe sklearn Pipelines and nested CV, SQL/warehouse semantic metrics, A/B power and SRM/AA guardrails, causal DAG covariate discipline, and Model Cards/Datasheets while treating train-test leakage, Simpson's paradox, peeking, and PSI>0.25 drift as first-class failure modes.

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。

Think and work like an expert Deep Learning Scientist. Use when a task calls for Deep Learning Scientist judgment. Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU-Pro/MMLU-CF with lm-eval decontamination and Pineau/NeurIPS reproducibility checklists.

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。

Think and work like an expert Computational Linguist. Use when a task calls for Computational Linguist judgment. Reasons from UD/PTB formalisms, validate.py/eval.py (LAS/MLAS/ELAS), and evalb .prm settings through Stanza/UDPipe pipelines, PropBank/FrameNet/AMR/UMR layers, IAA (κ, Krippendorff α), CONDA contamination checks, and ARR reproducibility while treating tokenizer mismatch, oracle inflation, train–test leakage, and guideline drift as first-class failure modes.

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。

Think and work like an expert Comparative Medicine Researcher. Use when a task calls for Comparative Medicine Researcher judgment. Reasons from species biology, translational validity, and the 3Rs through model-validity frameworks, IACUC protocols, ARRIVE 2.0 reporting, and FELASA/AALAS health surveillance while treating substrain drift, subclinical colony infection (murine norovirus, pinworm, Mycoplasma), analgesia-pathway confounds, and unstated husbandry variables as first-class failure modes.

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。

Think and work like an expert Chronobiologist. Use when a task calls for Chronobiologist judgment. Reasons from TTFL molecular clocks, SCN–peripheral coupling, and zeitgeber entrainment (PRC); analyzes actigraphy, DLMO, and PER2::LUC with ClockLab/LumiCycle, MetaCycle/eJTK/LimoRhyde, and CircaDB/CGDB/ChronobioticsDB while separating masking from endogenous τ under constant routine/FD.

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。

Think and work like an expert Bacteriologist. Use when a task calls for Bacteriologist judgment. Reasons from bacterial growth physiology, selective culture, Gram stain, MALDI-TOF and 16S/WGS identification, EUCAST/CLSI AST, BSL containment, contamination and VBNC, using BacDive and BV-BRC for strain metadata and pathogen genomics.

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。

Think and work like an expert Astrobiologist. Use when a task calls for Astrobiologist judgment. Reasons from habitability, redox disequilibrium, and Bayesian biosignature frameworks through Mars (Perseverance, Viking perchlorate lessons), Europa Clipper ocean worlds, agnostic signatures and the Ladder of Life Detection, while treating abiotic mimics, preservation, and LUCA phylogenomics as constraints—not templates—for extraterrestrial life.

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。

Think and work like an expert Agroecologist. Use when a task calls for Agroecologist judgment. Reasons from socio-ecological farm systems, functional diversity, soil-biology-mediated fertility, and yield-service trade-offs through mother-baby and mixed-model trials, N/P/C mass balances, PLFA/amplicon and pollinator surveys, and NDVI/FRAGSTATS landscape analysis, while treating edge-effect and plot-size artifacts, weather-year confounding, surface-only soil carbon, and ignored labor/tenure adoption constraints as first-class failure modes.

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。

Think and work like an expert AI Researcher. Use when a task calls for AI Researcher judgment. Reasons from data generating processes, inductive biases, and compute-data-algorithm trade-offs through train/val/test discipline, seed sweeps, ablation ladders, and standards like NeurIPS reproducibility checklists, model cards, and lm-eval-harness, while treating data leakage (Kapoor & Narayanan taxonomy), benchmark contamination, spurious correlations, and reward-model overoptimization as first-class failure modes.

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。

Patient-flow market sizing for med products — prevalence → diagnosed → interested → affordable → covered → treated → persistent, priced as price × duration per cohort, with capacity constraints, named historical analog anchoring, and always bull/base/bear named-driver grids. Use to size a therapy area or product market before any valuation or share 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。

Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles). Handles creating new context documents, loading existing ones, and enriching them with new decisions. Use when starting a new feature, resuming work, making technical decisions, resolving questions, or when context needs to persist across sessions. Use this skill whenever the user mentions 'load context', 'update context', 'context doc', 'decisions', 'continue where we left off', 'what did we decide', or 'capture this decision'.

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。

Enforce architectural rules when generating or modifying code, and validate proposed designs before approval (design mode). Defaults to clean architecture; supports any architecture style via the architecture-refiner. Validates layer responsibilities, dependency direction, and structural constraints using the loaded architecture rules. Use when generating code, reviewing architecture, creating new files, or when the user mentions 'architecture', 'layers', 'structure', 'dependency rules', 'hexagonal architecture', 'ports and adapters', 'modular monolith', or 'onion architecture'. Also use when reviewing generated code for structural compliance.

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。

Experiment executor and monitor for academic research. 2-agent system covering code experiments (ML training, statistical analysis, ETL, simulation) and human studies (surveys, field studies, interviews). 4 modes: run (execute + monitor code), manage (track human studies), validate (statistical interpretation + reproducibility verification), plan (Socratic experiment design). Use when a researcher wants to run or monitor a research experiment, manage or resume a human-subject study, check the statistics or reproducibility of research results, or design an experiment or study, in English or Chinese (e.g., 跑實驗、管理研究、驗證結果、規劃實驗).

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。

Select, integrate, and operate multi-model video-generation gateways — hosted inference aggregators such as fal.ai, Replicate, and WaveSpeed that expose many third-party video (and video-adjacent audio) models behind one account, one API surface, and one bill. Use when deciding whether to route video generation through a gateway versus a direct model-provider API; when comparing gateways on catalog, async/queue job design, webhooks, pricing, schema discovery, and version pinning; and when operating gateway workloads in production — spend controls, retries, cross-gateway failover, content- safety differences, data retention, and commercial-rights passthrough of the underlying model. Not for direct model-provider APIs, local/self-hosted inference, model training/fine-tuning, or image-only gateway use.

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。

Local and self-hosted text-to-speech with Kokoro, the ~82M-parameter open-weight (Apache 2.0) model by hexgrad. Use when synthesizing speech offline, on-device, in the browser, or on your own server without per-character API cost — for high-volume narration, audiobooks, privacy-constrained pipelines, and prototyping. Covers running Kokoro via the Python `kokoro` package, ONNX / kokoro-js in the browser, and the OpenAI-compatible Kokoro-FastAPI wrapper; picking voices and language codes; blending voices; chunking long text; controlling pronunciation via misaki/espeak-ng; and judging when Kokoro is the right tool versus when its lack of voice cloning, narrow emotional range, and weaker non-English quality mean you should reach for a hosted or larger model instead. Not for voice cloning, expressive/emotional character performance, or high-fidelity multilingual work — say so and route elsewhere.

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。

Produce text-to-speech with Alibaba/Qwen Qwen3-TTS through DashScope/Model Studio or open-weight Qwen3-TTS checkpoints. Use when an agent must choose Qwen3-TTS models, voices, realtime versus non-realtime synthesis, voice cloning, voice design, instruction/prosody controls, multilingual or dialect speech, audio artifact handling, regional routing, pricing/privacy/licensing constraints, or production QA for narration, characters, assistants, audiobooks, ads, localization, or voice-enabled media.

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。

Produce video with Moonvalley's Marey model family (Marey Realism v1.5) — a filmmaker-oriented, 1080p/24fps generative video model marketed as trained exclusively on licensed data. Use this skill when a task asks for Marey or Moonvalley specifically, when a brief demands brand-safe / legally reviewed AI video for commercial or studio work, or when the request needs Marey's director-style controls (camera trajectory, motion transfer, pose transfer, keyframing, reference conditioning). It covers what "commercially safe" really means versus the actual terms of service, access routes (Moonvalley web / Voyager, the fal API, ComfyUI), pricing, capability limits, prompt and reference strategy, where Marey fits production versus where other models win, iteration, and quality review. Do not use it for audio generation, for photoreal talking-head dialogue, or as a generic "best video model" default.

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。

Provider-independent title design and kinetic typography direction for video, animation, ads, explainers, social hooks, brand films, lyric/text videos, title cards, main titles, lower thirds, captions-as-design, and other motion-led text. Use when an agent must plan, prompt, implement, hand off, iterate, or QA typography hierarchy, readability, timing, reveal/hold/exit, motion semantics, line breaks, safe areas, localization, brand constraints, accessibility, flashing/motion safety, or production specs for animated text.

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。