「sel」の検索結果

Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency, high-risk controls, general-purpose AI obligations, governance, and implementation milestones. Use when an organization needs to triage an AI use case, vendor, model, product, or portfolio for Regulation (EU) 2024/1689; prepare an AI inventory, gap register, implementation roadmap, or counsel briefing; assess provider, deployer, importer, distributor, product-manufacturer, authorised-representative, or GPAI-provider responsibilities; or re-check readiness after regulatory or product changes.

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。

Generate SQL queries from natural-language requirements using SELECT, JOIN, GROUP BY, window functions, CTEs, and subqueries. Use when the user needs a new query from a business question or schema; use query-optimization when an existing query or execution plan is slow.

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 machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.

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 reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.

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。

Optimize a complete candidate context package by deduplicating, filtering, ordering, and allocating its token budget. Use when retrieved or assembled material is noisy or exceeds the useful context budget; use context-ranking for scoring chunks and context-compression for shrinking selected content.

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。

Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it.

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 and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.

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 a user provides one baseline image and requests game animation frames, sprite sequences, attack/walk/idle/hit/death/casting motion, transparent PNG frames, a spritesheet, keyframe prompts, or consistent whole-character pose animation.

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 Machine Learning Engineer. Use when a task calls for Machine Learning Engineer judgment. Reasons from decision-policy framing, Google's Rules of ML, point-in-time data, and prefill/decode inference physics through GBDT/PyTorch baselines, vLLM/SGLang/KServe serving with FP8/AWQ quantization, hybrid-retrieval RAG, RAGAS and human-validated LLM judges, OpenTelemetry GenAI tracing, and post-Omnibus EU AI Act obligations while treating train-serve skew, temporal leakage, prompt injection, LLM nondeterminism, and degenerate feedback loops 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 Mathematical Physicist. Use when a task calls for Mathematical Physicist judgment. Reasons from Hilbert-space domains, Wightman/OS and Haag–Kastler axioms, constructive QFT, Gibbs measures, and spectral/scattering theory; uses Reed–Simon, Glimm–Jaffe, MathSciNet/math-ph, while treating wrong self-adjoint extensions, invalid Wick rotation, limit-order swaps, and lattice-as-continuum claims 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 Microbial Ecologist. Use when a task calls for Microbial Ecologist judgment. Reasons from Vellend assembly (selection, dispersal, drift, diversification), compositional stats (ANCOM-BC2, MaAsLin2, Aitchison), and SILVA/GTDB/EMP workflows; treats kitome contamination, GCN bias, pseudoreplication, SparCC-as-interaction, and PICRUSt2-as-measured-function 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 Manufacturing Engineer. Use when a task calls for Manufacturing Engineer judgment. Reasons from process physics, capability, and cost through Shercliff-Lovatt process selection, ASME Y14.5 GD&T, CAM simulation, and AIAG APQP/PPAP with MSA-gated SPC capability, treating high %GRR masquerading as variation, false Cpk on unstable or short runs, datum-scheme mismatch, and uncontrolled ECN tweaks 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 Microbiologist. Use when a task calls for Microbiologist judgment. Reasons from culturability limits, CFU/MPN enumeration, selective media, DADA2/QIIME2 16S ASVs (SILVA/GTDB), and shotgun metagenomics (Kraken2, MetaPhlAn, HUMAnN); treats plate-count anomaly, compositional stats pitfalls, kit contamination, and index hopping 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 Gravitational Physicist. Use when a task calls for Gravitational Physicist judgment. Reasons from calibrated strain, colored non-stationary noise PSDs, matched-filter SNR, and Bayesian posteriors through PyCBC/GstLAL/cWB searches, Bilby/LALInference PE with NRSur/SEOBNR/IMRPhenom waveforms, and FAR/p_astro significance while treating glitch contamination, waveform-approximant mismatch, mass-spin and distance-inclination degeneracies, and unmodeled selection effects 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 Geomagnetist. Use when a task calls for Geomagnetist judgment. Reasons from spherical-harmonic main-field theory and remanence physics through IGRF-14/WMM2025 vs CHAOS-8 SV, INTERMAGNET baseline adoption (IBFV2.00), Swarm quiet-time modeling, stepwise AF/thermal demagnetization with PCA/Fisher, GEOMAGIA50/MagIC archaeomagnetic SVCs, and GFZ Kp/ap indices while treating geomagnetic jerks, IGRF epoch mismatch, VRM/CRM overprints, and Day-diagram mixed-carrier traps 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 Herpetologist. Use when a task calls for Herpetologist judgment. Reasons from detectability-limited sampling and ectotherm phenology through VES, pitfall/drift-fence and cover-board arrays, NAAMP call surveys, Program MARK CJS, unmarked/occuTTD occupancy, and Bd/Bsal MW113 qPCR biosecurity; uses AmphibiaWeb, Reptile Database, SSAR 9th ed./CNAH names, Amphibian Disease Portal, GBIF/CoordinateCleaner, and ARRIVE 2.0 while treating weather bias, pitfall selectivity, and pathogen cross-contamination 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 Green Chemist. Use when a task calls for Green Chemist judgment. Reasons from Anastas–Warner 12 principles, Trost atom economy, and PMI/MMI/E-factor mass metrics; selects solvents via CHEM21/GSK/ACS GCIPR guides, integrates catalysis and LCA (ISO 14040), and aligns REACH/CSS with ACS GC&E benchmarking.

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 Fisheries Scientist. Use when a task calls for Fisheries Scientist judgment. Reasons from recruitment, growth, and natural and fishing mortality through state-space assessment models (SS3, SAM, JABBA), CPUE/GLM standardization, and reference points like F_MSY and B_lim under ICES and Magnuson-Stevens frameworks, while treating hyperstability, retrospective bias (Mohn's rho), unaccounted discard mortality, and misspecified M or selectivity 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 Fluid Dynamicist. Use when a task calls for Fluid Dynamicist judgment. Reasons from Navier–Stokes and dimensionless scaling through RANS/LES/DNS selection, mesh/y+ strategy, OpenFOAM/Fluent workflows, and MMS + ASME V&V 20 / PIV 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。

Think and work like an expert Emergency Medicine Researcher. Use when a task calls for Emergency Medicine Researcher judgment. ED trial design expert for pragmatic and cluster RCTs, time-zero and immortal-time bias in acute cohorts, NIHSS/SOFA/qSOFA and ESI/CTAS triage, NEDS/NHAMCS registries, and CONSORT/SPIRIT reporting with Hawthorne and selection-bias 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 Fluid Mechanics Engineer. Use when a task calls for Fluid Mechanics Engineer judgment. Reasons from Navier–Stokes reductions through Darcy–Weisbach/Crane TP-410 pipe networks, pump system curves, NPSH/affinity laws, HI turbomachinery selection, and ASME V&V 20 CFD validation when simulation supports design.

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 Evolutionary Biologist. Use when a task calls for Evolutionary Biologist judgment. Reasons from coalescent demography, MSC gene-tree discordance, and selection–drift nulls; runs IQ-TREE/BEAST/ASTRAL/ANGSD workflows while treating LBA, rogue taxa, batch effects, and uncorrected genome scans 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 Galactic Astronomer. Use when a task calls for Galactic Astronomer judgment. Reasons from distance ladders, dust extinction, and survey selection functions through Gaia DR3 cross-matches, isochrone and Bayesian SFH fitting (PARSEC/MIST, Starfish), and orbit integration in named potentials (McMillan17, MWPotential2015) via galpy, Agama, and Gala, while treating parallax-S/N and RUWE failures, unresolved binaries and fiber collisions, dust-or-crowding overdensities, and spiral-arm-mimicking-streams 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 Computational Social Scientist. Use when a task calls for Computational Social Scientist judgment. Reasons from social mechanisms, measurement validity, and sampling frames through DAGs, fixed-effects and IV/DiD/RDD designs, ERGM/SAOM network models, and human-audited text classifiers while treating unobserved homophily, network interference and SUTVA violations, platform-driven selection, bot contamination, and digital-skew unrepresentativeness 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。