「model architecture」の検索結果

Build production-ready AI agents with Microsoft Foundry and Agent Framework. Use when creating AI agents, selecting LLM models, implementing agent orchestration, adding tracing/observability, or evaluating agent quality. Covers agent architecture, model selection, multi-agent workflows, and production deployment.

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。

Get external agent review and feedback. Routes Anthropic models through Claude Agent SDK (uses local subscription) and other models through OpenRouter API. Use for code review, architecture feedback, or any external consultation.

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 for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.

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。

Convert a semantic core into crawlable SEO and LLM-friendly information architecture. Use this skill when the user asks for URL structure, page taxonomy, canonical rules, hreflang groups, page roles, pillar/topic/news/article/blog/project separation, multilingual route strategy, or a durable content model such as one short brief plus one longform article. It prevents duplicate public content bodies and hands link-graph work to internal-link-graph-architect.

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。

Analyzes Claude Project context budget under the automatic-RAG-by-window model: knowledge files vs. threshold-exempt overhead (Skills, MCPs, CI, Memory). Two modes: Quick Diagnostic and Full Budget Audit. Use when user says "check my context budget," "how much context am I using," "is my project too big," "optimize my token usage," "tier my files," "optimize for RAG," "improve retrieval quality," "should I keep compressing," "am I over-compressing," "should I accept RAG mode." Also trigger on context pressure symptoms: "Claude forgets my instructions," "responses getting generic," "content not found in my knowledge files." Also use when a project audit scores Knowledge Architecture ≤ 3. Do NOT use for content placement decisions (use rootnode-memory-optimization if available), full project audits (use rootnode-project-audit if available), or behavioral tuning (use rootnode-behavioral-tuning if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.

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 a generative diffusion model (DDPM or score-based) with noise scheduling, U-Net architecture, training loop, and sampling procedures including DDIM acceleration. Use when building a generative model for image, audio, or molecular synthesis; implementing DDPM from a research paper; adding a custom noise schedule or conditioning mechanism; replacing a GAN-based generator with a diffusion alternative; or prototyping before scaling with production frameworks like diffusers.

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。

MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance labels.

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。

Create, read, edit, and open draw.io (.drawio) files. Supports architecture diagrams, ER diagrams, flowcharts, domain model diagrams, and more. Use when requests include "create a diagram", "make a flowchart", "draw an architecture diagram", "create an ER diagram", "open a .drawio file", "what's in this diagram?", etc. Do NOT use for Mermaid or PlantUML generation.

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。

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

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。

Unity UI/UX pattern design-to-code translation. Screen flow architecture, View/ViewModel separation, HUD architecture, feedback & juice systems, dynamic list/grid views, transition & animation contracts. UI Toolkit only. DESIGN INTENT format: INTENT/WRONG/RIGHT/SCAFFOLD/DESIGN HOOK. Based on Unity 6.3 LTS.

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 creating editable technical diagrams with draw.io / diagrams.net sources, including architecture diagrams, ERD, UML, sequence diagrams, flowcharts, ML model diagrams, official shape lookup, brand symbols, Graphviz auto-layout, codebase structure maps, .drawio validation, or draw.io CLI export fallback. Do not use for ordinary raster image generation, freehand sketches, interactive canvas/Three.js scenes, or decorative SVG animation. Chinese triggers include draw.io, diagrams.net, editable architecture diagrams, .drawio, ER diagrams, UML, sequence diagrams, auto layout, shape retrieval, code structure diagrams.

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 with the Falcon open models — UAE's TII models with strong multilingual and efficient architectures.

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 Mermaid architecture diagrams from your codebase. Produces C4 context and container diagrams, sequence diagrams for key flows, ER diagrams from database schemas, and module dependency graphs. Use when you need architecture diagrams, system diagrams, database ERD, sequence diagrams, dependency visualization, or C4 model diagrams.

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。

Declarative setup of Compliant Data Sharing (CDS) in Financial Services Cloud: enabling CDS per-object in IndustriesSettings, configuring OWDs, creating CDS permissions, adding the Financial Deal Participants related list, and defining Participant Roles. Trigger keywords: ethical walls, compliant data sharing setup, FSC sharing model, isolate banking teams, participant roles. NOT for participant record DML from Apex — use apex/fsc-compliant-sharing-api. NOT for the FSC sharing design decision — use architect/fsc-architecture-patterns.

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。

Router for the 101 SfSkills `data` skill packages. Data model, data movement and data quality: migrations, bulk loads, query optimisation, deduplicating at volume, archival. Ordinary-volume duplicate cleanup and prevention use salesforce-admin; come here for hundreds-of-thousands+ dedup or third-party tools. LDV architecture uses salesforce-architect. Use when the request mentions data model, data migration, data load, Data Loader, Bulk API, external id, deduplication at volume, archival, SOSL, cross-object search, sandbox seed data, SandboxPostCopy, native Data Seeding. Finds and opens the exact skill package to read; it does not contain the guidance itself.

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 auditing the conversational copy layer of a Salesforce bot or Agentforce agent: utterance authoring strategy, fallback message copy, escalation-criteria phrasing, and persona-consistent dialog scripting across channels. NOT for designing the bot dialog structure, intent model, or handoff architecture — use architect/einstein-bot-architecture. NOT for encoding agent tone in Agentforce system instructions — use agentforce/agentforce-persona-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。

Understand what SKMTC is, how its engine works, and the architectural invariants — for agents building or extending infrastructure *around* SKMTC rather than authoring generators or running the CLI. Covers the three-phase pipeline, the host/Worker boundary, cross-generator coordination, the manifest, the attribution / gen-maps (provenance) subsystem, the package graph, the dependency substrate, and the design decisions that make SKMTC behave unlike a typical codegen tool. Use this skill when the user asks "what is SKMTC", "how does the SKMTC engine work", "explain the SKMTC architecture", or is building platform infrastructure around SKMTC — a hosted generate API, a schema or generator registry, tracing or provenance tooling, a web app or SaaS that wraps the engine, or platform-level CI integration. This skill is the system mental model. It does NOT cover authoring generators (→ skmtc-generator), running CLI commands (→ skmtc-cli), or diagnosing broken runs (→ skmtc-debug).

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 preparing hardest high-leverage work for a stronger or scarce model, building a ranked execution queue, asking for fable prep, frontier prep, round-collapse, wave queue, or model-upgrade readiness across code, design, copy, marketing, or architecture 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。

Generate 3D models using each::sense AI. Create 3D assets from text or images for games, products, architecture, characters, vehicles, and more with PBR textures.

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 an ML model in the QuantConnect ML-Training-Pipeline with thermal-safe GPU usage and rigorous validation. Arguments: <architecture|script> [--dry-run] [--seeds 0,1,7,42,99] [--folds 5] [--bg]

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。

Jetpack Compose navigation expert with type-safe routes, Hilt DI, and MVVM/MVI architecture. Activate on: Jetpack Compose navigation, Compose type-safe routes, Hilt dependency injection, MVVM Android, MVI pattern, Compose state management, NavHost, ViewModel. NOT for: XML layouts (use frontend-architect), iOS SwiftUI (use swiftui-data-flow-expert), React Native (use react-native-architect).

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。

BDI (Beliefs-Desires-Intentions) agency framework for designing autonomous agents with mental state architectures

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。

LLM and cloud cost awareness — model tiering, token budgets, right-sizing, and when a cheaper model suffices. Trigger before finalising any architecture that calls LLMs, before scaling a workload, or when a cost estimate is needed.

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 treinamento distribuído de LLM nativo do PyTorch usando torchtitan com paralelismo 4D (FSDP2, TP, PP, CP). Use para fazer pré-treinamento de Llama 3.1, DeepSeek V3 ou modelos customizados em escala de 8 a 512+ GPUs com Float8, torch.compile e checkpoint distribuído.

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。