8,569 件 ・ 関連度順
概要と使いどころ
Fornece orientação para pós-treinamento de LLM com RL usando slime, um framework Megatron+SGLang. Use ao treinar modelos GLM, implementar fluxos de trabalho personalizados de geração de dados, ou precisar de integração estreita com Megatron-LM para escalabilidade em RL.
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。
Controle saída de LLM com regex e gramáticas, garanta geração válida de JSON/XML/código, aplique formatos estruturados e construa fluxos de trabalho multi-etapas com Guidance - framework de geração restrita da Microsoft Research
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。
Fornece orientação para treinar LLMs com aprendizado por reforço usando verl (Volcano Engine RL). Use ao implementar RLHF, GRPO, PPO ou outros algoritmos de RL para pós-treinamento de LLMs em escala com backends de infraestrutura flexíveis.
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。
Banco de dados de embeddings de código aberto para aplicações de IA. Armazene embeddings e metadados, realize buscas vetoriais e full-text, filtre por metadados. API simples com 4 funções. Escala de notebooks para clusters de produção. Use para busca semântica, aplicações RAG ou recuperação de documentos. Melhor para desenvolvimento local e projetos de código aberto.
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。
Mescle múltiplos modelos ajustados usando mergekit para combinar capacidades sem retreinar. Use ao criar modelos especializados misturando expertise específica de domínio (math + coding + chat), melhorando performance além de modelos únicos, ou experimentando rapidamente variantes de modelos. Cobre SLERP, TIES-Merging, DARE, Task Arithmetic, mesclagem linear e estratégias de deploy em produção.
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。
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
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。
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until it reaches the repository's configured Greptile merge threshold with zero unresolved actionable comments, or until the five-review maximum is reached. Triggers Greptile review, fixes all actionable comments, pushes/re-shelves, re-triggers review only for new head SHAs unless a 5/5 score is already published, and repeats. Use when the user wants to optimize a PR/MR/CL against Greptile's code review standards without creating runaway review loops.
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 the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"
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。
Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.
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。
Load this skill whenever you are planning, executing, or reviewing manual accessibility testing. Manual testing with real assistive technologies is essential — automated tools catch only ~30–40 % of WCAG issues. Absolutely always include keyboard-only testing and at least one screen reader test before marking a feature accessible. Under no circumstances skip forced colors mode testing for UI components.
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。
Load this skill whenever the project contains text, UI components, icons, form controls, data visualisations, or focus indicators — in short, almost every project. Under no circumstances hard-code colour values without verifying contrast ratios. Absolutely always ensure text meets 4.5:1, large text meets 3:1, and non-text UI elements meet 3:1 against adjacent colours. Test in light mode, dark mode, and forced-colors (high contrast) mode.
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。
Load this skill whenever the project contains tooltip components, hover- triggered informational popups, title attribute tooltips, or any content revealed on hover or focus. Under no circumstances create tooltips that are only triggered by hover without keyboard equivalent access. Absolutely always ensure tooltips are dismissible, persistent enough to read, and not the sole source of essential information.
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 the Opquast Digital Quality Framework (245 rules, 14 categories) when building, reviewing, or auditing websites and web applications. Use for web development quality assurance, accessibility compliance, security hardening, privacy implementation, e-commerce best practices, and holistic digital quality checks.
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] Use when activating the Research & Synthesis workflow — research a topic via web sources, then synthesize per --output={synthesis|business-eval|marketing|course} (knowledge report, business evaluation, marketing strategy, or course material).
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。
[Project Management] Use when you need to enforce quality gates, verify compliance with standards, track quality metrics, and generate audit trails.
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。
[Research] Use when starting a web research task — discover, gather, and triage candidate sources on a topic to feed deeper investigation.
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] Use when activating the E2E testing workflow to generate, update, or maintain Playwright/E2E tests. Pick mode with --source={changes|recording|update-ui}.
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。
[Testing] Use when you need to drive an integration-test suite to fully green — each round runs /integration-test-verify (whole system by default, or the target named in the prompt), and on ANY failure combines /debug-investigate + /integration-test-review (report-only) to adjudicate the fault (test wrong · test not optimal · source wrong), then /fix to resolve it at the owning layer, then /changes-review on that round's fix diff, then re-runs a FRESH full verify — looping until the whole suite passes its 2-consecutive-green-runs gate with zero failures.
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。
[Code Intelligence] Use when you need to build, update, or sync the code review knowledge graph. Flag: --scope={full|update|sync} (default auto-detect); --scope=full forces a full rebuild, --scope=update re-parses uncommitted working-tree changes, --scope=sync syncs committed git changes then updates the working tree.
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。
[Research] Use when deeply researching top sources from web-research.
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 planning the migration of a legacy system or monolith — analyzes the source codebase (current repo, or a repo URL cloned to a temp dir) and produces an evidence-based Strangler Fig migration plan with per-domain SPECs. Default target is .NET (Blazor WebAssembly, .NET MAUI, ASP.NET Core); other stacks allowed by user decision. Do NOT use to implement code or when approved SPECs already cover the migration.
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。
Identifies missing information required to complete qualification, segmentation, or outreach preparation. Use when the user provides records and a goal and wants prioritized research gaps with sources.
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。
Turns an ICP or research goal into a plan for finding and scraping suitable directories. Use when the user has a target audience but is unsure where to find them, and wants source categories, queries, and an extraction 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。