3,114 件 ・ 関連度順
概要と使いどころ
Use quando o usuário pergunta como construir com produtos ou APIs da OpenAI e precisa de documentação oficial atualizada com citações (por exemplo: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, capacidades ou limites de modelos); priorize ferramentas MCP de docs da OpenAI e restrinja qualquer fallback de navegação a domínios oficiais da OpenAI.
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。
Escreva papers prontos para publicação em NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use quando estiver elaborando papers a partir de repositórios de pesquisa, estruturando argumentos, verificando citações ou preparando submissões finais. Inclui templates LaTeX, diretrizes de revisores e workflows de verificação de citações.
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。
Skill de pesquisa profunda alimentado por NotebookLM MCP. Conduz pesquisa estruturada em múltiplas fontes (análise de mercado, inteligência competitiva, análise de tendências, pesquisa de prospects) usando Google NotebookLM como mecanismo de pesquisa, depois entrega briefs formatados e artefatos opcionais de estúdio (slides, podcasts de áudio, vídeos, infográficos, relatórios, mapas mentais).
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 tarefas de pesquisa autônoma que planejam, buscam, leem e sintetizam informações em relatórios abrangentes.
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。
Construa agentes de IA que interagem com computadores como humanos fazem - visualizando telas, movimentando cursores, clicando botões e digitando texto. Cobre Computer Use da Anthropic, Operator/CUA da OpenAI e alternativas de código aberto. Foco crítico em sandboxing, segurança e tratamento dos desafios únicos do controle baseado em visão. Use quando: computer use, automação de desktop agent, controle de tela IA, agente baseado em visão, automação de GUI.
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。
Pesquise a documentação da base de código gerada automaticamente para assinaturas de funções, docs de API, definições de classe e comentários de código. Use quando o usuário solicitar "pesquisar docs", "encontrar documentação", "procurar uma função", "verificar a API" ou antes de implementar mudanças para verificar assinaturas e padrões corretos.
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。
Ferramentas são como agentes de IA interagem com o mundo. Uma ferramenta bem projetada é a diferença entre um agente que funciona e um que alucina, falha silenciosamente ou custa 10x mais tokens do que o necessário. Esta skill cobre design de ferramentas desde schema até tratamento de erros. Melhores práticas em JSON Schema, escrita de descrições que realmente ajudam o LLM, validação e o emerging padrão MCP que está se tornando a língua franca para ferramentas de IA. Insight-chave: Descrições de ferramentas são mais importantes que implementação
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。
Avalia LLMs em mais de 60 benchmarks acadêmicos (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use quando benchmarking de qualidade de modelo, comparação de modelos, relatório de resultados acadêmicos ou rastreamento de progresso de treinamento. Padrão da indústria usado por EleutherAI, HuggingFace e laboratórios principais. Suporta HuggingFace, vLLM, APIs.
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 must support speech input or voice control — dictation, "click by voice" grammars, Dragon NaturallySpeaking, Voice Control (iOS/macOS), Voice Access (Android), or any interface where users activate controls by speaking. Under no circumstances let an aria-label override a visible label without keeping the visible text intact and in order. Absolutely always ensure the accessible name contains the visible label, and load alongside keyboard/SKILL.md since speech tools commonly emulate keyboard and pointer input.
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。
[Dev Data] Use when you need to implement or enhance test data seeders that simulate QC happy-path scenarios via application-layer commands. Flag: --mode=review reviews a target seeder (or the current changes / current work-context result) against every universal seed-data rule AND the project-specific seeder conventions — read-only, evidence-backed PASS/FAIL.
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。
Kova/OpenClaw validation: benchmarks, release gates, scenarios, perf reports.
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。
AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
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。
Test authentication and session management controls for bypass and account takeover scenarios.
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。
Appwrite Swift SDK skill. Use when building native iOS, macOS, watchOS, or tvOS apps, or server-side Swift applications with Appwrite. Covers client-side auth (email, OAuth), database queries, file uploads, real-time subscriptions with async/await, and server-side admin via API keys for user management, database administration, storage, and functions.
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。
Validate general MSX system emulation in EMULATORS, including BIOS-facing behavior, Z80/VDP interrupt wiring, standard I/O ports, PPI 8255 ports
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。
QA Engineer role in AID methodology. Use for test strategy, BDD scenarios, bug reporting, acceptance testing, flaky test prevention.
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, editing, debugging, or reviewing dealer language code in btn, dlr, or script files. Provides the complete dealer DSL syntax reference for bridge hand generation constraints.
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。
End-of-session wrap-up. Save what was learned this session to auto-memory, verify the working tree is committed/pushed, and emit a brief resume prompt the user can paste next time. Invoke as /done to close a work session. Wrap-up is auto-memory ONLY — never writes a handoff.md or any handoff file.
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。
Author a complete both-seats coaching lesson for a BBA-NATIVE bidding scenario and produce all served artifacts in one consistent pass: curate the pool → tokenized coaching-curated/<scn>.pbn → gated promote to served coaching/<scn>.pbn → resolve to South=student coaching-non-rotated/<scn>.pbn (bridge-classroom) → update both toc.json files. Invoke as `/coach-lesson <Scenario>` (e.g. `/coach-lesson Fourth_Suit_Forcing`). Use ONLY for conventions BBA bids natively (its bba/<scn>.pbn [Auction] is the answer key — Basics, New_Minor_Forcing, Fourth_Suit_Forcing). For conventions BBA CANNOT bid (Spiral Raises), use the py/spiral_auction.py substitution path instead — not this skill.
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。
Act on the queued items. Works through every pending item on the working todo list (the queue built with /list), actually doing each one, marking it in_progress then completed as you go. Use after stacking items with /list.
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。
Queue an item WITHOUT acting on it. Appends the provided text as a new pending item on the working todo list, then stops. Use /list <text> to stack up tasks or notes one at a time; act on them later with /go. Does not plan or start the 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。
Process the batch of incoming Bridge Classroom feedback. Pull open `classroom-feedback` issues from the PBS repo, cluster them by defect class, verify each against the actual board, and fix at the right altitude — patch a single board, or (when a class recurs) build a gate, sweep the whole corpus, and regenerate/drop collectively. Engine bugs route to the Classroom repo; bridge-judgment calls go to Rick. Nothing leaves the machine without David's OK. Invoke as `/issue` (optionally with an issue number or scenario to restrict the run).
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。
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.
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。