「oci」の検索結果

Adresse les commentaires de revue sur les PR (humain + bots). Mode auto-détecté selon le type d'issue. Usage: /review [<issue#>|<PR#>]

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。

Epic/report dashboard for Codex. Equivalent to the repository's Claude skill: render the orchestration state from bash scripts and summarize it cleanly. Usage: /report [<epic_N> ...]

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。

Conception pipeline for Codex. Equivalent to the repository's Claude skill: detect epic/task/bug mode, then delegate to the existing repo agents and workflows. Usage: /analyse [<issue#>] [<description>]

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。

Worktree recreation for Codex. Equivalent to the repository's Claude skill: recreate a local worktree for a PR so it can be tested locally. Usage: /open <PR>

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。

Documentation regeneration for Codex. Equivalent to the repository's Claude skill: regenerate user-facing docs from current code state. Usage: /doc or /doc <issue#>

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。

Execution pipeline for Codex. Detect epic/task/bug mode and implement with Codex models only. Usage: /implement <issue#>

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。

Creates LinkedIn posts, thought leadership content, and editorial calendars for SME marketing. Covers 7 post types (Awareness, Personal Story, Education, Conversion, How We Do It, Building In Public, Lead Magnet) with complete graphic prompts, first comments, and CTAs. Use when user asks to write social media posts, plan content calendars, create LinkedIn content, or develop thought leadership pieces.

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。

Creates ad copy, Google Ads RSA headlines, A/B test plans, and campaign analysis for SME performance marketing. Handles paid search, paid social, email campaigns, and SEO content. Use when user asks about ads, campaigns, Google Ads, paid media, SEO, conversion optimization, or marketing performance metrics.

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。

Polish an existing report, deck, or HTML page to the ReportRoom design bar — visual hierarchy, typography, charts, dark mode, OG/social link preview. Use when the user says "make it beautiful", "improve the design", "it looks plain", "fix the layout" about something already written or published. Not for creating content from scratch (use report-publisher or deck-publisher).

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。

Desenvolvimento moderno de JavaScript/TypeScript com runtime Bun. Cobre gerenciamento de pacotes, bundling, testes e migração do Node.js. Use quando trabalhar com Bun, otimizar velocidade de desenvolvimento JS/TS ou migrar do Node.js para Bun.

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。

Gerar memes usando a API memegen.link. Use quando usuários solicitarem memes, quiserem adicionar humor ao conteúdo ou precisarem de recursos visuais para redes sociais. Suporta 100+ templates populares com texto e estilo personalizados.

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。

Planeja, cria e otimiza campanhas de marketing incluindo estratégia de conteúdo, redes sociais, email e análise de dados. Ajuda a desenvolver estratégias de go-to-market, mensagens de campanha e medição de desempenho.

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。

Kit de ferramentas de product ownership ágil para Senior Product Owner, incluindo geração de histórias de usuário compatíveis com INVEST, planejamento de sprints, gerenciamento de backlog e rastreamento de velocidade. Use para escrita de histórias, planejamento de sprints, comunicação com stakeholders e cerimônias ágeis.

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。

Garanta estrutura válida de JSON/XML/código durante a geração, use modelos Pydantic para outputs type-safe, suporte modelos locais (Transformers, vLLM) e maximize velocidade de inferência com Outlines - biblioteca de geração estruturada da dottxt.ai

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。

Agentes de voz representam a fronteira da interação com IA - humanos falando naturalmente com sistemas de IA. O desafio não é apenas reconhecimento e síntese de fala, mas alcançar fluxo de conversa natural com latência inferior a 800ms enquanto se lidam com interrupções, ruído de fundo e nuances emocionais. Esta habilidade cobre duas arquiteturas: fala-para-fala (OpenAI Realtime API, menor latência, mais natural) e pipeline (STT→LLM→TTS, mais controle, mais fácil de depurar). Insight-chave: latência é a restrição. Hu

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。

Otimiza atenção em transformers com Flash Attention para ganho de 2-4x em velocidade e redução de 10-20x em memória. Use ao treinar/executar transformers com sequências longas (>512 tokens), ao encontrar problemas de memória GPU com atenção, ou quando precisa de inferência mais rápida. Suporta SDPA nativo do PyTorch, biblioteca flash-attn, H100 FP8 e sliding window attention.

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。

Acelere a inferência de LLMs usando especulative decoding, múltiplas cabeças Medusa e técnicas de lookahead decoding. Use ao otimizar velocidade de inferência (aceleração de 1,5-3,6×), reduzir latência em aplicações em tempo real ou fazer deploy de modelos com recursos computacionais limitados. Cobre modelos draft, atenção em árvore, iteração de Jacobi, geração paralela de tokens 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。

Load this skill whenever the project contains HTML data tables (<table> elements). Under no circumstances use tables for layout purposes. Absolutely always include <th> elements with appropriate scope attributes, a <caption> or aria-labelledby, and ensure complex tables have headers associated with data cells. Apply these rules to every data table without exception.

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 forms, inputs, selects, checkboxes, radio buttons, text areas, or any validation flow. Under no circumstances create a form without visible labels, error identification, and keyboard accessibility. Absolutely always associate every input with a label and provide clear, accessible error messages.

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。

[Content] Use when you need to create high-converting copy for marketing materials, social media, landing pages, email campaigns, and product descriptions.

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。

Route ordinary public-web information tasks to the correct Tavily CLI operation. Use when the task concerns publicly accessible webpages and needs web discovery, clean extraction, URL mapping, same-site crawling, or public-web-only research, but the exact Tavily operation is not yet clear or several operations must be sequenced. Prefer the specific leaf skill when intent is clear: tavily-search for discovery without a URL, tavily-extract for known URLs, tavily-map for URL/site-structure discovery, tavily-crawl for content from many pages on one site, tavily-research for cited multi-source synthesis, and tavily-dynamic-search for programmatic filtering with context isolation. Do not use for named social/community/media/career/code platforms, login or cookie-dependent content, platform-native discussions, or cross-platform collection; use Agent Reach there. Do not use for local files, Git operations, deployments, or ordinary code editing.

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。

NLM PubTator3 实体级关系挖掘原子 skill — 在 PubMed 文献里检索"疾病-药物-基因-化学品-突变-物种-细胞系"的标注与关系三元组。当用户问"BTK 与肺曲霉病的关联文献"、"BTK 抑制剂(MeSH D000077180)在哪些研究被讨论"、"标注这些 PMID 中提到的所有疾病/药物/基因实体"、"ibrutinib 的 MeSH/DrugBank ID"、"voriconazole 与 CYP2C19 药物-基因相互作用"、"BRAF V600E 突变 / rs113488022 检索"、"实体共现 / co-mention / 关系挖掘 / 实体规范化 / NER / annotation / entity normalization / disease-gene association / drug-gene interaction / chemical-disease relation" 时使用。无需 API key,跨平台稳定。**实体级 + 关系级**定位 — 不做综合文献检索(走 pubmed-eutils / europepmc-search)、不做全文段落抽取(走 bioc-fulltext-fetch)、不做证据等级排序(走 medical-evidence-grading)。

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 comprehensive synthesis with explicit citations from multiple ordinary public-web sources via the Tavily CLI. Use for detailed reports, comparisons, market or literature research, and questions whose answer requires multi-source web evidence rather than a quick lookup. Do not use for simple discovery (tavily-search), one known URL (tavily-extract), one-site URL discovery or bulk extraction (tavily-map/crawl), or research centered on named social, community, career, code, media, authenticated, or cross-platform sources (Agent Reach). Takes 30-120 seconds.

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 this skill when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and personal-IP content. The skill diagnoses “AI味”, preserves the user's meaning, adapts to optional style samples, replaces translation-like phrasing with natural Chinese expression, and outputs a polished version plus concise revision notes.

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。