「lab」の検索結果

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。

Otimiza inferência de LLM com NVIDIA TensorRT para máxima vazão e latência mínima. Use para implantação em produção em GPUs NVIDIA (A100/H100), quando você precisa de inferência 10-100x mais rápida que PyTorch, ou para servir modelos com quantização (FP8/INT4), batching em voo e escalabilidade multi-GPU.

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。

Framework PyTorch de alto nível com classe Trainer, treinamento distribuído automático (DDP/FSDP/DeepSpeed), sistema de callbacks e boilerplate mínimo. Escala de laptop para supercomputador com o mesmo código. Use quando quiser loops de treinamento limpos com boas práticas integradas.

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。

Especialista em CrewAI - o principal framework multi-agente baseado em papéis utilizado por 60% das empresas da Fortune 500. Abrange design de agentes com papéis e objetivos, definição de tarefas, orquestração de crew, tipos de processo (sequencial, hierárquico, paralelo), sistemas de memória e flows para workflows complexos. Essencial para construir equipes colaborativas de agentes IA. Use quando: crewai, equipe multi-agente, papéis de agentes, crew de agentes, agentes baseados em papéis.

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。

Processamento escalável de dados para workloads de ML. Execução em streaming em CPU/GPU, suporta Parquet/CSV/JSON/imagens. Integra-se com Ray Train, PyTorch, TensorFlow. Escala de uma única máquina para centenas de nós. Use para inferência em lote, pré-processamento de dados, carregamento de dados multi-modal ou pipelines distribuídos de ETL.

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。

Orquestração de treinamento distribuído em clusters. Escala PyTorch/TensorFlow/HuggingFace do laptop para milhares de nós. Ajuste de hiperparâmetros integrado com Ray Tune, tolerância a falhas, escalabilidade elástica. Use ao treinar modelos massivos em múltiplas máquinas ou executar varreduras distribuídas de hiperparâmetros.

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。

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

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 Canvas-owned clean-room skill to guide collaborative writing for documentation, proposals, technical specs, decision records, PRDs, RFCs, operating guides, and structured memos. Trigger when the user wants help drafting, organizing, refining, reviewing, or testing a document before sharing 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。

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。

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 SVG graphics — inline SVGs, external SVG files, SVG icons, SVG illustrations, or SVG-based data visualizations. Under no circumstances use SVG without proper accessible titles, descriptions, and ARIA roles where required. Absolutely always add <title> and <desc> to meaningful SVGs and set role="img" with aria-labelledby pointing to those elements. Also apply this skill whenever the project accepts untrusted or user-uploaded SVG content, which requires sanitization before rendering.

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 writing, editing, or reviewing any web content, copy, headings, labels, error messages, or instructions. Under no circumstances write inaccessible content — every piece of text must be clear, structured, and usable by people with cognitive, visual, and language differences. Absolutely always apply plain language, logical heading hierarchy, and meaningful link text.

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 when building any web feature, reviewing architecture decisions, or evaluating JavaScript dependencies. Under no circumstances build features that break completely when JavaScript is unavailable or fails. Absolutely always start with semantic HTML, layer CSS enhancements, and add JavaScript as the final, optional layer. Prioritize resilience and universal access over cutting-edge features.

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 static or interactive maps, embedded map widgets (Google Maps, Leaflet, Mapbox, OpenStreetMap), or any geographic visualizations. Under no circumstances embed a map without a text-based alternative conveying the same information. Absolutely always ensure map controls are keyboard-accessible and that all meaningful map content is available without the visual map.

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 likely duplicate profiles or companies using available record evidence. Use when the user provides a list and wants duplicate groups, match confidence, and merge recommendations. Describe records as likely duplicates unless there is an exact deterministic match.

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。

Converts inconsistent job titles into standardized role, department, and seniority labels. Use when the user provides records with free-text titles and wants consistent role family, department, and seniority fields.

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。

Classifies professional profiles into buyer, influencer, user, decision-maker, founder, recruiter, or other personas. Use when the user provides profiles and wants persona labels with evidence and confidence. Must not infer sensitive personal attributes.

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 after PROJECT_GUIDE.md exists, when the user asks if a project is worth their time, should they build vs buy, or invokes project-worth-my-time. Follow-up to explain-new-project—weighs project context (files, git history, chat) to recommend whether to invest in a repo, cherry-pick a feature, park the idea, pass, or use an existing polished product instead. Optionally enriched by a personal-memory MCP (e.g. Pieces) when one is available.

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 designing, reviewing, or implementing typography in Apple-platform apps — SwiftUI text styles, hierarchy, readable sizes, monospaced data, custom fonts, labels, captions, and accessibility.

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。

INTERNAL/HELPER skill — do NOT invoke directly from a user query. This is the shared formatter/poster used by answer-issue-questions and breakdown-issues. It formats a scope GitHub Issue body (label cc-triage-scope, used before code analysis), runs the pre-posting checklist, and executes `gh issue create`. Invoke this skill ONLY from one of the parent skills via the Skill tool, after the parent has finalized the task breakdown. If a user asks to 'create a scope issue' or similar, route them to the appropriate parent skill (/breakdown-issues for fresh breakdowns, /answer-issue-questions for derived sub-tasks) rather than invoking this one directly.

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。

Triage a GitHub issue that already has the cc-issue-created label and is assumed to be ready to start. First inspect the comment history to decide whether human confirmation is needed (cc-need-human-check, highest priority); otherwise decide whether the issue should be closed as not needed, unanswered confirmation items remain (cc-answer-issue-questions), the description is stale relative to settled comment-history content and must be refreshed before execution (cc-update-issue), or it can move to execution (cc-exec-issue). Dependency checks are out of scope.

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 an aggregated Epic PR from a `cc-epic-<Issue number>` branch to the default branch. Takes the Epic Issue number as argument, assumes sub-PRs have already been merged into the epic branch, and automatically generates the PR title and description from the commit log against the base branch (including sub-PR / sub-Issue references). The PR is posted via `gh pr create` with no label and `Closes #<Epic 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。

Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then publish to a dedicated assets branch when the task includes attaching the GIF to a pull request. Use when asked to make, record, or generate a GIF that demonstrates a browser workflow, and for every pull request that changes product-user-visible GUI behavior, which MUST include a GIF recorded from the pull request's real server and model flow.

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。