「rl」の検索結果

arXiv論文URLからスライドを作成する。(1)論文取得・分析(内部処理)→(2)JSONで保存しダイジェスト提示→(3)確認後スライド生成。分析結果はJSONファイルに保存し、ユーザーにはダイジェストのみ見せる。

arXiv論文URLからスライドを作成する。論文を取得・分析し、スライド構成JSONを保存、ユーザー確認後にgenerate_pptxツールでスライドを生成する。

改修後の動作確認を、AIが自分で環境を立てて最後まで進めるための検証スキル。CLI（curl / php evo / DB）を優先し、画面操作でしか判定できないときだけ Playwright（既定はヘッドレス）に切り替える。Docker の検証環境の起動、インストール、テスト用ユーザー作成、mailpit でのメール確認、main との比較、後片付けまでを扱う。「動作確認」「自走で確認」「実環境で確かめる」「ブラウザで確認」「再現を確認」「Playwright」と依頼されたとき、または修正のあとに実機での裏付けが必要なときに使う。

RL 强化学习训练与推理（rollout）路径的算子差异性扫描。当用户提供训练启动脚本路径，要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异（尤其是融合算子 vs 单算子不一致）时使用此 skill。典型触发词包括"训推算子扫描"、"训推差异性"、"算子差异报告"、"融合算子对比"、"train vs infer op diff"。注意：本 skill 通过运行完整 RL 训练脚本（集成 profiling）来采集真实运行时算子（非静态源码扫描，非独立分离运行）。当训练、推理使用不同脚本时禁止触发。

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。

为 verl-omni 接入或修复 MSProbe 训推一致性采集，生成打点代码、样本关联日志和诊断启动脚本。 用于 diffusion/omni 的 rollout 与 actor 数据采集、dump 缺失或配对失败；不负责精度根因分析。

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。

When the user wants to audit, review, or diagnose SEO issues, plan site architecture, or implement schema markup. Use when someone says 'SEO audit', 'technical SEO', 'site architecture', 'schema markup', 'internal linking', 'why isn't my site ranking', 'site health check', 'crawl issues', 'fix my SEO', 'my traffic dropped', 'rankings fell', or 'site not ranking'. Also trigger when someone wants to plan URL structure, design navigation, add structured data, or review any website for search performance. Three modes: Full Audit (comprehensive health check), Architecture (URL structure and internal linking), Schema (JSON-LD structured data). Covers crawlability, indexation, Core Web Vitals, and on-page factors.

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。

Call Exa Contents (POST /contents) for LLM-ready extraction from known URLs: text, highlights, summaries, links, image links, subpages, freshness-controlled crawl. Use when the agent already has URLs. Prefer Exa MCP web_fetch_exa when available; otherwise raw HTTP with EXA_API_KEY. NOT for open-ended discovery (use exa-search) or auth-walled X/Twitter (use mktg-x). For full-site crawl of a known domain, firecrawl may be better.

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。

Call Exa Search (POST /search) for semantic web retrieval with ranked results, filters, freshness, highlights/text, structured output, or streaming. Use when the agent needs open-ended web search, competitor discovery, news, people, or research papers and does not already have URLs. Prefer Exa MCP web_search_exa / web_search_advanced_exa when available; otherwise raw HTTP with EXA_API_KEY. NOT for known-URL extraction (use exa-contents or firecrawl) or multi-step list-building (use company-research / lead-generation / Agent API).

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。

Work with the @upstash/workflow TypeScript/JavaScript SDK for durable, long-running workflows in serverless functions, multi-step processes that survive timeouts, retries, and restarts (built on QStash). Use when defining a workflow endpoint with serve(), running steps with context.run, sleeping for minutes to days without holding a function open, calling external APIs with context.call, waiting for an external event or webhook, invoking other workflows, configuring retries, failure callbacks, and a DLQ, controlling concurrency, rate, and parallelism, triggering, cancelling, or inspecting runs with the Workflow client, building AI agents and orchestrators, human-in-the-loop approvals, realtime updates, local development with the QStash dev server, adding middleware, or migrating workflows safely. Also use when the user asks for durable execution, step functions, saga or orchestration patterns, background jobs with checkpoints, or long-running tasks on Vercel, Next.js, Cloudflare Workers, or other serverless platforms.

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。

Work with the @upstash/blob TypeScript/JavaScript SDK for S3-compatible object storage with direct browser uploads, presigned URLs, multipart, and signed reads. Use when storing files or blobs, uploading avatars, images, videos, attachments or user documents, letting a browser upload straight to storage without proxying bytes through a server, generating public or time-limited signed URLs, serving private files, streaming large files with pause and resume, setting cache headers on stored objects, or reaching an S3-compatible bucket from the AWS SDK.

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 to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.

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 Android build files and R8 keep rules to identify redundancies, broad package-wide rules, and rules that subsume library consumer keep rules. Use when developers want to optimize their app's size, remove redundant or overly broad keep rules, or troubleshoot Proguard configurations.

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。

Expert guidance for working with Wear OS Compose Material3. Use this skill when creating, updating or migrating Wear OS projects. This includes the androidx.wear.compose.material3, androidx.wear.compose.foundation and androidx.wear.compose.navigation3 libraries. Also working with core components such as AppScaffold, ScreenScaffold and TransformingLazyColumn. Migration from earlier versions such as Material 2.5 and Horologist.

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 free built-in .NET maintainability analyzers and code metrics configuration to find overly complex methods and coupled code. Use when a repo needs cyclomatic complexity checks, maintainability thresholds, or complexity-driven refactoring gates.

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 NixOS, Nix language, flakes, nixpkgs, configuration.nix, nixos-rebuild, modules, options, overlays, derivations, mkDerivation, callPackage, home-manager, nix-darwin, devenv, packaging, cross-compilation, binary caches, garbage collection, NixOS containers, networking, firewall, systemd services, filesystems, LUKS, Wayland, X11, kernel, profiles, NixOS testing or VM tests, ISO images, Docker images, Raspberry Pi, Terraform, distributed builds, remote machines, pinning nixpkgs, rollback, generations, Nix Pills, or any topic related to configuring, packaging, deploying, or troubleshooting NixOS and the Nix ecosystem.

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 explicitly asks for the Inngest REST API v2, raw HTTP, OpenAPI, API docs, API authentication, or an endpoint that the Inngest CLI does not expose. Covers api-docs.inngest.com, llms.txt, the OpenAPI v2 spec, Bearer authentication with API keys or signing keys, production and local base URLs, raw curl/fetch requests, request-shape discovery, pagination, secret redaction, and when to prefer the `inngest-api-cli` skill instead.

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。

Master coordinator for the founder. Filters noise, owns cross-functional processes, enforces consistency, routes decisions, and positions outputs for impact so the founder can think clearly. Doesn't own any function owns the space between all of them.

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。

Rebuild the Galyarder Knowledge Graph and Obsidian World Map. Essential for structural RAG and multi-platform synchronization.

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。

Optimize cloud and AI costs for modern SaaS stacks (Vercel, Supabase, Neon, Stripe, and AI APIs). Covers token efficiency, serverless database scaling, edge function optimization, and burn rate monitoring. Use when planning infrastructure, investigating high bills, or auditing API usage.

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。

Investigates phishing email incidents from initial user report through header analysis, URL/attachment detonation, impacted user identification, and containment actions using SOC tools like Splunk, Microsoft Defender, and sandbox analysis platforms. Use when a reported phishing email requires full incident investigation to determine scope and impact.

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。

Monitors dark web forums, marketplaces, paste sites, and ransomware leak sites for mentions of organizational assets, leaked credentials, threatened attacks, and threat actor communications to provide early warning intelligence. Use when establishing dark web monitoring coverage, investigating specific data breach claims, or enriching incident investigations with dark web context. Activates for requests involving dark web OSINT, leak site monitoring, credential exposure, Recorded Future dark web, or Tor hidden service intelligence.

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。

Executes comprehensive red team exercises that simulate real-world adversary operations against an organization's people, processes, and technology. The red team operates with stealth as a primary objective, employing the full attack lifecycle from initial reconnaissance through objective completion while testing the organization's detection and response capabilities. This differs from penetration testing by focusing on adversary emulation rather than vulnerability identification. Activates for requests involving red team exercise, adversary simulation, adversary emulation, or full-scope offensive security assessment.

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 agent company packages conforming to the Agent Companies specification (agentcompanies/v1). Use when a user wants to create a new agent company from scratch, build a company around an existing git repo or skills collection, or scaffold a team/department of agents. Triggers on: "create a company", "make me a company", "build a company from this repo", "set up an agent company", "create a team of agents", "hire some agents", or when given a repo URL and asked to turn it into a company. Do NOT use for importing an existing company package (use the CLI import command instead) or for modifying a company that is already running in Galyarder Framework.

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 existing copy needs tightening for clarity, accuracy, tone consistency, or executive readability without changing the underlying message.

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。