6,067 件 ・ 関連度順
概要と使いどころ
Cube is an open-source semantic layer that sits between a data warehouse and analytics applications and serves governed metrics over REST, GraphQL and SQL APIs. Use when a user asks to define cubes, measures and dimensions, add pre-aggregations, build a metrics API or embedded analytics, set up multi-tenant row-level security, or query Cube from React or the REST 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。
You are an expert in Cloudflare Workers AI, the serverless AI inference platform running on Cloudflare's global network. You help developers run LLMs, embedding models, image generation, speech-to-text, and translation models at the edge with zero cold starts, pay-per-use pricing, and integration with Workers, Pages, and Vectorize — enabling AI features without managing GPU infrastructure.
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。
Measures cyclomatic complexity, cognitive complexity, and function length across codebases to identify maintenance hotspots. Use when someone asks about code complexity, function length analysis, maintainability metrics, or needs to find the most complex parts of their codebase. Trigger words: complexity, cyclomatic, cognitive complexity, long functions, hotspots, maintainability index, code 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。
Clerk is a hosted authentication and user-management service with drop-in UI components, social login, email/password, organizations, RBAC and webhooks. Use when adding sign-in to Next.js, React, or Express apps, protecting routes with clerkMiddleware, setting up multi-tenant organizations and roles, or syncing Clerk users to your own database.
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。
Cerebras Inference is a hosted LLM API that runs open models on Cerebras wafer-scale chips at thousands of tokens per second, through an OpenAI-compatible endpoint. Use when a user wants the lowest-latency chat, code completion or agent loop, asks how to call the Cerebras API or SDK, needs streaming, tool calling, strict JSON schema output or reasoning control, or hits a "model not found" error from a retired Cerebras model ID.
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。
Braintrust is a hosted platform for evaluating and tracing LLM applications: it runs a task over a dataset, scores the outputs, stores each run as an experiment and logs production traces. Use when a user asks to write or run a Braintrust eval, score LLM outputs with autoevals, compare prompt or model versions as experiments, run evals in CI and fail on regressions, trace OpenAI or Anthropic calls with Braintrust, manage evaluation datasets, or use the bt CLI.
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 multiple documents in bulk with parallel execution. Use when a user asks to batch process files, convert many documents at once, run parallel file operations, bulk rename, bulk transform, or process a directory of files concurrently. Covers parallel execution, error handling, and progress tracking.
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。
Arize is an AI observability platform, and Phoenix is its open-source tracing and evaluation tool for LLM applications. Use this skill when the user wants to trace OpenAI or LangChain calls, run a local Phoenix server, score RAG answers for faithfulness, debug slow or wrong LLM responses, or send OpenTelemetry traces to Arize for production monitoring.
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。
Build with Amazon DynamoDB for fast, scalable NoSQL storage. Design tables with partition and sort keys, create GSI and LSI for flexible queries, enable streams for change data capture, and apply single-table design patterns for efficient data modeling.
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。
Auth.js (formerly NextAuth.js) is an open-source authentication library that adds OAuth sign-in, magic links, credentials and WebAuthn to Next.js, SvelteKit, Express and other frameworks. Use when a user asks to add login with Google or GitHub, set up NextAuth v5, protect routes with middleware or proxy, add roles to the session, or connect a database adapter such as Drizzle or Prisma. Notes that the project is in maintenance mode under Better Auth.
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。
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
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。
World-class level design expertise - spatial storytelling, player flow, blockout methodology, and the invisible hand that guides players without them knowingUse when "level design, blockout, graybox, whitebox, player flow, level layout, combat arena, exploration space, map design, multiplayer map, pacing, weenie, landmark, gating, metroidvania, open world design, linear level, environmental storytelling, teaching through design, playtesting, heatmap, metrics, sightlines, level-design, game-development, spatial-design, blockout, graybox, player-flow, pacing, environmental-storytelling, combat-design, multiplayer-maps, open-world, linear-design, metroidvania" mentioned.
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。
LLM application architecture expert for RAG, prompting, agents, and production AI systemsUse when "rag system, prompt engineering, llm application, ai agent, structured output, chain of thought, multi-agent, context window, hallucination, token optimization, llm, rag, prompting, agents, structured-output, anthropic, openai, langchain, ai-architecture" mentioned.
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 in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when "langfuse, llm observability, llm tracing, prompt management, llm evaluation, monitor llm, debug llm, langfuse, observability, tracing, llm-monitoring, evaluation, prompt-management, debugging, analytics" mentioned.
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。
Paul Graham's founder mode. When to delegate vs. dive deep. Maintaining velocity as you scale. Avoiding "professional CEO" traps. The operating mode that built Apple, Tesla, and every YC unicorn. Founder mode isn't micromanagement - it's having the conviction and context to make decisive moves that employees can't. It's staying in the arena when conventional wisdom says to step back. Use when "founder mode, should i delegate, staying close to work, micromanagement, when to step back, professional ceo, manager vs founder, skip level, how involved should i be, letting go of control, scaling as founder, founder burnout, founder, leadership, delegation, management, scaling, operational" mentioned.
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。
Build and maintain digital twins - virtual representations of physical systems that synchronize with real-world counterparts for monitoring, prediction, and optimization. Use when "digital twin, virtual model, real-time synchronization, physical-virtual coupling, predictive maintenance, asset modeling, system replica, live simulation, " mentioned.
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。
The art and science of creating AI-powered digital presenters, avatars, and synthetic spokespersons. This skill covers HeyGen, Synthesia, D-ID, Tavus, and the emerging landscape of photorealistic AI humans that can speak any script in any language. Digital humans aren't replacing human presenters—they're enabling scale that humans can't achieve. A product demo in 50 languages. Personalized video messages for thousands of customers. 24/7 customer support with a friendly face. Training videos that can be updated without reshoots. The practitioners of this skill understand both the power and the responsibility. They know when digital humans enhance experiences and when they feel uncanny. They navigate the ethics of synthetic media thoughtfully. They create AI presenters that feel helpful, not deceptive. Use when "digital human, AI avatar, AI presenter, HeyGen, Synthesia, D-ID, Tavus, synthetic, talking head AI, AI spokesperson, personalized video, video at scale, multilingual video, AI actor, digital-humans, avatar, ai-presenter, synthesia, heygen, d-id, synthetic-media, personalization, multilingual" mentioned.
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。
Infrastructure and practices for reproducible computational research. Covers environment management, data versioning, code documentation, and sharing protocols that enable others to reproduce your results. Use when ", " mentioned.
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 in building and scaling channel partner programs - resellers, agencies, system integrators, and technology partners that extend your reach and revenue. Covers partner program design, enablement, incentive structures, co-selling motions, and marketplace strategies. Knows when channel makes sense and when direct is better. Use when "channel partner, reseller, VAR, agency partner, partner program, co-sell, marketplace, distribution partner, " mentioned.
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。
Systematic code cleanup and refactoring agent that identifies and fixes code quality issues without changing functionality. Focuses on: - Dead code removal - Import organization - Type improvements - Consistent patterns - File organization Use when "User asks to "clean up" code, User mentions "dead code" or "unused", User wants to "organize imports", User asks about "code quality", User wants to "refactor" without changing behavior, Code review identifies cleanup items, After major feature completion, cleanup, refactoring, code-quality, maintenance, organization" mentioned.
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。
Global content at the speed of AI. This skill covers the full spectrum of AI-powered localization: translation, cultural adaptation, voice localization, visual adaptation, and the orchestration required to take content from one language/market to 50. Traditional localization is slow, expensive, and creates bottlenecks. AI-powered localization enables simultaneous global launches, personalized content by market, and continuous localization as content evolves. But localization isn't just translation. It's cultural adaptation. It's knowing that colors mean different things in different cultures, that humor doesn't translate, that some messages must be completely reimagined for new markets. Use when "localize, localization, translate, translation, multi-language, international, global, multilingual, market adaptation, cultural adaptation, other languages, different countries, localization, translation, international, global, multilingual, cultural-adaptation, ai-dubbing" mentioned.
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 in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when "AI wrapper, GPT product, AI tool, wrap AI, AI SaaS, Claude API product, " mentioned.
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。
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementations. The LLM never sees your code - it only sees the schema and description. Use when "agent tool, function calling, tool schema, tool design, mcp server, mcp tool, tool use, build tool for agent, define function, input_schema, tool_use, tool_result, agents, tools, function-calling, mcp, json-schema, anthropic, openai, llm-tools" mentioned.
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。
Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".
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。