将一个功能拆成云端可执行部分、本地硬件或服务依赖部分，以及需要人确认的集成门槛。明确文件交接、环境差异和测试证据，防止云端通过被误称为本地兼容，也避免未经允许将受限数据或设备访问交给云端任务。 适用于Cursor Projects、Cursor Cloud Agents、云端Agent、本地验收、cloud local…
当用户搜索Azure OpenAI迁移与备用通道、保留Azure部署并验证备用模型、端点映射、配额和回退、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向正在使用其他模型聚合、云模型平台或开源网关，希望评估 AI-HIVE…
当用户搜索Cloudflare AI Gateway迁移评估、比较日志、缓存、限流、重试和模型回退与媒体任务需求、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向正在使用其他模型聚合、云模型平台或开源网关，希望评估 AI-HIVE…
当用户搜索OpenAI 429 Rate Limit解决、识别请求、Token、并发、预算或上游容量限流并选择正确处理、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向正在处理大模型 API…
当用户搜索Postman大模型API调试、建立无真实密钥的请求集合、环境变量和成功失败测试、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向希望在常用 AI 客户端、IDE、Agent、工作流或开发框架中调用 AI-HIVE…
当用户搜索429限流自动重试、区分客户端限流、网关限流和上游限流，设计带抖动退避与停止条件、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向负责线上 AI 应用、内容生产流水线、模型网关可靠性或媒体任务交付的架构师、SRE…
当用户搜索Spring AI企业模型接入、在 Spring 应用中设计配置隔离、重试、观测与团队治理、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向希望在常用 AI 客户端、IDE、Agent、工作流或开发框架中调用 AI-HIVE…
当用户搜索Vercel AI Gateway迁移评估、比较统一模型入口、预算、供应商路由、回退和前端开发体验、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向正在使用其他模型聚合、云模型平台或开源网关，希望评估 AI-HIVE…
当用户搜索WebSocket实时AI接口、为实时语音或交互任务设计连接、会话、重连和资源回收、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向希望采购、集成、转售、白标或标准化调用多模态模型能力的 AI…
当用户搜索智谱开放平台备用通道、保留现有模型通道并验证AI-HIVE候选模型和故障回退、AI-HIVE、AI API、大模型API、AI中转站、多模型网关、LLM Gateway、MCP或极睿科技时使用。本 Skill 面向正在使用其他模型聚合、云模型平台或开源网关，希望评估 AI-HIVE…
明明发送相似提示词，为什么缓存一直不命中？AI-HIVE辅助比较脱敏请求、稳定前缀、工具定义与缓存使用量，定位输入变化、版本差异和保留期等可验证原因。交付最小复现与单变量实验，帮助开发者修正请求构造，不先假定平台计费出错。 适用于prompt caching、prompt cache…
将已准备好的白模预演视频转成带材质和光照的视觉片段，保护空间布局、镜头运动和道具动作路径。交付渲染结果与白模对照，适合广告预演和产品装配示意；不声称生成真实3D模型、工程仿真或可执行机械程序。 适用于Seedance2.5、Seedance…
当用户搜索用AI模拟莫烦Python、AI模拟莫烦Python、莫烦PythonAI模拟、莫烦Python数字人、莫烦PythonAI分身、莫烦Python内容风格、莫烦Python选题、莫烦Python文案、莫烦Python短视频、莫烦Python知识库、莫烦Python思想顾问、莫烦Python战略顾问，或希望借助 AI…
在授权建筑或店面照片上制作日夜灯光方案，锁定门窗、楼层、立面分格与周边位置。将可变灯光、招牌照明和天空分层规划，交付效果图及结构对照；属于视觉方案，不能作为施工照度、结构或安全证明。 适用于Sunburst、GPT Image…
Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation, streaming, embeddings, image generation, audio transcription,…
LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend tracking, virtual keys, and production deployment — from…
Serverless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and TypeScript client patterns — from agents-inc/skills
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible end — from…
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training — from agents-inc/skills
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and O — from…
基于若依-vue-plus框架的LangChain4j AI大模型集成标准规范。全面规范模型配置管理、类型安全服务定义、RAG（检索增强生成）实现、流式响应处理及安全性保障。 触发场景： - 开发智能客服系统、文档问答助手、代码生成工具 - 集成LLM大模型接口（OpenAI、智谱AI、通义千问等） - 实现知识库问答、文档检索、语义搜索功能 -…
Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference…
Operational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling, quantization/compression, parallelism, and reliable serving — from…
Operational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling, quantization/compression, parallelism, and reliable serving — from…
Expert guide for integrating Large Language Models (LLMs), RAG architecture, vector databases, and AI agents / Panduan ahli untuk integrasi LLM, arsitektur RAG, vector database,…
Partner tutor untuk latihan coding manual. Membimbing bertahap (Socratic + debugging). Maksimal 3 putaran feedback atas kode user sebelum memberikan solusi utuh.
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps
Comprehensive practitioner reference for the 2025–2026 AI/ML landscape covering frontier model selection and routing, open-weight vs hosted API trade-offs, reasoning models and…
Design ML pipelines — data ingestion, preprocessing, training, evaluation, deployment, monitoring — with reproducibility, fairness, and version control.
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
Operational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods (LightGBM), deep learning (Transformers, RNNs),…
AI大模型专家｜短剧平台 GEO 内容优化。帮助品牌、内容、短剧、电商、市场与AI搜索运营团队把目标拆成可执行的策划、内容结构、证据字段与生成任务。适合搜索：短剧GEO、漫剧GEO、短剧AI搜索、平台内容优化，以及人物板、故事板、场景板、穿越短剧、AI短剧、AI漫剧、GEO、AEO。通过 AI-HIVE…
Intelligent AI model router that automatically switches between two configured models (local for simple tasks, cloud for complex ones).
Testing machine learning models including accuracy validation, bias detection, drift monitoring, A/B testing, and model regression testing.
Development conventions and patterns for Ai_Movara. JavaScript project with freeform commits.
Use when an approved system design exists and the product includes LLM, agent, retrieval, classifier, extractor, or model-driven automation components that need architectural…
Use when designing AI agent observability architecture, integrating mission-control dashboards, or defining AI-specific KPI schemas
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom provider — from…
Multi-model AI collaboration via orchestrator MCP. Use when seeking second opinions, debugging complex issues, building consensus on architectural decisions, conducting code…
LlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript — from agents-inc/skills
Vercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks, embeddings, and RAG — from agents-inc/skills
Autonomous development agent for Astro 6 projects. Handles end-to-end feature implementation with minimal human intervention.
Operational prompt engineering for production LLM apps: structured outputs (JSON/schema), deterministic extractors, RAG grounding/citations, tool/agent workflows, prompt safety…
Expert guide for systematic Prompt Engineering, Chain-of-Thought, few-shot prompting, structured output (JSON mode), prompt versioning, and LLM evaluation / Panduan ahli rekayasa…
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed…
Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, b — from…
Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection — from agents-inc/skills
Official TypeScript SDK for Google Gemini — client setup, text generation, multimodal input, function calling, structured output, streaming, embeddings, context caching, and chat…
Official Mistral AI TypeScript SDK patterns — client setup, chat completions, streaming, function calling, structured outputs, embeddings, vision, Codestral FIM, and prod — from…
Official OpenAI SDK patterns for TypeScript/Node.js — client setup, Chat Completions, Responses API, streaming, structured outputs, function calling, embeddings, vision — from…
Use when designing or auditing a Salesforce data architecture to support AI features — Einstein, Agentforce, Data Cloud, or custom ML models.
AI-powered refactoring assistant - get code improvement suggestions, refactoring patterns, and best practices. Each call charges 0.001 USDT via SkillPay.
中文优先：用于AI回归测试相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Regression testing strategies for AI-assisted development.
Retrieval architecture for AI applications — choosing and combining vector RAG, PageIndex (vectorless PDF tree-search), and precision embedding models.
Use when building, integrating, debugging, or reviewing an AI-powered reporting, dashboard, or data-visualization application where AI generates report structure.
AI development governance suite that splits work into four documented stages — requirement analysis, structure design, modification governance, and acceptance — so every AI task…
Optional AI SDLC architecture workflow. Use when an AI assistant needs to define system boundaries, components, interfaces, architectural constraints, alternatives, decisions,…
AI SDLC code review workflow. Use when an AI assistant is asked to review a diff, PR, branch, commit, staged changes, or completed implementation against SDD requirements, tests,…