Claude ajan altyapısı — /ai-upgrade (repo kataloğu, araç yönetimi) + /ai-metodoloji (çalışma kalitesi denetimi). Stack bağımsız, her projede çalışır.
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval…
Navigating the regulatory landscape and ethical frameworks for responsible AI development and deployment.
Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or…
Implements federated learning architecture patterns for GDPR compliance. Covers secure aggregation protocols, differential privacy integration, communication protocols, and…
Design AI-friendly architecture with explicit patterns, layered documentation, and semantic boundaries.
Design AI-friendly architecture with explicit patterns, layered documentation, and semantic boundaries.
AI gateways for LLM serving — provider routing, fallback, retries, rate limiting, secrets, observability, guardrails.
System architecture for Salesforce AI governance: MLOps pipeline design, AI Audit Trail architecture, Einstein Trust Layer security design, Policy-as-Code engine, and regulatory…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface ass — 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 at…
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.
Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps
Operational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods (LightGBM), deep learning (Transformers, RNNs),…
Intelligent AI model router that automatically switches between two configured models (local for simple tasks, cloud for complex ones).
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
Multi-model AI collaboration via orchestrator MCP. Use when seeking second opinions, debugging complex issues, building consensus on architectural decisions, conducting code…
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…
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed…
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 this when: design an AI system, RAG vs fine-tuning, my agent keeps looping, architect a multi-agent system, which LLM should I use, context window keeps overflowing, add…
AI SDK v5 tool creation patterns for this project. Factory functions, Zod schemas, budget tracking, rate limiting, caching, timeout handling.
Reference for all AI tools available in DBX Studio's AI chat system. Use when adding, modifying, or debugging AI tool definitions, tool execution, or provider integrations.
Design explainability interfaces that help users understand AI decisions, build calibrated trust, and verify AI outputs.
Choose multi-agent architectures using environment-first analysis, coordination pressure, commitment tuning, and knowledge levels.
Turn an OpenClaw agent into an autonomous AI Chief that runs a business. Provides trust-based autonomy, structured knowledge management (bank/), worker delegation patterns, and…
Break down PM story into organized tasks in a single file following LAYERED ARCHITECTURE order: Types → Database → Repository → Service → API → Tests.
Request structured code review to catch correctness, security, performance, and readability issues. Reviews should happen early and often.
Break down PM story into organized tasks in a single file following UI DEVELOPMENT order: Setup → Static UI → Dynamic Logic → Interactions → Testing.
Define clear, testable acceptance criteria using Given/When/Then (Gherkin) format that can be directly used for testing.
Aidbox FHIR platform by Health Samurai. Use when user works with Aidbox — FHIR REST API, CRUD operations, search, transactions, bundles, access policies, subscriptions, custom…
AI-DLC units-generation skill. Decomposes the system into manageable units of work — logical groupings of components and stories for development purposes.
Manage local AIMA deployments and device state through the built-in AIMA MCP server.
Knowledge about AIND data infrastructure including MongoDB/DocumentDB access patterns, S3 asset storage, collection schemas, and query patterns.
Async HTTP server and client for Python with WebSocket support, middleware, streaming, and server-sent events
Airbyte is the leading open-source data integration platform providing 600+ pre-built connectors for ELT pipelines from APIs, databases, and files to data warehouses, lakes, and…
Guidelines for writing AI-friendly code. Detects semantic duplicates, context fragmentation, naming inconsistencies.
Python DAG workflow orchestration using Apache Airflow for data pipelines, ETL processes, and scheduled task automation
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment.
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment.
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment.
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment.
Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters. Use when planning airgapped deployments, editing…
Debug and implement Airtable synchronization logic including duplicate prevention, cache management, change detection, and RLS considerations; use when debugging sync failures,…
Parser AIS PHP-Python bridge usando pyais. Use quando trabalhar com decodificação de mensagens NMEA/AIS, comunicação entre PHP e Python, ou modificar o parser.
Sincroniza el estado de las specs y planes de Modo Cambio con tickets de Azure DevOps, Jira o GitHub Issues.
Consult prior AI war-stories before answering coding, deploy, debugging, refactoring, code-review, or framework-decision tasks.
Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repositories, middleware, or workin — from…
Display workspace status dashboard showing installed frameworks, deployments, artifact counts, and health indicators
draw.io Desktop CLI로 AWS VPC 기초 다이어그램을 `.drawio` XML로 만들고 PNG/SVG/PDF로 export한다. draw server나 MCP server를 사용하지 않고, macOS의 draw.io Desktop CLI와 AWS icon pack(mxgraph.aws4)을 사용한다.
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code).