Use when Agentforce run costs are climbing, you need to forecast scale, or you want to reduce tokens per conversation without hurting quality.
Score 70/100
Design Agentforce conversations that span multiple turns without losing context: session variable scoping, conversation memory, clarifying-question patterns, topic-to-topic…
Score 70/100
Use when defining or refining the tone, voice, and behavioral personality of an Agentforce agent: system instruction encoding, brand voice alignment, adaptive response formats,…
Score 70/100
Design Agentforce testing: topic coverage, action unit tests, deterministic golden sets, adversarial prompts, and regression harness.
Score 70/100
Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.
Score 70/100
Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.
Score 70/100
Transition from a hands-on "bricklayer" to a high-level "architect" by managing a fleet of autonomous AI agents.
Score 70/100
Architecture guidelines for Jarvy CLI - codebase structure, tool implementation patterns, registry system, platform-specific code organization, and module conventions.
Score 70/100
Testing guidelines for Jarvy CLI - unit testing patterns, integration tests with assert_cmd, test environment variables, platform-specific testing, and CI coverage strategies.
Score 70/100
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems.
Score 70/100
AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACT principles.
Score 70/100
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Score 70/100
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Score 70/100
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Score 70/100
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or…
Score 70/100
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool…
Score 70/100
Gives Claude Code operators a live dashboard for multi-agent sessions, tool calls, file activity, and nested task progress so debugging starts from what the agents are actually…
Score 70/100
Build stateful AI agents using the Cloudflare Agents SDK. Load when creating agents with persistent state, scheduling, RPC, MCP servers, email handling, or streaming chat.
Score 70/100
Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design
Score 70/100
Comprehensive L&D framework for upskilling DevOps/IaC/Automation teams to become AI Agent Engineers. Covers LLM literacy, RAG, agent frameworks, multi-agent systems, and LLMOps.
Score 70/100
Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the…
Score 70/100
Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops.
Score 70/100
Deep code scan for AI security issues — prompt injection, PII in prompts, hardcoded keys, unguarded agents.
Score 70/100
WHEN: Deep AI-powered code analysis, multi-model code review, security scanning with Codex and Gemini WHAT: Comprehensive code review using external AI models with severity-based…
Score 70/100
Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations.
Score 70/100
Comprehensive AI/ML development guide for LangChain, LangGraph, and ML model integration in FastAPI. Use when building LLM applications, agents, RAG systems, sentiment analysis,…
Score 70/100
Technical decision criteria, anti-pattern detection, debugging techniques, and quality check workflow.
Score 70/100
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
Score 70/100
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations.
Score 70/100
Expert in building comprehensive AI systems, integrating LLMs, RAG architectures, and autonomous agents into production applications.
Score 70/100
Practical guide for building production ML systems based on Chip Huyen's AI Engineering book. Use when users ask about model evaluation, deployment strategies, monitoring, data…
Score 70/100
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval…
Score 70/100
Navigating the regulatory landscape and ethical frameworks for responsible AI development and deployment.
Score 70/100
Design AI-friendly architecture with explicit patterns, layered documentation, and semantic boundaries.
Score 70/100
Design AI-friendly architecture with explicit patterns, layered documentation, and semantic boundaries.
Score 70/100
System architecture for Salesforce AI governance: MLOps pipeline design, AI Audit Trail architecture, Einstein Trust Layer security design, Policy-as-Code engine, and regulatory…
Score 70/100
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 -…
Score 70/100
Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference…
Score 70/100
Operational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling, quantization/compression, parallelism, and reliable serving at…
Score 70/100
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
Score 70/100
Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps
Score 70/100
Operational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods (LightGBM), deep learning (Transformers, RNNs),…
Score 70/100
Multi-model AI collaboration via orchestrator MCP. Use when seeking second opinions, debugging complex issues, building consensus on architectural decisions, conducting code…
Score 70/100
Operational prompt engineering for production LLM apps: structured outputs (JSON/schema), deterministic extractors, RAG grounding/citations, tool/agent workflows, prompt safety…
Score 70/100
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed…
Score 70/100
Use when designing or auditing a Salesforce data architecture to support AI features — Einstein, Agentforce, Data Cloud, or custom ML models.
Score 70/100
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.
Score 70/100
Retrieval architecture for AI applications — choosing and combining vector RAG, PageIndex (vectorless PDF tree-search), and precision embedding models.
Score 70/100
AI SDK v5 tool creation patterns for this project. Factory functions, Zod schemas, budget tracking, rate limiting, caching, timeout handling.
Score 70/100
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.
Score 70/100
Break down PM story into organized tasks in a single file following LAYERED ARCHITECTURE order: Types → Database → Repository → Service → API → Tests.
Score 70/100
Request structured code review to catch correctness, security, performance, and readability issues. Reviews should happen early and often.
Score 70/100
Break down PM story into organized tasks in a single file following UI DEVELOPMENT order: Setup → Static UI → Dynamic Logic → Interactions → Testing.
Score 70/100
Define clear, testable acceptance criteria using Given/When/Then (Gherkin) format that can be directly used for testing.
Score 70/100
Async HTTP server and client for Python with WebSocket support, middleware, streaming, and server-sent events
Score 70/100
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…
Score 70/100
Python DAG workflow orchestration using Apache Airflow for data pipelines, ETL processes, and scheduled task automation
Score 70/100
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment.
Score 70/100
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment.
Score 70/100
Debug and implement Airtable synchronization logic including duplicate prevention, cache management, change detection, and RLS considerations; use when debugging sync failures,…
Score 70/100