菜单
这个仓库中的 skills
SkillsMP 已收集 paulpas/agent-skill-router 中的 1,338 个 Skill。打开任一 Skill 可查看来源和详情。
paulpas/agent-skill-router已展示 40 / 1,338 个已收集 Skill。
Continuously monitors agent performance in production through token tracking, LLM-as-a-Judge evaluation, A/B testing for improvements, drift detection, anomaly detection, and trajectory analysis with structured feedback loops.
原文语言：英语
Implements agent resilience patterns including retry logic with exponential backoff, fallback handler chains, state rollback, graceful degradation, and error escalation to maintain reliability under failure conditions.
原文语言：英语
Implements proactive agent exploration patterns for discovering unknown opportunities, generating hypotheses, designing experiments, and sharing findings through autonomous research loops beyond predefined optimization targets.
原文语言：英语
Implements goal-oriented agent architectures with objective definition, LLM-based success criteria evaluation, iterative progress tracking, and max-iteration bounded refinement loops for proactive autonomous systems.
原文语言：英语
Protects agent systems from harmful outputs through behavioral constraints, input validation and sanitization, jailbreaking defenses, structured output enforcement, the Principle of Least Privilege, and fault-tolerant state management for safe autonomous…
原文语言：英语
Implements GUI agent interaction patterns (screen vision recognition, UI element detection, automated mouse/keyboard execution) for operating desktop and web applications without APIs.
原文语言：英语
Integrates human oversight into AI agent workflows for high-stakes decisions through approval gates, feedback loops for RLHF, escalation policies, and decision augmentation patterns that balance automation with accountability.
原文语言：英语
Enables agents to improve through experience using reinforcement learning patterns (PPO, DPO, RLHF) and knowledge base RAG for continuous self-improvement and adaptive behavior across sessions.
原文语言：英语
Integrates the Model Context Protocol (MCP) standard for LLM tool discovery and interaction, implementing MCP client-server architecture with stdio/HTTP transport, tool/resource/prompt types, and FastMCP SDK patterns.
原文语言：英语
Manages agent memory across short-term (conversation buffers), long-term (vector stores, persistent databases), and procedural (learned patterns) layers to maintain stateful context across extended agent interactions.
原文语言：英语
Orchestrates multiple specialized agents in concert using hierarchical, parallel, and sequential topologies (parent-child, debate/consensus, expert teams, sequential handoffs) to solve complex problems that exceed single-agent capability.
原文语言：英语
Implements concurrent task execution patterns (parallel branches, fan-out/fan-in, multi-API calls, multi-modal processing) to reduce total agent processing time through independent subtask parallelism.
原文语言：英语
Implements multi-step plan generation, iterative refinement, and dynamic task decomposition for proactive agent execution with self-correction.
原文语言：英语
Implements sequential prompt chaining patterns (linear LCEL pipelines, LangGraph stateful flows, Google ADK primitives) to decompose complex reasoning into reliable multi-step agent workflows.
原文语言：英语
Implements advanced prompt engineering techniques (zero-shot/one-shot design, verb-based instructions, structured output, evaluation rubrics) for maximizing LLM response quality.
原文语言：英语
Implements Retrieval-Augmented Generation patterns (chunking strategies, embedding-based vector search, semantic vs keyword retrieval, RAG pipelines) to ground LLM outputs in authoritative external knowledge sources.
原文语言：英语
Implements advanced reasoning methodologies (Chain-of-Thought, Tree-of-Thoughts, ReAct, Self-Correction, Graph of Debates, Program-Aided LLMs) for multi-step problem-solving in complex agent tasks.
原文语言：英语
Implements self-correction feedback loops (execution → evaluation/critique → refinement) to iteratively improve agent outputs through producer-critic collaboration and automated quality gates.
原文语言：英语
Dynamically routes agent work based on cost, budget constraints, latency requirements, and query complexity using LLM-driven model selection with feedback-loop optimization for efficient resource utilization.
原文语言：英语
Implements intent-based routing patterns (LLM classifiers, node transitions, computational graphs) to dispatch queries to specialized sub-agents with fallback chains and confidence scoring.
原文语言：英语
Enables agents to rank and schedule tasks by urgency, importance, dependencies, and resource cost using priority matrices, dynamic re-prioritization, and dependency-aware scheduling for optimal execution order.
原文语言：英语
Implements agent tool use and function calling patterns (@tool decorators, CrewAI tools, Google ADK built-in tools) to enable agents with real-time external data access, API operations, calculations, and code execution.
原文语言：英语
Implements intelligent acceptance orchestrator with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
原文语言：英语
Implements intelligent address github comments with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
原文语言：英语
Implements structural design patterns for AI agent systems including monolithic, multi-agent, hierarchical, and event-driven architectures with state management and security primitives.
原文语言：英语
Implements inter-agent communication patterns (message passing, event-driven coordination, shared memory protocols, RPC-style calls, structured JSON messaging) for reliable multi-agent systems.
原文语言：英语
Implements context window management, sliding window strategies, and persistent memory patterns to maintain AI agent coherence across long interactions.
原文语言：英语
Implements context window management and memory architectures for LLM agents including token budgeting, sliding window strategies, summarization fallbacks, cross-turn state persistence, and external vector store integration.
原文语言：英语
Implements systematic debugging workflows for LLM agent failures including hallucination detection, infinite loop recovery, context window exhaustion, tool call errors, and cascading failure diagnosis using distributed tracing patterns.
原文语言：英语
Implements intelligent agent evaluation with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
原文语言：英语
Implements intelligent agent manager skill with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
原文语言：英语
Implements intelligent agent memory systems with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
原文语言：英语
Implements tracing, cost tracking, and latency monitoring patterns for AI agent systems to debug failures, control token spend, and optimize response times across multi-agent workflows.
原文语言：英语
Implements fault-tolerance mechanisms for AI agent systems including circuit breakers, exponential backoff retries, graceful degradation, health checks, dead letter queues, and timeout management with observability hooks.
原文语言：英语
Defines and structures functional, non-functional, and safety requirements for AI agent systems including capability matrices, hallucination thresholds, data quality standards, and evaluation criteria.
原文语言：英语
Implements prompt injection detection, input validation, tool access control, and output sanitization to secure LLM agents against adversarial attacks.
原文语言：英语
Implements systematic evaluation, benchmarking, and testing of AI agent behaviors with tool-use accuracy, hallucination detection, multi-turn reasoning metrics, and automated grading pipelines.
原文语言：英语
Implements intelligent ai agent development with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
原文语言：英语
Implements guardrails, safety checks, hallucination detection, prompt injection defense, and output validation for autonomous AI agents to prevent misuse, unauthorized actions, and unreliable behavior.
原文语言：英语
Implements intelligent ai agents architect with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
原文语言：英语