ai-agent-skills

Plugin ai-agent-skills from marketplace ops-engineering-skills in selvarajmurugesan90/ops-engineering-skills. Commands read from the repo's manifest — 1 month ago.

Skills (20)

• agent-architecture-design

  Guides designing the control loop, state/memory model, and tool boundaries for an LLM-driven agent. Use when a user asks to "design an agent architecture," choose between a ReAct loop / plan-and-execute / finite-state agent, decide on single-agent vs multi-agent decomposition, define how an agent sh

• agent-bad-response-triage-and-root-cause-classification

  Guides triaging a single reported bad, wrong, or harmful agent response: reproducing it deterministically and classifying the root cause into one of five buckets — prompt issue, tool failure, retrieval issue, model behavior change, or genuine edge case — so the fix targets the actual cause instead o

• agent-cost-and-latency-spike-investigation

  Guides rapidly triaging a sudden cost or latency spike affecting one specific agent workflow — scoping it, correlating it against recent changes, and applying a fast, safe stopgap — before launching a full optimization pass. Use when a user asks "why did our LLM bill jump overnight," "this one workf

• agent-evaluation-and-guardrails

  Guides building evaluation harnesses, regression test suites, and runtime guardrails for LLM agents. Use when a user asks to "evaluate this agent," "write test cases for a prompt change," "set up an eval harness," "add guardrails to prevent unsafe output," "detect prompt injection at runtime," or ne

• agent-tool-call-loop-diagnosis-and-circuit-breaking

  Guides diagnosing an active or recurring runaway agent tool-call loop and stopping it safely with a bounded retry policy and a hard ceiling — distinct from raising the iteration limit. Use when a user asks to "figure out why the agent is stuck calling the same tool," "safely kill a runaway agent ses

• agent-tool-use-patterns

  Guides designing safe, reliable tool/function-calling interfaces and loops for LLM agents. Use when a user asks to "design tool schemas," fix an agent that hallucinates tool calls or arguments, prevent infinite tool-call loops, decide how much autonomy to give an agent's tool use, handle untrusted t

• code-knowledge-graph-tools-for-ai-agents

  Compares GitNexus, Graphify, and CodeGraph — tools that precompute a structural knowledge graph of a codebase and expose it to AI coding agents via MCP, replacing repeated grep/file-read exploration with direct impact-radius, call-chain, and dependency queries. Use when a user asks to "give my codin

• complete-ai-agent-stack-deployment-cloud-managed-from-scratch

  Sequences a complete, end-to-end AI agent stack deployment built on managed cloud services from scratch — a cloud landing zone, agent control-flow architecture, an LLM gateway routing across managed provider APIs (vendor-neutral: Anthropic/OpenAI/Azure OpenAI/Bedrock/ Vertex AI), a managed vector da

• complete-ai-agent-stack-deployment-self-hosted-from-scratch

  Sequences a complete, end-to-end, fully self-hosted AI agent stack deployment from scratch — GPU procurement/sizing for open-weight model serving, self-hosted LLM serving (vLLM/TGI), agent control-flow architecture, a self-hosted vector database for RAG, self-hosted MCP servers for tool access, and

• crewai-and-autogen-multi-agent-frameworks

  Guides building multi-agent systems with role-based frameworks — CrewAI's crew/task/process model and Microsoft AutoGen's conversable-agent model — as opinionated implementations of multi-agent orchestration patterns. Use when a user asks to "build this with CrewAI," "set up a crew of agents," "use

• langchain-and-langgraph-agent-orchestration

  Guides building LLM applications with LangChain's chain/agent abstractions and, for stateful multi-step agents, LangGraph's graph-based orchestration (nodes, edges, cycles, checkpointed persistence, human-in-the-loop interrupts). Use when a user asks to "build this with LangChain," "use LangGraph fo

• llm-cost-and-latency-optimization

  Guides reducing token cost and response latency of LLM-based agents without degrading quality. Use when a user asks to "reduce our LLM API bill," "make the agent respond faster," "our token usage is too high," "should we use a smaller/cheaper model here," decide where to apply prompt caching, stream

• llm-gateway-and-multi-provider-routing

  Configures an LLM gateway/proxy (LiteLLM, Portkey, OpenRouter-style) that sits between agent code and one or more model providers to unify routing, automatic fallback on a provider outage or rate-limit, and cost/rate-limit tracking across providers behind one API surface. Use when a user asks to "se

• mcp-server-development

  Guides building and hardening an MCP (Model Context Protocol) server that exposes tools, resources, or prompts to AI coding agents. Use when a user asks to "build an MCP server," "expose this API as MCP tools," "write an MCP manifest/tool schema," connect Claude Code/Cursor/Gemini CLI/Copilot to a c

• multi-agent-orchestration

  Guides deciding when and how to split a task across multiple cooperating LLM agents (supervisor/worker, pipeline, or debate patterns) instead of one agent with many tools. Use when a user asks to "design a multi-agent system," "should this be one agent or several," "orchestrate sub-agents," fix agen

• prompt-and-context-engineering

  Guides structuring system prompts, managing context window budget, and organizing what an LLM agent sees at each turn. Use when a user asks to "write a system prompt," "reduce token usage," "fix inconsistent agent behavior," "the model ignores my instructions," "organize context for a long-running a

• rag-pipeline-design

  Guides designing retrieval-augmented generation (RAG) pipelines: document chunking, embedding, indexing, retrieval, and grounding LLM output in retrieved content. Use when a user asks to "build a RAG pipeline," "the agent hallucinates facts it should know from our docs," "improve retrieval relevance

• vector-database-configuration-validation

  Validates a vector index's schema/dimension/distance-metric config and its actual recall/query-performance behavior before a production cutover — catching a mismatch that returns wrong-but-plausible results or degraded recall instead of an error. Use when a user asks to "validate my vector index con

• vector-database-ingestion-pipeline-for-rag

  Builds and operates the ingestion pipeline that feeds a vector database for RAG — document chunking as a pipeline stage, batch embedding jobs, idempotent/resumable upserts, and re-indexing triggered by source-document updates. Use when a user asks to "build a pipeline to embed and load documents int

• vector-database-operations-pinecone-weaviate-milvus

  Guides day-to-day operation of vector databases — index configuration, sharding/replication for scale and availability, and upsert/query performance tuning — with concrete equivalents across Pinecone, Weaviate, and Milvus. Use when a user asks to "configure a vector index," "scale our vector DB for

Similar plugins