ops-engineering-skills

In the author's own words, from each skill's SKILL.md — showing the first 29 of 297 files.

• 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 should manage state and memory across turns, or review whether an existing agent's control flow is sa…

  plugins/ai-agent/skills/agent-architecture-design/SKILL.md on GitHub (opens in a new tab)

• 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 of the symptom. Use when a user asks to "investigate this bad agent response," "why did the agent sa…

  plugins/ai-agent/skills/agent-bad-response-triage-and-root-cause-classification/SKILL.md on GitHub (opens in a new tab)

• 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 workflow got slow/expensive all of a sudden," "investigate a cost/latency spike," or reports an alert/in…

  plugins/ai-agent/skills/agent-cost-and-latency-spike-investigation/SKILL.md on GitHub (opens in a new tab)

• 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 needs to know whether a prompt/model/tool change made an agent better or worse before shipping it.

  plugins/ai-agent/skills/agent-evaluation-and-guardrails/SKILL.md on GitHub (opens in a new tab)

• 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 session," "the agent keeps retrying the same failing action," "someone just raised the retry limit and…

  plugins/ai-agent/skills/agent-tool-call-loop-diagnosis-and-circuit-breaking/SKILL.md on GitHub (opens in a new tab)

• 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 tool output safely, or add confirmation gates before destructive tool actions.

  plugins/ai-agent/skills/agent-tool-use-patterns/SKILL.md on GitHub (opens in a new tab)

• 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 coding agent a code graph," "reduce how many tool calls/tokens my agent burns exploring the repo," "set…

  plugins/ai-agent/skills/code-knowledge-graph-tools-for-ai-agents/SKILL.md on GitHub (opens in a new tab)

• 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 database for RAG, MCP servers for tool access, an evaluation-and-guardrails harness, and cost/latency…

  plugins/ai-agent/skills/complete-ai-agent-stack-deployment-cloud-managed-from-scratch/SKILL.md on GitHub (opens in a new tab)

• 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 an evaluation/guardrails harness — with no managed LLM API or managed vector database anywhere in t…

  plugins/ai-agent/skills/complete-ai-agent-stack-deployment-self-hosted-from-scratch/SKILL.md on GitHub (opens in a new tab)

• 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 AutoGen for multi-agent," "define agent roles and tasks in CrewAI," "configure a GroupChat in AutoG…

  plugins/ai-agent/skills/crewai-and-autogen-multi-agent-frameworks/SKILL.md on GitHub (opens in a new tab)

• 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 for a stateful agent," "add persistence/checkpointing to a LangChain agent," "add a human approval st…

  plugins/ai-agent/skills/langchain-and-langgraph-agent-orchestration/SKILL.md on GitHub (opens in a new tab)

• 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, streaming, or batching, or needs to size a cost/latency budget before scaling an agent to more users.

  plugins/ai-agent/skills/llm-cost-and-latency-optimization/SKILL.md on GitHub (opens in a new tab)

• 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 "set up an LLM gateway/proxy," "route between OpenAI/Anthropic/Azure/Bedrock," "add a fallback model w…

  plugins/ai-agent/skills/llm-gateway-and-multi-provider-routing/SKILL.md on GitHub (opens in a new tab)

• 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 custom data source or internal API, or review an MCP server for security issues before granting it t…

  plugins/ai-agent/skills/mcp-server-development/SKILL.md on GitHub (opens in a new tab)

• 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 agents that duplicate work or talk past each other, or is deciding how a supervisor agent should delega…

  plugins/ai-agent/skills/multi-agent-orchestration/SKILL.md on GitHub (opens in a new tab)

• 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 agent," or is deciding what belongs in a system prompt vs. a tool description vs. retrieved content…

  plugins/ai-agent/skills/prompt-and-context-engineering/SKILL.md on GitHub (opens in a new tab)

• 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," "chunk documents for embedding," or needs to ground an agent's answers in a private/internal kno…

  plugins/ai-agent/skills/rag-pipeline-design/SKILL.md on GitHub (opens in a new tab)

• 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 config before we go live," "will this embedding dimension/metric mismatch break retrieval," "test reca…

  plugins/ai-agent/skills/vector-database-configuration-validation/SKILL.md on GitHub (opens in a new tab)

• 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 into our vector DB," "re-index when source documents change," "batch-embed a large corpus," "the vecto…

  plugins/ai-agent/skills/vector-database-ingestion-pipeline-for-rag/SKILL.md on GitHub (opens in a new tab)

• 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 more vectors/QPS," "tune HNSW parameters," "set up sharding or replication for Pinecone/Weaviate/Mi…

  plugins/ai-agent/skills/vector-database-operations-pinecone-weaviate-milvus/SKILL.md on GitHub (opens in a new tab)

• aws-codepipeline-and-codedeploy

  Designs AWS CodePipeline stage/action structure and integrates it with CodeDeploy deployment groups and appspec.yml for EC2/on-prem, ECS, or Lambda deploys. Use when the user asks to "set up CodePipeline," "add a CodeDeploy deployment group," "write an appspec.yml," "wire CodePipeline to CodeDeploy," "troubleshoot a stuck/failed CodePipeline action," or "add a manual approval action before an AWS…

  plugins/cicd-tooling/skills/aws-codepipeline-and-codedeploy/SKILL.md on GitHub (opens in a new tab)

• azure-pipelines-yaml-and-multi-stage

  Designs Azure Pipelines YAML (azure-pipelines.yml), multi-stage pipelines with environments/approvals, templates for reuse across repos, and self-hosted vs. Microsoft-hosted agent pools. Use when the user asks to "set up Azure Pipelines," "write an azure-pipelines.yml," "add a multi-stage pipeline with approvals," "create a reusable pipeline template," "configure a self-hosted agent pool," or "tr…

  plugins/cicd-tooling/skills/azure-pipelines-yaml-and-multi-stage/SKILL.md on GitHub (opens in a new tab)

• bamboo-pipeline-yaml-and-java-specs

  Authors Atlassian Bamboo pipeline definitions using either Bamboo Specs (Java DSL, compiled and run to create/update a plan) or Bamboo's YAML specs format, covering plan/job/stage structure and how a Specs definition links to and updates a live Bamboo plan. Use when the user asks to "write a Bamboo Specs plan," "convert our Bamboo plan to code," "add a stage/job to a Bamboo build," "use Bamboo YA…

  plugins/cicd-tooling/skills/bamboo-pipeline-yaml-and-java-specs/SKILL.md on GitHub (opens in a new tab)

• complete-cicd-pipeline-deployment-for-kubernetes-from-scratch

  Builds a complete CI/CD pipeline for a Kubernetes-targeted service from an empty repo — source checkout, container image build, SCA/SAST security gates, registry push, and a deploy step that ends at a GitOps handoff (committing a new image tag to a manifests repo) rather than a direct kubectl apply or helm upgrade against the cluster. Use when the user asks to "build a full CI/CD pipeline for Kub…

  plugins/cicd-tooling/skills/complete-cicd-pipeline-deployment-for-kubernetes-from-scratch/SKILL.md on GitHub (opens in a new tab)

• complete-cicd-pipeline-deployment-for-serverless-from-scratch

  Builds a complete CI/CD pipeline for a serverless (AWS Lambda-style) function from an empty repo — source checkout, zip/layer packaging (not a container image), SCA/SAST security gates, package upload, and a SAM/Serverless-Framework/CDK-style deploy step with alias-based canary traffic shifting, distinct from Kubernetes rollout mechanics. Use when the user asks to "build a full CI/CD pipeline for…

  plugins/cicd-tooling/skills/complete-cicd-pipeline-deployment-for-serverless-from-scratch/SKILL.md on GitHub (opens in a new tab)

• complete-cicd-pipeline-for-vm-based-workloads-from-scratch

  Builds a complete CI/CD pipeline for a VM-based workload from an empty repo — source checkout, build, immutable machine-image baking (Packer-style AMI, not a container image or a zip), SCA/SAST security gates, and a deploy step that's either a blue-green instance-group swap or a config-management push (Ansible) to existing long-lived VMs, distinct from both container and serverless deploy mechani…

  plugins/cicd-tooling/skills/complete-cicd-pipeline-for-vm-based-workloads-from-scratch/SKILL.md on GitHub (opens in a new tab)

• gitea-actions-and-ci

  Configures Gitea Actions — Gitea's GitHub Actions-compatible CI/CD runner — including self-hosted act_runner setup/registration and the specific differences from GitHub Actions (supported contexts, missing features, runner labels). Use when the user asks to "set up CI on Gitea," "configure Gitea Actions," "register an act_runner," "port a GitHub Actions workflow to Gitea," or "troubleshoot a Gite…

  plugins/cicd-tooling/skills/gitea-actions-and-ci/SKILL.md on GitHub (opens in a new tab)

• github-actions-centralized-reusable-workflows

  Designs organization-level reusable GitHub Actions workflows (workflow_call) and shared composite actions hosted in a dedicated repo, so many repos call one standardized pipeline definition instead of duplicating workflow YAML. Use when the user asks to "centralize our GitHub Actions workflows," "create a reusable workflow with workflow_call," "enforce a standard CI pipeline across all repos," "v…

  plugins/cicd-tooling/skills/github-actions-centralized-reusable-workflows/SKILL.md on GitHub (opens in a new tab)

• github-actions-single-repo-workflows

  Authors and troubleshoots GitHub Actions workflow YAML that lives in and serves a single repository — triggers, jobs/steps, matrix builds, caching with actions/cache, and composite actions defined within the same repo under .github/actions/. Use when the user asks to "write a GitHub Actions workflow," "add a matrix build," "fix a failing GitHub Actions job," "add a composite action to this repo,"…

  plugins/cicd-tooling/skills/github-actions-single-repo-workflows/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill