DevOps Claude Skills
4 344 DevOps skills from 392 authors. They ship releases, run infrastructure and keep watch over what is deployed. Half of them fit into 2 095 tokens or less — that is what one costs your context window when the agent loads it. 513 ship runnable scripts rather than instructions alone. 28 of them cannot work without an MCP server, most often rube. We also found 633 copies of these same skills sitting in other people's repositories — counted once here, not 633 times.
4 344 unique 392 authors 2 063 updated this month 579 from vendors
Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says "analyze experiment", "compare experiments", "analyze against baseline", or provides one or two experiment IDs for analysis.
Datadog skills for AI agents. Essential monitoring, logging, tracing and observability.
End-to-end Agent Observability pipeline for an instrumented ml_app — classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a "continue" checkpoint between each. Pure orchestration over the agent-observability sub-skills (`agent-observability-session-classify`, `agent-observability-trace-rca`, `agent-observability-eval-bootstrap`, `agent-observability-experiment-py-bootstrap`, `agent-observability-experiment-analyzer`). Use when user says "run the eval pipeline", "go from traces to evals", "bootstrap evals end to end", "classify then RCA then bootstrap", "build an eval set from scratch", "onboard me to datasets and experiments", "walk me through experiments", "I have an ml_app, now what", "Agent Observability onboarding", "guided experiment setup", "from traces to experiments", or wants a deterministic, narrated tour from production data through evaluators, datasets, and experiments. Stop early with `--stop-after <phase>` to short-circuit at evaluators or dataset, or resume mid-flow with `--start-at <phase>`.
>- Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the Agent Observability SDK", or has `ddtrace` installed and wants idiomatic SDK code.
> Classify whether user intent was satisfied in a Datadog Agent Observability trace or session. (2) trace_id — classify a single Agent Observability trace without RUM; (3) ml_app — sample and classify multiple sessions or traces from a given LLM app. Output is compact by default (verdict + one-sentence reason). Use when evaluating satisfaction, classifying sessions/traces, labeling data, or generating signal for agent-observability-eval-pipeline or agent-observability-trace-rca.
>- Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and repeats. Use when the user says "run an auto experiment", "hill-climb this code", "iteratively improve X and measure the delta", "optimize this prompt/file against my traces", "auto-optimize against LLM-Obs", or wants the local equivalent of the auto_experiments worker. Works from a local dataset file, an ml_app, a dataset_id, or a list of trace_ids.
Install the Datadog Agent on Kubernetes using the Datadog Operator — required before enabling Single Step Instrumentation (SSI), which automatically instruments applications for APM without code changes. Only use if no Datadog Agent is deployed on the cluster yet.
Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says "what's wrong with my app", "why is my eval failing", "analyze errors", "root cause analysis", "diagnose failures", or wants to understand production failure patterns.
Diagnose and fix Single Step Instrumentation (SSI) issues on Kubernetes — SSI automatically instruments applications for APM without code changes. Only use if the agent and SSI are already configured but traces are missing or instrumentation is not working.
Enable Single Step Instrumentation (SSI) on Kubernetes — automatically instruments applications for APM without code changes. Only use if the Datadog Agent is already running on the cluster — if not, use agent-install first.
Verify Single Step Instrumentation (SSI) is working end-to-end on Kubernetes — SSI automatically instruments applications for APM without code changes. Only use after enable-ssi has run.
> Generate a BYOD ownership preferences reference table for a customer. Walks through preference types, generates CSV, and provides upload instructions (UI, API, cloud storage, or Terraform). Use when asked about BYOD setup, preferences reference table, k9_ownership_preferences, or ownership customization.
Configurez correctement vos zones DNS pour l'email deliverability (SPF, DKIM, DMARC), la sécurité (DNSSEC, CAA), et l'automatisation (OVH API, Cloudflare, Terraform), basé sur les best practices 2024-2025. Use when: **Configurer l'authentification email** - SPF, DKIM, DMARC pour éviter le spam folder; **Sécuriser un domaine** - DNSSEC, CAA records, protection contre le spoofing; **Automatiser la gestion DNS** - OVH API, Cloudflare API, Terraform; **Débugger des problèmes DNS** - dig, nslookup...
Generate predictive pipeline forecasts with confidence intervals and scenario modeling for revenue planning
Track buying signals like funding announcements, job postings, tech changes, and company news to identify sales-ready prospects
Build durable competitive advantage using Hamilton Helmer's \"7 Powers\" framework—the complete, mutually exclusive enumeration of all possible sources of sustainable business moats. Use when: **Evaluate your competitive position** and identify if you have true Power; **Choose strategic direction** for building durable advantage; **Analyze competitors** to understand their moats and vulnerabilities; **Advise on M&A** whether an acquisition target has defensible value; **Assess startup investmen...
> (colcon/ament), edits launch files (.launch.py), configures QoS or DDS, writes URDF/xacro, implements ros2_control hardware interfaces or controllers, sets up Nav2/MoveIt 2 pipelines, processes sensor data (camera/LiDAR/PCL), works with Gazebo/Isaac Sim, configures SROS2 security, develops micro-ROS firmware, manages multi-robot fleets (Open-RMF), debugs with ros2 doctor/rosbag2, deploys via Docker/cross-compilation, or migrates from ROS 1. DO NOT TRIGGER for general C++/Python questions unrelated to ROS 2, non-robotics middleware, or web/mobile development tasks.
Deploy trained machine learning models as production-ready services using REST APIs, containers, serverless functions, and orchestration platforms.
A skill to create, manage, and automate machine learning pipelines.
Monitor cloud infrastructure and applications using metrics, logs, and traces to provide real-time observability into performance, health, and reliability.
Set up a continuous integration and continuous delivery (CI/CD) pipeline for a software project, automating builds, tests, and deployments across environments.
Define, deploy, and manage cloud infrastructure as code using tools like Terraform, Pulumi, CloudFormation, and CDK, ensuring consistency, repeatability, and version control.
Set up and orchestrate multi-container Docker applications using docker-compose, including service configuration, networking, volumes, and environment management.
Deploy, manage, and scale applications on Kubernetes clusters using manifests, Helm charts, and autoscaling configurations.
Automatically migrates build systems and CI/CD configurations to target platforms. Use when modernizing build infrastructure, switching CI/CD providers, or standardizing across projects. Supports common migration paths including Maven↔Gradle, npm↔Yarn, Travis CI→GitHub Actions, CircleCI→GitHub Actions, Jenkins→GitLab CI, and GitLab CI→GitHub Actions. Analyzes existing configuration, generates equivalent target configuration, maps dependencies and commands, and provides validation and migration documentation.
Generate GitHub Actions deployment workflows for automated deployment to staging and production environments on cloud platforms (AWS, GCP, Azure). Use when setting up continuous deployment pipelines, creating deployment automation, or configuring multi-environment deployment strategies. Includes templates for environment-specific deployments with approval gates, secrets management, and rollback capabilities.
Generate configuration files for applications, services, and infrastructure. Use when: (1) Setting up new projects (package.json, requirements.txt, tsconfig.json), (2) Creating Docker or Kubernetes configurations, (3) Configuring CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI), (4) Setting up web servers (Nginx, Apache), (5) Defining infrastructure as code (Terraform, CloudFormation), (6) Generating linter/formatter configs (ESLint, Prettier, Black). Provides templates and custom-generated configs for diverse tech stacks.
Generate Dockerfiles, Docker Compose configurations, and Kubernetes manifests for containerizing applications. Use when: (1) Creating Dockerfiles for Node.js, Python, Java, Go, or other applications, (2) Setting up multi-service environments with Docker Compose, (3) Generating Kubernetes deployments, services, and ingress configurations, (4) Optimizing container images for production, (5) Implementing containerization best practices. Provides both ready-to-use templates and custom-generated configurations based on project requirements.
Generate setup scripts and instructions for development environments across platforms. Use when: (1) Setting up new development machines (Python, Node.js, Docker, databases), (2) Creating automated setup scripts for team onboarding, (3) Need cross-platform setup instructions (macOS, Linux, Windows), (4) Installing development tools and dependencies, (5) Configuring version managers and package managers. Provides executable setup scripts, platform-specific guides, and tool installation instructions.
Suggests rollback strategies for failed deployments across different platforms and failure types. Use when deployments fail and need to be reverted, including application code rollbacks, database migration reversions, infrastructure changes, and configuration updates. Supports Docker/Docker Compose environments with step-by-step procedural guidance for safe and effective rollback execution.
Creates visual representations of system structure including architecture diagrams, data flow diagrams, deployment diagrams, and sequence diagrams. Use when Claude needs to visualize system components, infrastructure, data flows, or interactions. Supports Mermaid (recommended for Markdown/GitHub), PlantUML (for detailed UML), and Graphviz/DOT (for complex networks). Trigger when users request diagrams, visualizations, or ask to "show", "diagram", "visualize", or "map out" system architecture, infrastructure, data flows, or component interactions.
The lifecycle gate for a local Codespace-equivalent sandbox. Routed to when the user invokes /ca-sandbox:sandbox to pull an untrusted repo into an ephemeral, host-FS-isolated Docker container, or any of the interaction commands (/ca-sandbox:sandbox-shell, /ca-sandbox:sandbox-exec, /ca-sandbox:sandbox-cp, /ca-sandbox:sandbox-destroy) against an existing box. Five gated phases — pre-flight, clone+build, isolated run, interact, teardown. The load-bearing invariant is structural: untrusted code in the box can never reach the host filesystem (no bind mount, no docker socket, never --privileged, cap-drop ALL, non-root, read-only root). Network defaults to offline; egress out is host-initiated only. Every object is labeled ca.sandbox=1 and torn down on exit.
Automatically fix Azure SDK CI/CD pipeline failures by applying code changes and verifying locally. USE FOR: "fix pipeline failure", "fix CI", "fix failing tests", "auto-fix and commit the fix", "fix build error", "fix mypy/pylint/type-check/lint errors", "auto-fix pipeline", "resolve pipeline failure". DO NOT USE FOR: pipeline analysis (instead use azsdk-common-pipeline-analysis), API design review, SDK publishing. INVOKES: azure-sdk-mcp:azsdk_package_build_code, azure-sdk-mcp:azsdk_package_run_check, azure-sdk-mcp:azsdk_package_run_tests, azure-sdk-mcp:azsdk_verify_setup.
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdk_analyze_pipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in CI", "analyze pipeline", "debug SDK pipeline". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing, applying code fixes (instead use azsdk-common-pipeline-fixer). INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_get_pipeline_llm_artifacts, azure-sdk-mcp:azsdk_get_pr_checks, azure-sdk-mcp:azsdk_get_pipeline_status.
Authors and modifies Azure TypeSpec (.tsp) API specifications. MUST BE USED FOR ALL TypeSpec changes regardless of complexity — even adding a single property or enum value requires this skill's validation workflow. USE FOR: any TypeSpec/tsp change — api versions (add, bump, preview, stable, promote), resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO, suppressions, operationId, spread model. Covers both ARM resource-manager (Azure.ResourceManager) and data-plane (Azure.Core) services. DO NOT USE FOR: SDK generation, releasing SDK packages, or single MCP tool calls. INVOKES: azure-sdk-mcp:azsdk_typespec_generate_authoring_plan, azure-sdk-mcp:azsdk_run_typespec_validation.
Run the Azure SDK generation pipeline for a release plan and create the generated SDK pull requests, for one language or for all languages. **UTILITY SKILL**. USE FOR: "run SDK generation for all languages", "generate SDK for release plan <id>", "generate SDK for release <id>", "pipeline SDK generation", "generate SDK without a local clone", "create SDK pull requests". DO NOT USE FOR: generating a single SDK locally from a local clone (use azsdk-common-generate-sdk-locally), releasing/publishing an already-generated package (use azsdk-common-sdk-release), API design review. INVOKES: azure-sdk-mcp:azsdk_get_release_plan, azure-sdk-mcp:azsdk_run_generate_sdk, azure-sdk-mcp:azsdk_get_sdk_pull_request_link.
Run Azure SDK QA bot evaluations on curated datasets locally, including a single test case. WHEN: "run evaluation", "run eval", "evaluate the bot", "run perf evaluation", "run basic evaluation", "run a single test case", "evaluate one question", "run all scenarios", "score the bot", "run evals locally". DO NOT USE FOR: preparing or uploading datasets, pipeline troubleshooting, knowledge-graph indexing.
Authors and modifies Azure TypeSpec (.tsp) API specifications. USE FOR: any TypeSpec/tsp change — api versions (add, bump, preview, stable, promote), resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO, suppressions, operationId, spread model. Covers ARM resource-manager and data-plane services. DO NOT USE FOR: SDK generation, releasing SDK packages, or single MCP tool calls. INVOKES: azure-sdk-mcp:azsdk_typespec_generate_authoring_plan, azure-sdk-mcp:azsdk_run_typespec_validation.
Deploy test resources and run Azure SDK tests in live, record, or playback mode. WHEN: \"run live tests\", \"run recorded tests\", \"deploy test resources\", \"record tests\", \"run tests in record mode\", \"clean up test resources\", \"run tests against live resources\". DO NOT USE FOR: writing new tests, authoring Bicep templates, playback-only test runs without resource deployment. INVOKES: azure-sdk-mcp:azsdk_package_run_tests.
Diagnose and resolve failures in Azure SDK CI and generation pipelines. **UTILITY SKILL**. USE FOR: \"pipeline failed\", \"build failure\", \"CI check failing\", \"SDK generation error\", \"reproduce pipeline locally\", \"debug SDK pipeline\". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing. INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_package_build_code, azure-sdk-mcp:azsdk_package_run_check.
Self-contained SaaS pipeline — invoke directly, do not decompose. Generates a Vibes app, adds auth + billing, and deploys live. Uses Agent Teams to parallelize for maximum speed. Use when the user wants to build and ship a complete SaaS product in one step, or says "launch", "ship it", "build and deploy".
Self-contained SaaS pipeline — invoke directly, do not decompose. Generates a factory app with landing page, Stripe subscription checkout, Vibe Token economics, and deploys to Cloudflare Workers. Use when the user wants to monetize an app, add billing, create token-backed revenue sharing, or turn an app into a business.
Self-contained deploy automation — invoke directly, do not decompose. Deploys a Vibes app to Cloudflare Workers via the Deploy API. Use when deploying, publishing, going live, pushing to production, or hosting on the edge.
Self-contained SaaS pipeline — invoke directly, do not decompose. Generates a Vibes app, adds auth + billing, and deploys live. Uses Agent Teams to parallelize for maximum speed. Use when the user wants to build and ship a complete SaaS product in one step, or says "launch", "ship it", "build and deploy".
Self-contained deploy automation — invoke directly, do not decompose. Deploys a Vibes app to Cloudflare Workers via the Deploy API. Use when deploying, publishing, going live, pushing to production, or hosting on the edge. Authenticates with Pocket ID.
Comprehensive GitHub repository management toolkit. Provides file editing, issue/PR management, GitFlow workflow, release management, commit investigation, CI/CD workflow creation, and configuration file generation via MCP GitHub tools.