Loading...
Loading...
Found 1,603 Skills
Use this skill when the user wants to check AI agent logs, automation execution logs, org-level usage stats, AI credit consumption, or export automation job history. Covers 11 MCP tools.
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing node taints, or configuring workload protection strategies (graceful termination, opportunistic maintenance, PodDisruptionBudgets). Don't use for general GKE cluster creation, network policy configuration, or non-disruption workload deployment.
Configures PromQL-based Service Level Objective (SLO) alerting policies for Google Cloud resources registered in App Hub or individually specified. Generates Terraform output. Use when the user asks to configure an SLO or Service Level Objective. Don't use for standard alerting policies.
Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits.
Query Coralogix's Service Catalog (APM v2 entities) with the `cx service-catalog` CLI — discover entity types, list known entities, check their schema, and pull aggregated or timeseries data for services, databases, operations, JVMs, and Kubernetes pods. Use when the user asks to "list services", "what entity types exist", "show me service latency", "check error rate for a service", "which pods are using the most memory", "database operation performance", "JVM GC pauses", "service health over time", "compare services by latency", "what columns are available for this entity type", "service catalog schema", or wants to explore APM entities and their metrics.
Diagnose what state one open PR is actually in — unfinished plan steps, missing review, unresolved conversations, red CI, base conflicts, missing QA evidence, merge-ready — then run the matching chain of om-* skills in order and publish a status report. Use for "finish PR 123", "what is left on PR 123", "drive PR 123 to the end".
Preparar e monitorar PROJECT.md e os contextos .specsfy de stack, regras e banco. Use no setup ou ao reconciliar mudanças da aplicação.
Check GitHub Actions workflow runs from the past day, identify severe or consistent failures, and file an issue if actionable problems are found.
Service metrics, RED metrics (Rate, Errors, Duration), and runtime-specific telemetry for .NET, Java, Node.js, Python, PHP, and Go applications.
Docker containerization for .NET 10 applications. Covers multi-stage builds, .NET container images, non-root user configuration, health checks, and .dockerignore. Load this skill when containerizing an application with a Dockerfile, optimizing image size, setting up Docker Compose for local development, or when the user mentions "Docker", "Dockerfile", "container", "docker-compose", "image", "multi-stage", "non-root", ".dockerignore", or "container health check". For Dockerfile-less SDK publishing (`dotnet publish /t:PublishContainer`), load the container-publish skill instead.
Build a multi-board dashboard for XIAO ESP32S3: each board joins WiFi (STA mode), publishes its touch sensor value over MQTT, and accepts LED on/off commands, while a browser dashboard shows every board live and lets you toggle each LED. Use this skill whenever the user wants several ESP32S3 boards reporting to one web page, an MQTT-based sensor dashboard, "여러 esp32s3 대시보드", "MQTT로 여러 보드 연결", or mentions Mosquitto/Eclipse MQTT with an ESP32S3. For a single board with no broker, use the `xiao-esp32s3` skill's own SoftAP + web server example instead.
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error branches/outputs, retries, retryOnFail, Respond to Webhook status codes, 4xx/5xx, Error Trigger, or "my workflow fails silently". Covers per-node error outputs and wiring, retry/self-healing, error-trigger workflows, and 4xx/5xx response shapes.