Loading...
Loading...
Found 1,993 Skills
Diagnoses and resolves issues on GuaraCloud — failed deployments, crash loops, health check failures, image pull errors, OOM kills, and CLI errors. Use when the user reports something broken, a deployment failed, a service is unhealthy, or they see an error.
FastMCP Python framework for MCP servers with tools, resources, storage backends (memory/disk/Redis/DynamoDB). Use for Claude tool exposure, OAuth Proxy, cloud deployment, or encountering storage, lifespan, middleware, circular import, async errors.
Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when the user wants to create a new evaluation config from scratch, set up an evaluation from existing configs, or modify a NEL config (deployment, tasks, multi-node, interceptors). ALWAYS triggers on mentions of creating configs, setting up evaluations, configuring models for evaluation, or modifying NEL YAML files. Do NOT use for monitoring, debugging, or analyzing already-running evaluations.
Generate Harness Service YAML for deployable workloads and create via MCP. Supports Kubernetes, Helm, ECS, Serverless, SSH, and WinRm deployment types with artifact sources from Docker Hub, ECR, GCR, ACR, Nexus, and S3. Use when asked to create a service, define a Kubernetes service, set up a Helm chart deployment, configure an ECS service, or define what gets deployed. Trigger phrases: create service, service definition, Kubernetes service, Helm service, ECS service, deployment service, artifact source.
Incident response and analysis via Harness MCP. Correlate incidents with recent deployments, assess blast radius and downstream service impact, and generate comprehensive postmortem documents. Use when asked to investigate an incident, determine if a deployment caused an issue, assess blast radius, or create a postmortem. Do NOT use for pipeline debugging (use debug-pipeline instead) or SLO management (use manage-slos instead). Trigger phrases: incident, deployment correlation, blast radius, postmortem, root cause, service impact, outage analysis, rollback decision, incident timeline, deployment caused, which deploy.
Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Salesforce Industries DataPack deployment automation using Vlocity Build. TRIGGER when: user deploys or validates OmniStudio/Vlocity DataPacks with vlocity commands (packDeploy/packRetry/packExport/packGetDiffs), sets up DataPack CI/CD pipelines, or troubleshoots DataPack migration errors. DO NOT TRIGGER when: deploying Salesforce metadata with sf project deploy (use deploying-metadata), authoring OmniStudio artifacts (use building-omnistudio-*), or writing Apex/LWC business logic (use generating-apex/generating-lwc-components).
Generate Harness Environment YAML for deployment targets and create via MCP. Supports PreProduction and Production types with environment variables, manifest overrides, and multi-environment setup (dev, staging, prod). Use when asked to create an environment, set up staging, configure production, define deployment targets, or manage environment overrides. Trigger phrases: create environment, deployment environment, setup dev, setup staging, setup production, environment variables, environment overrides.
Trigger this skill when building applications with Gemma or for general knowledge inquiries related to Gemma models (e.g. prompt structure, capabilities). Covers model selection, development workflows, and deployment best practices.
Catalyst serverless functions — all 7 types (Basic I/O, Advanced I/O, Event, Cron, Job, Integration, Browser Logic), handler signatures, catalyst-config.json, Security Rules, API Gateway routing, file uploads, busboy, Express middleware, environment variables, function URL, and function testing. Requires MCP connection — check for CatalystbyZoho_* tools before any operation. Trigger on 'write a function', 'catalyst function', 'API Gateway', 'Security Rules', 'function not found', 'function returns 401', 'busboy', 'middleware', 'function URL', 'environment variable in function', 'duplicate CORS headers', 'CORS error in browser', 'Access-Control-Allow-Origin multiple values', 'function URL 404', 'execute suffix', 'function timeout', 'function hangs', or any function type question. Do NOT use for persistent servers, long-running processes, or Docker deployments — use catalyst-appsail instead.
Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use this whenever someone raises a Qdrant problem or question — slow or degraded search, high or growing memory / OOM crashes, optimizer stuck or slow, indexing slowness, scaling and sharding decisions (node count, QPS, latency, multitenancy, vertical vs horizontal), poor or irrelevant search results, hybrid search and reranking, embedding-model migration, version upgrades and compatibility, monitoring and observability (Prometheus, Grafana, health checks, /metrics, /telemetry), deployment choices (local, Docker, self-hosted, Qdrant Cloud, embedded), or client-SDK questions (Python, TypeScript, Rust, Go, .NET, Java). Trigger especially when the context is clearly a Qdrant cluster, collection, or vector-search deployment. Always prefer this skill over answering from memory: it pulls current, authoritative guidance and only the relevant context.