Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Installing, configuring, and running @sasjs/server - the open-source NodeJS wrapper around the SAS binary that provides a REST API, filesystem (SASjs Drive), Stored Program execution, and web app streaming. Covers desktop vs server modes, runtimes (SAS/JS/Python/R), env vars, auth (tokens, LDAP), and mock servers. Use when deploying, troubleshooting, or developing against sasjs/server.
Develops business applications on SAP Business Technology Platform (BTP) using CAP (Node.js/Java) or ABAP Cloud. Use when: building cloud applications on SAP BTP, deploying to Cloud Foundry or Kyma runtimes, integrating with SAP HANA Cloud, implementing SAP Fiori UIs, connecting to remote SAP systems, building multitenant SaaS applications, extending SAP S/4HANA or SuccessFactors, setting up CI/CD pipelines, implementing observability, or following SAP development best practices. Keywords: SAP BTP, Business Technology Platform, CAP, Cloud Application Programming Model, ABAP Cloud, Cloud Foundry, Kyma, SAP HANA Cloud, SAP Fiori, SAPUI5, CI/CD, observability, multitenant, SaaS, SAP BTP ABAP environment, SAP Business Application Studio, SAP Cloud SDK, SAP Integration Suite, SAP Event Mesh, SAP Connectivity Service, SAP Destination Service, XSUAA, OAuth, OpenID Connect, OData, CDS, Core Data Services, ABAP CDS, ABAP RESTful Application Programming Model, RAP, ABAP development, SAP BTP development
CloudBase platform overview and routing guide. This skill should be used when users need high-level capability selection, platform concepts, console navigation, realtime (broadcast / presence / live database changes), or cross-platform best practices before choosing a more specific implementation skill.
Design and operate service reliability targets in Elastic Observability: choose an SLI type and a defensible target, pick a time window and budgeting method, create and maintain SLOs through the Kibana API, attach burn-rate alert rules, and decide when an SLO is the wrong instrument and a threshold rule, anomaly job, or synthetics monitor is right. Use when defining or reviewing SLOs and error budgets, tuning burn-rate alerting, reducing alert noise, or setting up availability monitoring for a user-facing endpoint.
Onboard an application into Elastic Observability with the Elastic Distribution of OpenTelemetry (EDOT): route on language and runtime, detect and replace a classic Elastic APM agent, apply the required OTLP configuration, and then verify with ES|QL that traces, metrics, and logs actually arrive under the expected service name. Use when adding observability to a service, migrating off the classic Elastic APM agent, or debugging why an instrumented service is not showing up in Elastic.
ALWAYS USE THIS SKILL to create, list, or delete org shapes. An org shape is a captured baseline configuration (features, limits, edition, and Metadata API settings) of a source org, without its data or metadata. Use when the user asks to create/make/take an org shape, capture or replicate an org's configuration/edition/limits, list/show/view existing org shapes (including INACTIVE/superseded ones) or their IDs and status, or delete/remove org shapes for a source org. Requires a source org with Dev Hub and Org Shape for Scratch Orgs enabled. DO NOT TRIGGER for creating/checking/listing/deleting snapshots (use dx-org-snapshot-manage) or for creating scratch orgs (use dx-org-manage).
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation after user confirmation. Use when the user wants to instrument their app, add tracing from scratch, set up LLM observability, integrate OpenTelemetry or openinference, or get started with Arize tracing.
Core Catalyst project setup — directory structure, environments, CLI commands, and all Catalyst IDs (Project ID, ZAID, Table ID, Segment ID, Org ID). Trigger on 'start a Catalyst project', 'what is .catalystrc', 'where do I find my Table ID', 'difference between Development and Production', or any Catalyst ID or CLI question.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism
Onboard an Elastic Cloud organization: configure the `elastic` CLI's Cloud context and API key, establish a default region, then invite users, assign predefined or custom Serverless project roles, and create or revoke Cloud API keys. Use when setting up Cloud authentication or when granting, modifying, or auditing user access to an organization and its projects.
Provision and operate Elastic Cloud infrastructure: create, connect to, update, and delete Serverless projects (Elasticsearch, Observability, Security); manage traffic filters (IP and AWS PrivateLink network security); and manage the lifecycle of Elastic Cloud Hosted deployments. Use when creating or performing day-2 operations on serverless projects or hosted deployments, or restricting their network access.
Safe-release techniques DURING rollout: feature flags, progressive rollouts, canary analysis, guardrail metrics, production smoke tests, and synthetic users. Bridges QA and SRE practices. Use when: "feature flag testing," "canary deploy," "progressive rollout," "guardrail metrics," "dark launch," "safe rollout." Not for: scheduled probes that run continuously after release — use `synthetic-monitoring`. Not for: designing tests from prod telemetry — use `observability-driven-testing`. Related: release-readiness, synthetic-monitoring, observability-driven-testing, qa-metrics.
Complete PowerShell expertise system across ALL platforms (Windows/Linux/macOS). PROACTIVELY activate for: (1) ANY PowerShell task (scripts/modules/cmdlets), (2) CI/CD automation (GitHub Actions/Azure DevOps/Bitbucket), (3) Cross-platform scripting, (4) Module discovery and management (PSGallery), (5) Azure/AWS/Microsoft 365 automation, (6) Script debugging and optimization, (7) Best practices and security. Provides: PowerShell 7+ features, popular module expertise (Az, Microsoft.Graph, PnP, AWS Tools), PSGallery integration, platform-specific guidance, CI/CD pipeline patterns, cmdlet syntax mastery, and production-ready scripting patterns. Ensures professional-grade, cross-platform PowerShell automation following industry standards.
Catalyst AppSail — persistent backend PaaS with managed runtimes (Node.js, Java, Python) and custom Docker containers. Trigger on 'AppSail', 'persistent server', 'Docker on Catalyst', 'X_ZOHO_CATALYST_LISTEN_PORT', or 'long-running process on Catalyst'. Do NOT use for stateless request/response handlers, event-driven functions, or scheduled jobs — use catalyst-functions instead.
Apply when implementing caching logic, CDN configuration, or performance optimization for a headless VTEX storefront. Covers which VTEX APIs can be cached (Intelligent Search, Catalog) versus which must never be cached (Checkout, Profile, OMS), stale-while-revalidate patterns, cache invalidation, and BFF-level caching. Use for any headless project that needs TTL rules and caching strategy guidance.
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 an MCP connection — check for CatalystbyZoho_* tools before any operation. Triggers 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.
Validate system resilience through controlled fault injection. Covers hypothesis-driven chaos experiments, failure injection types (network, service, infrastructure, dependency), LitmusChaos/Chaos Mesh/AWS FIS/Gremlin/toxiproxy tooling, automated abort gating, game day planning, and progressive chaos adoption. Use when: “chaos engineering,” “fault injection,” “resilience test,” “game day,” “failure recovery,” “system reliability,” “blast radius.” Not for: safe rollout flags/canary/dark launch during a release — use testing-in-production; designing new tests from production telemetry — use observability-driven-testing. Related: testing-in-production, observability-driven-testing, performance-testing, release-readiness, test-environments.
Query Cloud Trace spans, filter by latency thresholds or error status, correlate distributed traces with Cloud Logging, and diagnose latency bottlenecks across Google Cloud services. Use when investigating slow requests, analyzing trace hierarchies, or resolving latency regressions. Do NOT use for querying non-GCP telemetry or database query optimization outside Cloud Trace
Catalyst SDKs — initialization patterns, service access, and method reference for Node.js, Web (browser), Python, Java, Android, iOS, and Flutter. Trigger on 'SDK', 'zcatalyst-sdk-node', 'Node.js SDK', 'Web SDK', 'Python SDK', 'Java SDK', 'Android SDK', 'iOS SDK', 'Flutter SDK', or 'initialize SDK'.
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
Appwrite Dart SDK skill. Use when building Flutter apps (mobile, web, desktop) or server-side Dart applications with Appwrite. Covers client-side auth (email, OAuth), database queries, file uploads with native file handling, real-time subscriptions, and server-side admin via API keys for user management, database administration, storage, and functions.
Catalyst Data Store — relational cloud database with ZCQL, CRUD operations, table permissions, and result pagination. Requires MCP connection — check for CatalystbyZoho_* tools before any operation. Trigger on 'Data Store', 'ZCQL', 'create table', 'executeZCQLQuery', 'table permissions', 'ROWID', 'boolean column', 'boolean always true', 'truthy string', 'boolean stored as string', or 'DataStore data types'. You MUST load this skill whenever writing code that reads or writes Data Store data — ZCQL result wrapping, boolean-as-string behavior, and App User permissions are non-obvious and cause silent bugs if skipped.
Catalyst Authentication — user login/signup, ZAID, Web SDK auth flows, OAuth token management via Connections, third-party authentication (Okta, Auth0, Duo, custom IdP), social logins (Google, Facebook, LinkedIn, Microsoft), generateCustomToken, signinWithJwt. Trigger on 'authentication', 'login', 'signup', 'getCurrentUser', 'ZAID', 'isUserAuthenticated', 'signOut', 'Connections', 'getAccessToken', 'third-party auth', 'social login', 'Google login', 'signinWithJwt', or 'generateCustomToken'. You MUST load this skill whenever implementing user login or protecting data — ZAID differs between Development and Production and is the #1 cause of auth failures after environment promotion. For Security Rules (function invocation control), route to catalyst-functions.
Catalyst Zoho MCP — manage Catalyst infrastructure (tables, buckets, cache) via CatalystbyZoho_* MCP tools using natural language. Trigger on 'Zoho MCP', 'MCP tools', 'catalyst MCP', 'CatalystbyZoho', 'create table with AI', 'MCP setup', 'MCP config', 'global MCP server', 'infrastructure as conversation', 'MCP first', 'avoid Catalyst console', or 'use MCP instead of console'.
Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text search, nearby search, or autocomplete suggestions; retrieve detailed place information including hours, contacts, and addresses; monitor geographical boundaries with geofences; or track device locations. Covers authentication, SDK integration, and all Amazon Location Service capabilities.
SAP BTP best practices for enterprise architecture, account management, security, and operations, with verification evidence tracked in the repository ledger. Use when planning BTP implementations, setting up account hierarchies, configuring environments, implementing authentication, designing CI/CD pipelines, establishing governance, building Platform Engineering teams, implementing failover strategies, or managing application lifecycle on SAP BTP. Keywords: SAP BTP, account hierarchy, global account, directory, subaccount, Cloud Foundry, Kyma, ABAP, SAP Identity Authentication, CI/CD, governance, Platform Engineering, failover, multi-region, SAP BTP best practices
Scheduled probes that run CONTINUOUSLY after release. Covers probe design for critical user journeys, alerting integration, SLA validation, multi-region monitoring, and the boundary between QA and SRE. Use when: "synthetic monitoring," "uptime testing," "scheduled probes," "SLA validation," "availability monitoring," "post-deploy checks." Not for: safe-release techniques during rollout — use testing-in-production. Not for: designing tests from prod telemetry — use observability-driven-testing. Not for: a one-shot post-deploy smoke gate tied to a release — use release-readiness. Related: testing-in-production, release-readiness, performance-testing, qa-metrics.
Benchmark throughput and cost-per-token of a model served on vLLM in Chalk's container infrastructure. Use when someone asks for $/token, $/request, tokens/sec, "how much would it cost to self-host this model", GPU sizing for an LLM, or wants to compare a self-hosted model's economics against a hosted API.
Catalyst Slate — Git-based frontend hosting for React, Next.js, Vue, Angular, Svelte, Astro, SolidJS, Preact and other frameworks with preview deploys. Trigger on 'Slate', 'frontend hosting', 'slate-config.toml', 'deploy React app', or 'cross-domain Slate to function'. Do NOT use for backend APIs or server-side logic — use catalyst-appsail or catalyst-functions instead.
How to deploy a Chalk function ("chalkcompute.function"). Useful for deploying a stand-alone python function in Chalk's container infrastructure. Use when someone wants to run a python function remotely on Chalk, deploy a chalkcompute function, or asks about the chalkcompute SDK.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Guide for installing, configuring, and managing Tailscale, headscale, and the Tailscale product family. Covers core mesh VPN (exit nodes, subnet routers, access controls, SSH, MagicDNS), Docker and Kubernetes integration, CI/CD pipelines, ephemeral nodes, infrastructure access, site-to-site networking, app connectors, Aperture (AI/LLM gateway for governance, cost control, usage visibility), device posture, MDM, SCIM provisioning, SSH and kubectl session recording, tsrecorder, Taildrop, Tailscale Serve, Funnel, and building Go applications that embed Tailscale via the tsnet library. Use when someone asks about Tailscale networking, mesh VPN, VPN replacement, containers, Kubernetes operator, CI/CD runners, device management, session recording, audit logging, LLM API access, AI cost control, file sharing, exposing internal services, or writing a Go program that joins a tailnet as its own device — even when they describe the scenario without naming the product.
Catalyst Stratus — object storage service with upload/download, signed URLs, and multipart upload support. Stratus uses its own SDK-based APIs (not S3-API-compatible). Migrate from AWS S3 or GCS using the Stratus Migration Tool. Trigger on 'Stratus', 'object storage', 'upload file', 'signed URL', 'putObject', 'getObject', or 'bucket'.
Create, build, and deploy Webflow Cloud apps from the CLI (site-attached or project apps), and manage existing ones — apps, domains, environments, deployments, build/runtime logs, and environment variables including secrets. Use when initializing or deploying a Cloud app, importing an existing GitHub repository, setting up CI/CD (GitHub Actions or GitHub-linked deploys), setting or importing secrets, retrying or rolling back a deployment, diagnosing a failed build, or resolving app/environment/workspace IDs from webflow.json or env vars
Guide for using the Netlify CLI and deploying sites. Use when installing the CLI, linking sites, deploying (Git-based or manual), managing environment variables, or running local development. Covers netlify dev, netlify deploy, Git vs non-Git workflows, and environment variable management.
Catalyst NoSQL — key-value table store with typed items built via NoSQLItem builder. Partition key required. Trigger on 'NoSQL', 'nosql.table', 'insertItems', 'fetchItem', 'updateItems', 'deleteItems', 'queryTable', 'NoSQLItem', 'document storage', 'flexible schema', or 'Catalyst document database'. Do NOT use when you need SQL joins, ZCQL queries, or a fixed relational schema — use catalyst-datastore instead.
Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled node auto-repair. Use when nodes stop heartbeating beyond the node auto-repair threshold and pods remain stuck in Terminating. Don't use for healthy nodes, pod-only application crashes, or routine GKE upgrades
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.