Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Provides AWS CloudFormation patterns for Amazon RDS databases. Use when creating RDS instances (MySQL, PostgreSQL, Aurora), DB clusters, multi-AZ deployments, parameter groups, subnet groups, and implementing template structure with Parameters, Outputs, Mappings, Conditions, and cross-stack references.
Provides AWS CloudFormation patterns for VPC foundations, including subnets, route tables, internet and NAT gateways, endpoints, and reusable outputs. Use when creating a new network baseline, segmenting public and private workloads, or preparing CloudFormation networking stacks for application deployments.
Guides users through bioinformatics analysis on AWS HealthOmics. Covers analysis type selection (alignment, variant calling, QC, interpretation), workflow generation in Nextflow or WDL, container sourcing from public registries, infrastructure setup (S3, ECR, IAM), workflow registration, parameter preparation, execution, and monitoring. Use when a user wants to run any bioinformatics pipeline on HealthOmics, set up genomics infrastructure on AWS, create a new analysis workflow, or run existing tools like BWA, GATK, DeepVariant, FastQC, or similar on HealthOmics. Triggers include "HealthOmics", "bioinformatics", "genomics pipeline", "Nextflow", "WDL", "BWA", "GATK", "DeepVariant", "FastQC", "variant calling", "alignment", "RNA-seq", "whole genome sequencing", "ECR pull-through", "workflow registration", "run cache"
Provides comprehensive guidance for Azure Storage including blob storage, file shares, queues, and storage account management. Use when the user asks about Azure Storage, needs to store data in Azure, configure Azure Storage, or work with Azure storage services.
Provides comprehensive guidance for Huawei Cloud ECS including instance creation, configuration, security groups, and ECS management. Use when the user asks about Huawei Cloud ECS, needs to create ECS instances, configure ECS, or manage Huawei Cloud compute resources.
Deployment patterns from Kubernetes to serverless and edge functions. Use when deploying applications, setting up CI/CD, or managing infrastructure. Covers Kubernetes (Helm, ArgoCD), serverless (Vercel, Lambda), edge (Cloudflare Workers, Deno), IaC (Pulumi, OpenTofu, SST), and GitOps patterns.
Build type-safe D1 databases with Drizzle ORM for Cloudflare Workers. Includes schema definition, migrations with Drizzle Kit, relations, and D1 batch API patterns. Prevents 12 errors including SQL BEGIN failures. Use when: defining D1 schemas, managing migrations, writing type-safe queries, implementing relations or prepared statements, using batch API for transactions, or troubleshooting D1_ERROR, BEGIN TRANSACTION, foreign keys, migration apply, or schema inference errors. Prevents 12 documented issues: D1 transaction errors (SQL BEGIN not supported), foreign key constraint failures during migrations, module import errors with Wrangler, D1 binding not found, migration apply failures, schema TypeScript inference errors, prepared statement caching issues, transaction rollback patterns, TypeScript strict mode errors, drizzle.config.ts not found, remote vs local database confusion, and wrangler.toml vs wrangler.jsonc mixing. Keywords: drizzle orm, drizzle d1, type-safe sql, drizzle schema, drizzle migrations, drizzle kit, orm cloudflare, d1 orm, drizzle typescript, drizzle relations, drizzle transactions, drizzle query builder, schema definition, prepared statements, drizzle batch, migration management, relational queries, drizzle joins, D1_ERROR, BEGIN TRANSACTION d1, foreign key constraint, migration failed, schema not found, d1 binding error
Comprehensive skill for interacting with Grafana's HTTP API to manage dashboards, data sources, folders, alerting, annotations, users, teams, and organizations. Use when Claude needs to (1) Create, read, update, or delete Grafana dashboards, (2) Manage data sources and connections, (3) Configure alerting rules, contact points, and notification policies, (4) Work with folders and permissions, (5) Manage users, teams, and service accounts, (6) Create or query annotations, (7) Execute queries against data sources, or any other Grafana automation task via API.
Manage CloudRobo inference services — deploy a model into a managed inference service, list/query deployed services and their logs, start/stop a running service, update or delete a service, and orchestrate the 'wait-deploy' convenience flow that polls a service until it finishes deploying. Inference services consume models produced by cloudrobo-train and are consumed by robo-dispatcher when dispatching embodied tasks. Triggers include: infer, inference, model deployment, deploy model, inference service, service deployment, start inference, stop inference, service logs, wait-deploy, model serving, 推理, 推理服务, 模型部署, 部署模型, 推理服务管理, 服务日志, 模型服务.
Secures SaaS apps (Microsoft 365, Google Workspace, Salesforce, Slack) via CASB/SSPM deployment, conditional access policies, OAuth app governance, and session-level DLP controls enforcing identity verification and device compliance. Use when adding MFA/device-compliance conditional access, discovering shadow IT, governing OAuth consent grants, or applying session controls to sensitive SaaS data.
Review dead letter queue implementations for completeness using the Lenses MCP server. Checks DLQ topic existence, configuration, monitoring, metadata preservation, retry logic, reprocessing paths and connector DLQ alignment. Use when user says "review dead letter queues", "check DLQ setup", "DLQ audit" or asks about error handling, message failures or reprocessing. Do NOT use for reprocessing DLQ messages or managing consumer offsets.
Write, validate and run KubeSense SPL — the piped log query language — via validate-spl and execute-spl. Covers the storage-name field contract that inverts every other KubeSense surface, log_processed attributes, the command and aggregation vocabulary, and why an SPL query can compile and still fail.
Publish a local file (HTML report, PDF, image, dataset sample, build output) to Lightning AI and get a durable, public lightning.ai/artifacts/ link that never expires and renders inline in the browser. Also lists the artifacts drive, unpublishes (revokes) links and deletes the files behind them, all through the `lightning` CLI (`lightning-sdk` package) with `lightning login` or an API key, no code. Use when the user wants to share a file, a generated one-pager, or an agent-made artifact as a permanent URL, hand a file to a teammate or CI job, see or revoke existing shared links, or asks to "get a public / shareable link for this file".
Manage Lightning AI Studios (cloud dev machines with CPUs/GPUs) - create, start, stop, delete studios, switch machine types, run commands in them (including long detached runs with live progress tracking), upload/download files, and SSH in. Use when the user wants to work with lightning.ai Studios, needs a cloud GPU dev box, or asks to run something "on a studio". Also load it before launching or resuming any detached run on a Studio, even one driven by your own helper scripts, a handoff note or the summary of a compacted conversation, and load it again after a compaction; every such run needs the live progress bar from lightning-jobs/progress.py.
Use when a project contains okteto.yaml or okteto.yml, or when the user mentions Okteto, dev environments, or an okteto command. Also use before running kubectl, helm, or docker build in a repo that has an Okteto manifest; when okteto up hangs or seems stuck; when parallel git worktrees collide over the same environment; or when deciding whether okteto destroy or okteto namespace delete is safe to run.
Use when the user describes a broken or unhealthy Okteto environment. Triggers on phrases like: "service is crashing", "service keeps restarting", "service won't start", "environment is broken", "deployment is failing", "pods are stuck", "pods are not ready", "pods are pending", "CrashLoopBackOff", "OOMKilled", "ImagePullBackOff", "Evicted", "what's wrong with my service", "debug my environment", "why won't it start", "something's wrong", "logs show errors", "service isn't responding", "my code changes aren't showing up", "file sync is stuck". Also triggers if the user pastes kubectl or okteto output showing unhealthy pod states.
Optimize cloud infrastructure costs through FinOps practices, commitment discounts, right-sizing, and automated cost management. Use when reducing cloud spend, implementing budget controls, or establishing cost visibility across AWS, Azure, GCP, and Kubernetes environments.
Turns kube-bench output into a finished CIS Kubernetes Benchmark audit: interpreting PASS/FAIL/WARN per control, judging which failures are genuine on a managed cluster, writing remediation, and packaging evidence for SOC 2 or PCI DSS. Use when conducting a scheduled compliance audit, triaging kube-bench results, deciding which controls are not applicable on EKS, GKE, or AKS, or producing hardening evidence for an auditor. Keywords: CIS Kubernetes Benchmark, control plane, remediation, compliance evidence, SOC 2, PCI DSS, managed cluster exception. Do not use for installing and running the tool - use benchmarking-kubernetes-with-kube-bench.
How to write, test, and deploy an app with Prisma Composer (`@prisma/composer`): declare services with `compute()` and typed dependencies, define RPC contracts, compose Modules, declare the service input (config and secrets as one schema, read back with `input()`), compose the ready-made cron/storage/streams Modules, provision a raw S3-compatible object-store bucket with `bucket()`, find extensions (npm packages named `prisma-composer-*`), test with `mockService`/`bootstrapService`, run the whole app locally with `prisma-composer dev` and tail its logs with `prisma-composer log`, and deploy with `prisma-composer deploy` (stages, destroy). Use when building a Prisma App, wiring a service dependency, adding a Postgres database, adding scheduled jobs / blob storage / event streams / a raw bucket, writing tests for composed services, running an app locally, reading its logs, or deploying/tearing down an environment. Triggers on "prisma composer", "@prisma/composer", "prisma app", "compute()", "service.load()", "module()", "contract()", "mockService", "bootstrapService", "prisma-composer dev", "prisma-composer log", "prisma-composer deploy", "--stage", "--fresh", "--tail", "prisma-composer destroy", "prisma-composer-", "bucket()".
Structured workflows for investigating production issues in Honeycomb — the sequence of tool calls (context priming, broad query, BubbleUp, trace analysis, verification) and how to chain results between steps to reach root causes. Trigger phrases: "investigate production issue", "debug latency spike", "find root cause", "use BubbleUp", "analyze traces", "debug an outage", "why is my API slow", "errors are increasing", "health check", "SLO burning", or any request to investigate or debug production problems.
Expert in migrating Apache Solr collections to OpenSearch indexes. Translates Solr XML/JSON schemas to OpenSearch mappings and converts Solr syntax (Standard, DisMax, eDisMax) into OpenSearch DSL. Provides sizing for nodes, shards, and JVM heap. Provides guidance auf authentication migration from Solr to OpenSearch. Uses the AWS Knowledge MCP Server for accurate, up-to-date OpenSearch and AWS service information.
Design and build SuperPlane workflow canvases from requirements. Translates workflow descriptions into canvas YAML with triggers, actions, edges, and expressions. Use when the user wants to create a new workflow, build a canvas, design a pipeline, or wire up actions. Triggers on "build canvas", "create workflow", "design pipeline", "automate".
Full-stack application guidance for TanStack Start, including server functions, middleware, deployment, and framework adapters. Use when a project uses TanStack Start or when the task needs its setup, implementation, debugging, testing, migration, or integration guidance.
Provides comprehensive guidance for Terraform infrastructure as code including resource definition, state management, modules, and cloud provider integration. Use when the user asks about Terraform, needs to define infrastructure as code, manage cloud resources, or work with Terraform modules.
Operate and troubleshoot the MT5 tick collection system. HOST MOVED 2026-08-07 - MT5 now runs on the FXView VPS (Windows scheduled tasks, C:\odb-tickrings), NOT <gpu-host>/Linux-Wine/systemd. EA, ring format, and gap-detection reasoning are unchanged. Covers gap detection, restart recovery, and daily ops
Upgrades Flutter's Android SDK dependency to a new Android API version (or preview/canary release) in packages.txt, verifies CIPD tag uniqueness, and packages/uploads the binaries using create_cipd_packages.sh across macOS, Linux, and Windows. Use whenever a user wants to pick up a new version of Android or upload Android SDK packages to CIPD.
Operate Woodpecker CI from installation through production troubleshooting: configure servers and agents, connect Forgejo/Gitea or another forge, write and validate pipelines, manage secrets and plugins, use Docker or Kubernetes backends, run the CLI, and diagnose failed builds. Use when setting up, administering, or debugging Woodpecker CI. Do not use this skill for unrelated requests; route to the nearest named specialist.
Remediate GitHub Actions action findings identified by the action-audit skill. Applies the appropriate fix per action type — `@main` ref for internal `bitwarden/` actions, full SHA with inline version comment for external actions, or full replacement — across selected repos and creates draft PRs. Run the action-audit skill first to identify findings before using this skill. <example> User: Go ahead and fix the unpinned actions from the audit Action: Trigger action-remediate to apply fixes and create PRs </example> <example> User: Replace tj-actions/changed-files with the safe version across those repos Action: Trigger action-remediate to swap the action and create PRs </example>
Add OpenTelemetry traces to an AG2 `Agent` via `TelemetryMiddleware` (`ag2.middleware.builtin`). Emits spans for the full turn, each LLM call, each tool execution, and each human-input request, following the OpenTelemetry GenAI semantic conventions. Compatible with any OTLP backend — Jaeger, Grafana Tempo, Datadog, Honeycomb, Langfuse. Use when the user wants production-grade traces, latency analysis, token-usage attribution, or to ship telemetry into an existing observability stack.
arkcli model query and foundation model service activation capabilities: list, search, and get details of Volc public foundation models, and activate model services explicitly requested by the user (`arkcli models activate`); Volc also supports TTFT/TPOT performance rankings, latency trends, and input length comparisons. Activating an existing foundation model service is not the same as deploying/creating an Endpoint and must not be turned into `+deploy`. Prefer the product command `arkcli models ...` over calling the Raw API directly. Anti-trigger: when the user's ultimate goal is to create/deploy an Endpoint, this skill takes on a bounded read-only candidate query, and the owning skill is determined by the creation path: ordinary product creation goes to arkcli-deploy; when the user explicitly requests raw CRUD / CI / unguarded `infer endpoint create`, it goes to arkcli-infer-endpoint. Candidates first run `models search ... --size 10 --format json`; successful complete results are reused directly, empty results and capture defects are recovered in a bounded way per the reference, and the live-returned `name` is combined with a non-empty `primary_version` into a complete ID that can be passed directly to `--model`; do not pull the full list, treat a bare family name as a deployable ID, or append `models get` for each candidate. Note: querying/managing self-uploaded or fine-tuned custom models (`cm-xxx`) under the account goes to arkcli-custommodel.
Expert knowledge for Azure Anyscale On Azure development including limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when registering AKS as Anyscale clouds, wiring ACR images, enabling Private Link/RBAC, ARM-based deployments, or region checks, and other Azure Anyscale On Azure related development tasks. Not for Azure Databricks (use azure-databricks), Azure Kubernetes Service (AKS) (use azure-kubernetes-service), Azure Machine Learning (use azure-machine-learning), Azure HDInsight (use azure-hdinsight)
Expert knowledge for Azure Application Network development including decision making, and configuration. Use when enabling App Network logs, Azure Monitor metrics, AKS/App Gateway versioning, or upgrade compatibility, and other Azure Application Network related development tasks. Not for Azure Virtual Network (use azure-virtual-network), Azure Virtual Network Manager (use azure-virtual-network-manager), Azure Networking (use azure-networking), Azure Application Gateway (use azure-application-gateway).
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.