Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Complete Python Cloudflare deployment system. PROACTIVELY activate for: (1) Python Workers with Pyodide, (2) FastAPI on Workers, (3) Cloudflare Containers for heavy compute, (4) Service bindings (RPC), (5) Environment variables in Workers, (6) Cold start optimization, (7) Workflows for durable execution, (8) GPU containers for AI. Provides: Worker code patterns, wrangler config, Dockerfile templates, FastAPI integration. Ensures edge deployment with proper architecture choices.
Use this skill to wire `adb` reliably into CI — bash idioms, exit codes, parallel device fan-out with `xargs -P`, port forwarding (`adb forward` LOCAL REMOTE vs `adb reverse` REMOTE LOCAL — opposite argument order, the most common scripting bug), test-runner status codes (`-1` error, `-2` failure, `-3` ignored, `-4` assumption-failure), `am instrument -w -r` with `--num-shards` / `--shard-index`, the `timeout` wrapper (since `adb -t` is transport-id, NOT timeout), retry-on-transient-error with `adb kill-server`, idempotent setup (`pm clear` + animations to 0), `trap` cleanup, capture-on-failure (`screencap` + `logcat -d`), and Test Orchestrator wiring through `androidTestUtil("androidx.test:orchestrator:1.6.1")` (NOT `androidTestImplementation`). If the user mentions "adb forward vs reverse argument order", "am instrument exit code 0 even on failure", "adb timeout flag", "retry adb kill-server", "trap cleanup adb", or "androidTestUtil orchestrator", use this skill.
Operate the observability stack that deploys as one unit: Prometheus scrape configuration, recording and alerting rules, relabeling, retention, and high availability; OpenTelemetry Collector pipelines (receivers, processors, exporters, sampling, trace/span correlation); and Loki ingest, LogQL, retention, and label design — with a bundled read-only telemetry-check script for Prometheus rule sanity and scrape-target reachability. Use when running, tuning, or troubleshooting a Prometheus, OpenTelemetry Collector, or Loki deployment, or reviewing the collection/ingest/retention layer, including bounded PromQL and LogQL query construction, semantic review, and no-data diagnosis. Do not use for observability strategy, SLI/SLO design, or paging policy (that is platform-engineering), Grafana dashboards, panels, and Grafana-side alerting (that is grafana), or Tempo/tracing operations, which remain deferred to a future named-tool skill.
One-stop Cloudflare setup for TinyShip: Workers + D1/Hyperdrive + R2 + Email Sending + Turnstile. Use when the user asks to "set up cloudflare", "all-in cloudflare", "deploy to workers", "configure d1", "configure r2", "cf setup", "cloudflare full stack", or wants to use the Cloudflare ecosystem for their TinyShip project.
Expert guidance on building and deploying apps to WendyOS edge devices. Use when developers mention: (1) Wendy or WendyOS, (2) wendy CLI commands, (3) wendy.json or entitlements, (4) deploying apps to edge devices, (5) remote debugging Swift on ARM64, (6) NVIDIA Jetson or Raspberry Pi apps, (7) cross-compiling Swift for ARM64.
Use this skill when the user asks to “analyze network traffic with Wireshark,” “capture packets for troubleshooting,” “filter PCAP files,” “follow TCP/UDP streams,” “detect network anomalies,” “investigate suspicious traffic,” or “perform protocol analysis.” It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark.
Create an agent platform instance in DMS via Alibaba Cloud OpenAPI. Supports Simple Mode and Advanced Mode. Use this skill when the user wants to provision, deploy, or set up a new Dify instance on Alibaba Cloud DMS.
Alibaba Cloud FinOps Resource Inspection Skill. Performs cost-oriented health inspection across all regions of an Alibaba Cloud account. Scans ECS, RDS, EIP, Cloud Disks, Load Balancers (CLB/ALB/NLB), and NAT Gateways to identify underutilized and idle resources. Triggers: "FinOps巡检", "成本巡检", "资源利用率检查", "idle resource detection", "cost optimization", "finops inspection", "资源浪费检查", "闲置资源检测".
Build, manage, and operate APIs with Amazon API Gateway (REST, HTTP, and WebSocket). Triggers on phrases like: API Gateway, REST API, HTTP API, WebSocket API, custom domain, Lambda authorizer, usage plan, throttling, CORS, VPC link, private API. Also covers troubleshooting API Gateway errors (4xx, 5xx, timeout, CORS failures) and IaC templates containing API Gateway resources. For general REST API design unrelated to AWS, do not trigger.
Adds the Azure SQL Database container as a sidecar service in an existing Docker Compose stack or Dev Container. Use when wiring the local Azure SQL Database engine into compose or devcontainer.json, when an app needs a SQL backend via a service name (not localhost), or for prompts like "add SQL to my compose", "add a database service", "depends_on database", "devcontainer SQL sidecar", "compose healthcheck for SQL", "wait for the database before starting the app". Handles platform linux/amd64, the private registry login, the healthcheck wait-until-ready, and a one-shot init service that creates appdb (the engine does not auto-create databases). Not the SQL Server image. Prefer this for any compose or Dev Container SQL wiring.
Optimize CircleCI configuration for speed, reliability, and maintainability. Use when users ask to improve `.circleci/config.yml`, reduce CI runtime, tune caching/workspaces/parallelism, remove pipeline waste, or fix flaky pipeline behavior caused by configuration choices.
Lifecycle Center for DX Inspector and Builder Central. Use this skill first for four jobs: (A) list the orgs connected to DX Inspector; (B) connect a new org (sandbox or scratch, production, OrgFarm) as a deploy target; (C) connect or check the Lifecycle Center org, also written LifecycleCenter org, lifecycle-center, ALMDevOpsCenterHub, DevOps Center hub, or Hub org; (D) deploy, validate, or quick-deploy components that already exist in the user's org to a connected org, and poll a simple-deploy requestId. TRIGGER on: show, list, or pick connected orgs or environments; connect, add, log in to, or repair an org; connect the Lifecycle Center org; deploy, validate, or push components to another org, URL, org id, alias, or environment name. Short asks like "connect a new org", "which orgs can I deploy to", or "deploy to my sandbox" match. These deploys move components from the connected source org to another org, not local project files
Deploy, configure, and manage applications on the Fly.io platform using flyctl CLI, fly.toml configuration, Fly Machines, Fly Volumes, private networking, secrets, health checks, autoscaling, and GitHub Actions CI/CD. Use when deploying any application to Fly.io, writing or modifying fly.toml configuration, managing Fly Machines or Volumes, configuring networking (public services, private 6PN, Flycast, custom domains, TLS), setting secrets, configuring health checks, setting up autostop/autostart or metrics-based autoscaling, deploying with GitHub Actions, managing Fly Postgres databases, or preparing an app for production on Fly.io.
Reduces container attack surface by building application images on Google distroless base images that ship only the application runtime - no shell, package manager, or OS utilities - using multi-stage build patterns plus debugging and scanning techniques adapted to distroless. Use when hardening container images, cutting attack surface in a container architecture, or answering an assessment finding about bloated base images. Keywords: distroless, multi-stage build, no shell, nonroot tag, debug image, scratch, attack surface. Do not use for scanning an image for known CVEs - use scanning-docker-images-with-trivy.
Fine-tune a Kev decision model (open Jev-style System One model) on a user's own workload and serve it with calibrated probabilities. Interviews the user, finds existing Jev/TypeSafe questions or labelled data in their codebase, generates enough synthetic training data to measure a gain, trains and calibrates on Modal, scores against the released checkpoint, deploys a TypeSafe-compatible endpoint, and tears everything down. Use when someone wants noul/choice/score questions answered on their own domain (routing, triage, moderation, classification, scoring), wants calibrated confidence for automation thresholds, mentions Jev, TypeSafe, System One or Kev, or asks to fine-tune, evaluate, deploy or clean up Kev.
This skill should be used when the user asks to run isolated or untrusted code on Modal.com. PROACTIVELY activate for: modal.Sandbox, safe user code execution, coding playgrounds, named sandboxes, PTY sessions, filesystem snapshots, timeout and resource limits, egress policies, sandbox lifecycle cleanup, terminate(), and security review for code execution. Provides: sandbox security checklist, lifecycle and cleanup patterns, egress/resource-limit recipes, and snapshot/PTY usage examples.
This skill should be used when the user asks to work with Modal.com persistence or shared state. PROACTIVELY activate for: Modal Volumes, vol.commit, Dict, Queue, CloudBucketMount, S3 or GCS mounts, secret-backed storage credentials, model cache persistence, dataset staging, shared queues, distributed state, volume consistency, and storage troubleshooting. Provides: storage primitive selection matrix, commit/consistency patterns, mount configuration recipes, and troubleshooting checklists.
NVIDIA Sync desktop app. Manage remote connections to DGX Spark, DGX Station, and SSH Linux hosts. Features mDNS auto-discovery, manual IP, SSH config import, Tailscale, and automatic network switching. Includes Cluster Assistant, ConnectX-7 cluster topology, netplan validation, Resource Monitor (CPU / GPU / memory), and release notes. Launch VS Code, VS Code Insiders, Cursor, NVIDIA AI Workbench, and custom apps; supports port forwarding and SSH tunnels.
Write OpenTofu modules and tests for homelab infrastructure (infrastructure/modules/). Use when: creating new modules, writing or modifying .tftest.hcl test files, adding variables/outputs/resources, debugging test failures, or questions about tftest syntax. Triggers: "opentofu module", "terraform module", "tofu module", "create module", ".tftest.hcl", "tftest", "test my module", "module test", "infrastructure test", "variables.tf", "outputs.tf", "module testing", "assertion", "task tg:test", "test-config"
Query Prometheus API for cluster metrics, alerts, and observability data. Use when investigating cluster health, performance issues, resource utilization, or alert status. Triggers on questions like "what's the CPU usage", "show me firing alerts", "check memory pressure", "query prometheus for", or any PromQL-related requests.
Modern Python patterns for Modal.com serverless platform. PROACTIVELY activate for: (1) Modal function deployment, (2) Type-safe Modal with Pydantic, (3) Async patterns in Modal, (4) GPU workloads (ML inference, training), (5) FastAPI web endpoints on Modal, (6) Scheduled tasks and cron jobs, (7) Modal Volumes and storage, (8) Testing Modal functions with pytest, (9) Modal classes and lifecycle methods, (10) Parallel processing with map/starmap. Provides: Type hints patterns, Pydantic integration, async/await patterns, pytest testing, FastAPI integration, scheduled tasks, Volume usage, cost optimization, and production-ready examples following Python 3.11+ best practices.
Design, exercise, and evidence graceful degradation, disaster recovery, and restoration behavior across systems and dependencies. Covers failure-mode analysis, RTO/RPO decision records, restore testing, game days, failover drills, data integrity verification, and recovery communication. Do not use for live incident command or incident response; route to site-reliability-engineering for those. Do not use for infrastructure implementation details; route to platform-engineering.
Set up CI so every pull request gets a Testomat.io run scoped to the code it changes. One job runs after the deploy — it creates the run and launches the affected tests into it. Use when the user wants to integrate Testomat.io runs into a CI pipeline, create test runs per pull request, or set up change-aware testing that triggers affected tests from CI events.
This skill should be used when user asks to "use supabase CLI", "supabase init", "supabase start", "run migrations", "deploy edge functions", "manage Supabase project", or works with the supabase command-line tool for local development and project management.
Create, modify, and maintain Taskfiles following Task (https://taskfile.dev) best practices. Use when: (1) Creating new tasks or Taskfiles, (2) Modifying existing task definitions, (3) Adding new task includes, (4) Debugging task execution issues, (5) Questions about Taskfile syntax or patterns, (6) Running or understanding "task" commands, (7) Questions about available tasks or task namespaces. Triggers: "taskfile", "Taskfile.yaml", "task command", "task:", "create task", "add task", "task --list", "task tg:", "task inv:", "task wt:", ".taskfiles/", "how to run", "available tasks", "task syntax", "taskfile.dev" This skill covers the repository's specific conventions in .taskfiles/ and the root Taskfile.yaml.
Deploy applications and websites to Vercel with a claimable preview. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". No authentication required - returns preview URL and claimable deployment link.
Use this skill when controlling a VMOS Edge Android cloud phone through the Android Control API. If the current session also has `vmos-edge-container-api`, use `host_ip` and resolve the target `db_id` through the container APIs first. If this skill is installed alone, prefer `cloud_ip`; if `host_ip` and `db_id` are already known, the host route can also be used. If no IP is provided and local `cbs_go` is running, default `host_ip` to `127.0.0.1`.
Use this skill for safe, read-only queries of VMware infrastructure — no destructive operations exist in the codebase; a test enforces it. Directly handles: a one-glance cross-cluster health summary, object-centered VM/host/datastore investigation drill-downs (correlating surrounding infrastructure + recent events), a cross-vCenter "what needs attention now?" rollup, list VMs/hosts/datastores/clusters, active alarms, recent events, VM details. Always use vmware-monitor when the user asks to "list VMs", "check vSphere alarms", "show host status", "is anything on fire", "what needs attention now", "what is happening around this VM/host/datastore", "investigate this VM" — or needs read-only VMware info before making changes. Do NOT use for any write operations — this skill is read-only and has no code path that creates, modifies, or deletes a vSphere resource. For VM modifications use vmware-aiops, for networking use vmware-nsx, for metrics/capacity use vmware-aria. For load balancing/AVI/AKO use vmware-avi.
Operate Alibaba Cloud CloudMonitor Service (CMS) AgentLoop ContextStore by using aliyun CLI with api version 2024-03-30. Use when users mention CloudMonitor, CMS, AgentLoop, agent loop, context, memory, experience, ContextStore, context store, context library, memory library, experience library, or ask to create/query/update/delete stores, write/search/update/delete context records, manage store API keys, or debug aliyun cms ContextStore commands.
Diagnose and troubleshoot Alibaba Cloud NAS mount failures. Use when users encounter NAS mount errors on Linux or Windows, including NFS and SMB protocol mount failures, network connectivity issues, permission group misconfigurations, security group port blocks, or specific error codes like "mount.nfs No such device", "access denied by server", Windows system error 53/58/64/67/85/1231/1272/1312/3227320323, and auto-mount failures on boot. Covers both General Purpose NAS and Extreme NAS file systems. Also handles container (K8s/Docker) NAS mount issues, cross-VPC/cross-account mount problems, and ECS cloud assistant batch mount failures.
Chunked, compressed N-dimensional arrays for cloud storage with Zarr — parallel I/O, S3/GCS integration, and NumPy/Dask/Xarray compatibility. Use when storing or reading large N-D scientific arrays, streaming chunked data to/from cloud object stores, or building large-scale scientific computing pipelines. Part of the AlterLab Academic Skills suite.
Provides comprehensive guidance for Tencent Cloud CVM including instance creation, configuration, security groups, and CVM management. Use when the user asks about Tencent Cloud CVM, needs to create CVM instances, configure CVM, or manage Tencent Cloud compute resources.
Avoid designs that inflate bills on Cloudflare (Workers, static assets, KV, D1, R2, Durable Objects, Queues, Workers Logs), and choose a cost-effective approach. Use when designing what to deploy on Cloudflare, adding a Worker or binding, deciding how to serve pages or data, or writing loops or retries.
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.