Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Use when creating Makefiles for process lifecycle management with PID tracking, logging, and status monitoring. Triggers on: 'use makefile mode', 'makefile', 'create makefile', 'process management', 'background jobs', 'start/stop services'. Full access mode - can create/modify Makefiles.
This skill should be used when the user asks to automate Azure ML and Azure Data Factory production workflows. PROACTIVELY activate for: (1) Azure ML code asset registration, azure-ai-ml SDK, AML code versions, `result.version`, requested-vs-actual versions, (2) ADF to Azure ML orchestration, ADF WebActivity, managed identity blob reads, `connectVia`, managed VNet IR, (3) code asset version pointer blobs, latest.json contracts, training/scoring code version propagation, (4) private storage firewalls, Microsoft-hosted CI agents, temporary network rules, storage data-plane smoke tests, (5) marshmallow<4 pinning, AML SDK import failures, runtime validation for Azure ML infrastructure. Provides: operationally safe Azure ML + ADF automation patterns.
NetBox Branching plugin — create isolated branch schemas for safe change staging, review, and merge. Use when working with branch lifecycle, the X-NetBox-Branch header, async provisioning/sync/merge jobs, conflict resolution, or Change Request integration.
How to use NetBox's configuration template system for generating device configs. Covers Jinja2 templates, config contexts, template rendering API, and common patterns. Use when building config generation workflows, automating device provisioning, or integrating NetBox with config management tools.
Configure and operate Orb Agent for automated network discovery into NetBox. Use when writing agent.yaml configs, setting up network/device/SNMP/worker discovery backends, deploying Orb Agent containers, managing policies and secrets, or troubleshooting discovery pipelines.
NetBox Data Exchange (NDX) — a curated catalog of infrastructure component metadata. The device/module/rack type definitions are open to the world (browse + manual YAML download); the "enrichment data" (lifecycle dates, thermal, environmental, operational, platform/NOS, observability protocol metadata) and the built-in NDX features in NetBox Cloud/Enterprise are commercial. Use when consuming enrichment data via the API, running EOL/lifecycle analyses, importing device types, or understanding how NDX data is structured.
Audit and review NetBox data model design choices. Use when evaluating site hierarchy, IPAM organization, device modeling, tenancy patterns, custom field vs tag decisions, naming conventions, and extensibility strategy. Identifies modeling anti-patterns and suggests improvements aligned with NetBox best practices.
Use when adding service-wide Spring Boot 3 Actuator, Micrometer metrics, distributed tracing, OpenTelemetry export, structured logging, health probes, dashboards, or alerts. Combine with ai-observability only for Spring AI-specific token, prompt, and model telemetry.
Detects and prevents manual edits to release-please managed files (CHANGELOG.md, version fields in package.json, pyproject.toml, Cargo.toml). Provides conventional commit templates. Use when editing changelogs, version bumps, release files, or when user mentions "release", "changelog", "version bump", or "conventional commits".
Use this skill when releasing a new version of a GitHub project, covering the full process of version number management, CHANGELOG syncing, writing release notes, creating tags, CI build monitoring, release verification, and history cleanup. Applies to any GitHub-based software project such as desktop apps, CLI tools, web apps, and libraries/SDKs. Triggers when the user mentions "发布" (release), "release", "打 tag" (tagging), "新版本" (new version), "更新版本号" (updating the version number), "写 release notes" (writing release notes), "发布失败了" (release failed), "CI 挂了" (CI is down), "Actions 配额告急" (Actions quota running low), "短时间内多次发版" (multiple releases in a short time), "monorepo", "批量打包" (batch packaging), "多 skill 发布" (multi-skill releases), "skill zip", "专家套件 zip" (expert suite zip). Also used to reject the anti-pattern of treating a release as a CI verification mechanism ("打 tag 看一下", just tag it and see). Do not use for non-GitHub projects (such as pure GitLab / Gitea projects) or manual release scenarios that require no CI.
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastructure as code, deployment automation, and monitoring. Use when setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes
Guided entry point for using Sentry through your agent. Orients you to your current setup and, for a new project, sets up Sentry end to end with sane defaults — provision a project, install the SDK (errors, tracing, and whatever it enables by default), and confirm real telemetry reaches Sentry. Routes other intents (adding more signals, fixing issues) to the right skill.
Use when preparing server provisioning plans, IaC drafts, SSH hardening, users, firewalls, backups, monitoring, and rollback. Dry-run by default; do not create, mutate, or destroy production servers without explicit approval.
Use when choosing hosting/server architecture for a site or app: static hosting, VPS, PaaS, CDN, region, cost assumptions, scaling, security, and ops tradeoffs. Advisory only; do not provision servers or create paid resources without explicit approval.
Use when planning SSL/TLS, HTTPS redirects, HSTS, security headers, CSP, cookie flags, backups, monitoring, and basic launch hardening. Dry-run first; do not mutate production server, DNS, certificates, or secrets without explicit approval.
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.
Use when the user needs to perform real UCloud resource operations through the official UCloud CLI, including viewing, creating, updating, or deleting cloud hosts, networks, EIPs, load balancers, and databases. Also use this skill when the user wants to deploy a web app or take a service live on UCloud, even if they describe a deployment task rather than naming a specific cloud product.
Query and answer questions about Volcengine API specifications. Trigger this skill whenever a user asks about Volcengine API parameters, error codes, request methods, enum values, required fields, response structures, pagination, parameter dependencies, or API comparisons — even if they don't explicitly say "API". Typical triggers include questions like "What parameters does DescribeInstances have?", "What values does Status support?", "What does InvalidInstanceId.NotFound mean?", "Does Volcengine have a batch tag deletion API?", "Which APIs does ECS support?", "How do I pass parameters to CreateDatabase?", "Is ChargeType required?", "What fields does DescribeInstances return?", "How do I paginate instance lists?", "What's the difference between these two APIs?", "RunInstances returns InvalidParameterValue". When the user needs runnable SDK code, hand off to the volcengine-sdk-generator skill. When the user needs CLI-based operations, hand off to the volcengine-cli skill. Supports both Chinese and English prompts.
Zyte account work that has no Zyte MCP tool: credentials (set up, log in, get an API key, or a blocked site); deploying or pushing a project to Scrapy Cloud, and saving a job's full items, log or requests to a file (Zyte MCP results are truncated); Zyte API plan pricing (plans, tiers, discounts, commitments, free credit); how-to and docs questions about any Zyte product or account/billing, from docs.zyte.com. Scrapy Cloud jobs, recorded usage and per-website prices are Zyte MCP tools; use this skill for them only when those tools are missing, to tell the user how to connect the Zyte MCP. NOT for writing/debugging spiders locally (scrapy-extra).
Exploit CI/CD pipeline misconfigurations and OIDC federation weaknesses across GitHub Actions, GitLab CI, and Jenkins—poisoned workflows, secret exfiltration, runner compromise, overly broad OIDC trust policies, build artifact poisoning, and credential theft. Use when pentesting CI/CD infrastructure, assessing OIDC federation trust boundaries, reviewing pipeline security posture, or exploiting a path from repository access to cloud credentials.
Add a custom domain to a Temps project and provision an automatic SSL/TLS certificate via Let's Encrypt, driven entirely from the `@temps-sdk/cli` CLI. Handles subdomains, apex domains, HTTP-01 and DNS-01 challenges, wildcard domains, and domains served through a Cloudflare Tunnel (no certificate, no open ports). Use when the user wants to: (1) Add a custom domain to their Temps app, (2) Set up HTTPS/SSL for a deployment, (3) Point their own domain at a Temps project, (4) Add a wildcard domain, (5) Configure DNS for Temps, (6) Expose an app on a worker behind NAT through a tunnel. Triggers: “add custom domain”, “point my domain at temps”, “set up ssl”, “https for my app”, “wildcard domain”, “add domain to project”, “cloudflare tunnel”, “expose app without open ports”.
Provision dedicated AI agents on AgentBox via x402 payment ($5 USDC on Solana). Use when creating cloud instances running OpenClaw AI gateways with HTTPS and web terminal. Requires Node.js and a Solana wallet.json with USDC funds. Covers: provisioning new instances, polling status, interacting via OpenAI-compatible chat completions, extending, and listing instances.
Use when the user needs to generate a log collection configuration file (OpenTelemetry Collector or Elastic Beats / Filebeat) that writes logs to Alibaba Cloud Elasticsearch or self-managed Elasticsearch. Covers file logs, log API ingestion (OTLP / HTTP webhook), and Kafka log topics. Also matches natural requests such as: write a filebeat.yml, generate an otelcol config, send logs to ES, collect nginx or Java application logs to Elasticsearch, or sync Kafka logs to ES. Always output one configuration file targeting Elasticsearch; never mix technology stacks or emit non-ES outputs.
Use Apple’s `container` CLI on Apple silicon macOS for Linux containers, OCI image builds, registries, volumes, networks, port forwarding, host access, persistent `container machine` Linux environments, and experimental local Kubernetes clusters. Use this skill whenever the user asks to replace Docker Desktop with Apple Container, run Linux commands on macOS, build/run/inspect Apple containers, debug Apple Container service/network/build failures, use Container Machines, or use `container k8s`.
CloudBase auth provider configuration and login-readiness guide. This skill should be used when users need to inspect, enable, disable, or configure auth providers, publishable-key prerequisites, login methods, SMS/email sender setup, or other provider-side readiness before implementing a client or backend auth flow.
Use when an ECS Service Connect DNS alias returns IPv6 addresses and an IPv4-only Fargate task cannot connect with `network is unreachable` / `EAI_AGAIN` etc. Typical symptoms are OTel Collector → Tempo OTLP gRPC and Fargate → Service Connect HTTP/gRPC communication suddenly failing. It is fine to start from ECS / Fargate / Service Connect / OTLP / IPv6 dual-stack connection failures even if the user has not identified IPv6 as the cause.
Assess whether a project is ready for cloud-native deployment. Evaluates statelessness, config, scalability, and produces a readiness score (0-12). Use when user asks about containerization readiness, Docker/Kubernetes compatibility, deployment feasibility, whether their app can run in containers or the cloud, or wants a pre-deployment assessment. Also triggers on "/cloud-native-readiness".
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Includes critical guidance on choosing between Agents SDK (infrastructure/state) vs AI SDK (simpler flows). Use when: deciding SDK choice, building WebSocket agents with state, RAG with Vectorize, MCP servers, multi-agent orchestration, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors.
Build with D1 serverless SQLite database on Cloudflare's edge. Use when: creating databases, writing SQL migrations, querying D1 from Workers, handling relational data, or troubleshooting D1_ERROR, statement too long, migration failures, or query performance issues.
Build semantic search with Cloudflare Vectorize V2 (Sept 2024 GA). Covers V2 breaking changes: async mutations, 5M vectors/index (was 200K), 31ms latency (was 549ms), returnMetadata enum, and V1 deprecation (Dec 2024). Use when: migrating V1→V2, handling async mutations with mutationId, creating metadata indexes before insert, or troubleshooting "returnMetadata must be 'all'", V2 timing issues, metadata index errors, dimension mismatches.
Build durable, long-running workflows on Cloudflare Workers with automatic retries, state persistence, and multi-step orchestration. Supports step.do, step.sleep, step.waitForEvent, and runs for hours to days. Use when: creating long-running workflows, implementing retry logic, building event-driven processes, coordinating API calls, scheduling multi-step tasks, or troubleshooting NonRetryableError, I/O context, serialization errors, or workflow execution failures. Keywords: cloudflare workflows, workflows workers, durable execution, workflow step, WorkflowEntrypoint, step.do, step.sleep, workflow retries, NonRetryableError, workflow state, wrangler workflows, workflow events, long-running tasks, step.sleepUntil, step.waitForEvent, workflow bindings
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, AI agent development, or migrating existing/GitHub apps that need VPC access to MySQL/PostgreSQL/Redis. Also use when diagnosing CloudRun container deploy failures (deploy_failed, readiness/probe failed, image won't start, docker.io pull loops) or a deploy stuck behind a running deploy task. For stateless HTTP services, prefer HTTP cloud functions.
Set up a "software factory" that turns labelled GitHub issues into reviewed pull requests, using coding agents (Claude Code, Codex or any other CLI agent) that run in Upstash Box sandboxes and are started by GitHub Actions. Use this whenever someone wants to build, recreate, extend or debug an issue-to-PR pipeline, a pool of background coding agents, "agents that work on my GitHub issues", a label-triggered agent workflow, or anything that combines Upstash Box with coding agents and GitHub, even if they never say "software factory". Also use it to add a repo, an agent type, workers, a model or effort setting, or a worker image (snapshot) to a factory built this way.
Deploys a Software-Defined Perimeter per the CSA v2.0 specification, configuring Single Packet Authorization, mutual TLS, and SDP controller/gateway components to enforce zero trust network access. Use when building or hardening zero trust network architecture, implementing SPA-based "invisible" infrastructure that cloaks services from unauthenticated scanning, or meeting compliance requirements for zero trust network access.
Deploys and operates Falco with the modern eBPF driver in Kubernetes and Docker, covering driver selection, Helm installation, output channels, and the built-in ruleset that detects container escape, namespace abuse, privileged mounts, and anomalous syscalls. Use when standing Falco up on a cluster, choosing between the eBPF and kernel-module drivers, routing Falco alerts into a SIEM or Falcosidekick, or upgrading an existing deployment. Keywords: Falco, modern_ebpf, kernel module, Helm, Falcosidekick, runtime security, syscall. Do not use for authoring individual escape rules - use detecting-container-escape-with-falco-rules.
Dibbla CLI for scaffolding projects, deploying apps, managing apps/databases/secrets and multi-service `dibbla.yaml` manifests, authoring and operating workflows (slim YAML; `wf execute` sync/`--async`/`--follow`; `wf logs <runId>`, `wf runs list/output` for run monitoring), building Go workers via `github.com/dibbla-agents/sdk-go`, and running `dibbla-task.yaml` pipelines (`dibbla run`).
Production-grade Docker containerization for Python and Node.js applications. This skill should be used when users ask to containerize applications, create Dockerfiles, dockerize projects, or set up Docker Compose. Auto-detects project structure, analyzes .env for secrets, validates security, and generates tested Dockerfiles.
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.