Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Design and audit observability cost governance across logs, metrics, traces, events, profiling, session replay, analytics, retention, sampling, cardinality, dashboards, alerting, ownership, privacy redaction, budgets, and incident usefulness. Use when telemetry spend grows or observability needs to stay useful, safe, and cost-efficient.
Drive a PR or branch to green CI. Reads check status through tracker operations, pulls failed-step logs, classifies each failure (real bug, test bug, flake, infra), fixes the real ones in an isolated worktree with tests, pushes, and re-checks — iterating until every required check passes or a genuine blocker is reported. Never goes green by weakening tests or disabling checks.
Provide CI/CD best practices and pipeline templates for GitHub Actions and GitLab CI, recommending configurations based on project type (frontend, backend, fullstack, library, monorepo, mobile). Trigger when users ask about setting up CI/CD, automating builds, improving pipelines, or mention keywords like GitHub Actions, GitLab CI, pipeline templates, or deployment automation.
Use when developing BK-CI pipeline plugins, such as adding an Atom, writing `task.json`, defining inputs and outputs, handling multilingual runtimes, and debugging and publishing plugins. Prefer this when the user needs to work on the plugin itself rather than the executor or pipeline model.
Set up, inspect, link, and deploy Polpo projects using the current .polpo directory layout and CLI. Use for project bootstrap, project files, cloud linking, deployment, or deciding whether behavior belongs to Polpo OSS or Polpo Cloud. For agent design, runtime calls, Channels, integrations, or React UI, use the corresponding specialized Polpo skill.
Design and audit reliability incident learning, postmortems, incident timelines, contributing factors, action items, recurrence prevention, customer impact, status updates, error budget learning, operational follow-through, and blameless review. Use when outages, degraded service, data incidents, support spikes, or release failures need durable improvement instead of shallow postmortems.
Roots ecosystem implementation guide for Bedrock, Sage, Acorn, Trellis, @roots/vite-plugin, roots/wp-config, WP Packages, Trellis CLI, and first-party Acorn extension packages. Use when working on Roots-based WordPress projects, especially for Bedrock configuration and Composer-managed WordPress, Sage Blade templates/components/composers, Acorn booting/providers/routes, Blade rendering in WordPress, Trellis provisioning or deployment, Trellis GitHub Actions setup, WordPress package distribution, or Acorn packages such as acorn-mail, acorn-user-roles, acorn-post-types, acorn-prettify, acorn-fse-helper, acorn-llms-txt, and acorn-ai.
Software Composition Analysis (SCA) and container vulnerability scanning using Aqua Trivy to identify CVE vulnerabilities in dependencies, container images, IaC misconfigurations, and license compliance risks. Use when: (1) scanning container images and filesystems for vulnerabilities and misconfigurations, (2) analyzing dependencies for known CVEs across multiple languages (Go, Python, Node.js, Java, etc.), (3) detecting IaC security issues in Terraform, Kubernetes, and Dockerfile, (4) integrating vulnerability scanning into CI/CD pipelines with SARIF output, (5) generating a Software Bill of Materials (SBOM) in CycloneDX or SPDX format, (6) prioritizing remediation by CVSS score and exploitability.
SeaweedFS distributed storage. Covers filer, S3 API, replication, cloud tiers, and operations. Use when deploying SeaweedFS, configuring filer stores, exposing S3-compatible endpoints, or planning backup and security controls. Keywords: SeaweedFS, weed, filer, S3, object storage.
Servd (servd.host) — Craft-specialised managed hosting for Craft CMS. Covers git push-to-deploy with the optional servd.yaml build config, local → staging → production environments with uni-directional Project Config sync, the servd/craft-asset-storage plugin (S3-backed Flysystem volumes on the svdcdn.com CDN, off-server image transforms, Imager-X/ImageOptimize integrations), Servd's static caching (full vs tag-based purge, {% dynamicInclude %}, CSRF injection, cache-busting) and running Blitz alongside it in reverse-proxy mode, MariaDB/MySQL databases over an SSH tunnel, automatic + manual backups, the Dedicated Queue Runner, environment variables and secrets, the ephemeral load-balanced filesystem (Redis + remote volumes for runtime files), plugin/feature constraints, and Servd-vs-Craft-Cloud differences.
Guide users through creating Sindri extensions. Use when creating new extensions, understanding extension.yaml structure, validating extensions against schemas, or learning about extension installation methods (mise, apt, binary, npm, script, hybrid). Includes NEW capabilities system for project-init, authentication (multi-method API key + CLI auth), lifecycle hooks, and MCP integration. Helps with extension development, registry updates, and category assignment.
Transform product requirements into executable technical architecture. Use when users request: (1) Technical/system architecture design, (2) Tech stack selection, (3) Architecture from PRD, (4) Deployment strategy, (5) Architecture review. Provides workflows from requirements to deployment with tech stack templates. Triggers: architecture, tech stack, system design, deployment, infrastructure. | 将产品需求转化为技术架构。触发词：架构设计、技术架构、系统架构、技术选型、部署方案、基础设施。
Synchronize TinaCMS schema changes by regenerating local artifacts and committing them. Use when the Tina schema (tina/config.ts) has been modified, when adding new block types or collection fields, or when tinacms build fails with "Unable to seed" errors. Triggers on "sync tina", "rebuild tina", "tina schema changed", "regenerate tina artifacts", "tina lock file", or after any edit to tina/config.ts.
Use when working on the BK-CI Worker executor, such as task claiming and execution, plugin running, log reporting, environment variable passing, and artifact archiving. Prefer this when the user needs to change the Worker execution path rather than plugin definitions or scheduling policies.
Extends Fastly VCL with loops, functions, constants, macros, conditionals, and includes via XVCL — a VCL transpiler that compiles .xvcl files into standard VCL. Use when writing VCL for Fastly, working with .xvcl files, generating repetitive VCL (multiple backends, routing rules, headers) with loops, defining reusable VCL functions with return values, using compile-time constants instead of magic numbers, or writing any Fastly VCL configuration. XVCL syntax is not in training data so this skill is required. Also applies when writing and testing VCL locally (compile with `uvx xvcl`, test with falco), reducing VCL code duplication, splitting large VCL into modular includes, or doing any VCL development task for Fastly — even without explicitly mentioning XVCL.
Scaffold production-ready AI agents on Google's Agent Development Kit (ADK): ReAct-style single agents, multi-agent orchestration (Sequential/Parallel/Loop), tool wiring, evaluation, and optional Vertex AI Agent Engine deployment. Use when building, scaffolding, or deploying ADK agents on Google Cloud, or when wiring ADK tools and orchestration patterns. Trigger with "build an ADK agent", "scaffold an agent on ADK", or "deploy to Agent Engine".
Perform SysOM deep diagnosis on Alibaba Cloud PAI products (EAS / DLC) to identify root causes of instance-level issues. Use when users report: - EAS instance anomalies, GPU OOM (out of memory), GPU memory out-of-bounds errors - Slow first-token latency, uneven request scheduling across model service instances - OOM (Out Of Memory), insufficient memory, processes being killed - Abnormally high system load, high IO latency, network jitter, packet loss - Instance crashes, unexpected restarts, kernel oops - DLC training job hangs, communication timeouts, per-step throughput degradation - Any issue related to EAS instance health, DLC job health, or underlying compute resource performance
Batch health inspection for Alibaba Cloud RDS MySQL instances. Supports single, multiple, or all-instance global scan with configurable time window (default 7 days, max 30). Outputs one HTML report per instance plus a summary HTML. Dimensions: instance basics, resource utilization (CPU/memory/disk/IOPS/connections), CloudMonitor alert history, top 20 space-consuming tables (DAS), slow log statistics (DAS), kernel-version / expiration checks. Cluster instances auto-detected; per-node metrics and slow logs. Triggers: RDS inspection, RDS health check, RDS MySQL inspection, Alibaba Cloud RDS inspection, batch/global/multi-instance inspection, slow log analysis, space analysis, RDS 巡检, 阿里云 RDS 巡检, 数据库巡检, 批量巡检, 慢日志分析, 表空间分析.
Deploys websites, web apps, APIs, and agents to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Handles plain HTML/CSS/JS pages and static sites (Astro, Hugo, Jekyll, Eleventy, Vite) as well as Next, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP servers, Claude Agent SDK scripts, Python workers, and Dockerized projects. Routes to free static hosts — Cloudflare Pages, Netlify, GitHub Pages, Render — or to Vercel, Railway, Docker+SSH VPS, or a cloudflared tunnel, and can also run the project locally. Use when the user says "/all-deploy", "/deploy", "/despliega", "deploy this", "ship this", "push to prod", "get this online", "publish my website", "sube mi página web", "publicar mi página", "hosting gratis", "free hosting", "custom domain", "dominio propio", "run it locally", "corre esto localmente", or otherwise asks to publish a site or project to a URL.
Instrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web). Use for Real User Monitoring (RUM) — page views, clicks, AJAX/fetch dependencies, exceptions, custom events, and browser-side GenAI agent traces correlated to backend OpenTelemetry traces. Covers SDK Loader Script and npm setup, framework extensions (React, React Native, Angular), Click Analytics, telemetry initializers, and OTel GenAI semantic conventions for agent/tool/model spans emitted from the browser.
Celery async task dispatch and management skill with cross-platform deployment support (Windows/Linux/macOS). Provides automatic configuration of an isolated skill environment, command execution tasks, delayed scheduling, and task monitoring. Use cases: (1) executing commands or scripts asynchronously, (2) delayed or scheduled task execution, (3) task queue management and monitoring, (4) distributed task processing. Built-in cross-platform compatibility handling automatically detects the system type and adapts the configuration. **Three required services**: Redis/Memurai, Celery Worker, and Flower monitoring are all required, and any that is not running should be started automatically. **AI assistant auto-starts services**: before dispatching a task, it automatically checks for and starts any service that is not running, with no manual user intervention. Requires Redis/Memurai (Windows) to be installed first.
Configuration reference for domestic Git platforms—SSH/HTTPS/credentials/CI integration differences and mirror synchronization for Gitee, Coding.net, 极狐 GitLab, and CNB. Invoke only when the user explicitly says /chinese-git-workflow; do not trigger automatically based on context.
Write a CI/CD pipeline playbook for a service or team. Use when asked to document a CI/CD pipeline, write a deployment process, define release gates, document build and test stages, or create a deployment guide. Produces a structured playbook covering pipeline stages, environment definitions, deployment gates, rollback procedures, and on-call responsibilities.
Cloudflare Images, covering both the Images API for upload and storage and Image Transformations for optimizing any publicly accessible image. Includes account setup and API tokens, multipart uploads, direct creator uploads for end users, named and flexible variants, signed URLs for private images, imagedelivery.net delivery, /cdn-cgi/image/ URL transforms, and cf.image options from a Worker, plus automatic WebP and AVIF conversion for responsive images. Use when adding image upload or storage to a project, resizing or reformatting images via URL or Workers, building an image CDN or responsive image pipeline, managing variants, generating signed URLs, or debugging CORS failures on direct creator uploads and transformation errors such as 5408, 9401, and 9403.
Complete knowledge domain for Cloudflare Queues - flexible message queue for asynchronous processing and background tasks on Cloudflare Workers. Use when: creating message queues, async processing, background jobs, batch processing, handling retries, configuring dead letter queues, implementing consumer concurrency, or encountering "queue timeout", "batch retry", "message lost", "throughput exceeded", "consumer not scaling" errors. Keywords: cloudflare queues, queues workers, message queue, queue bindings, async processing, background jobs, queue consumer, queue producer, batch processing, dead letter queue, dlq, message retry, queue ack, consumer concurrency, queue backlog, wrangler queues
Production-tested setup for Cloudflare Workers with Hono, Vite, and Static Assets. Use when: creating new Cloudflare Workers projects, setting up Hono routing with Workers, configuring Vite plugin for Workers, adding Static Assets to Workers, deploying with Wrangler, or encountering deployment errors, routing conflicts, or HMR crashes. Prevents 6 documented issues: export syntax errors, Static Assets routing conflicts, scheduled handler errors, HMR race conditions, upload race conditions, and Service Worker format confusion. Keywords: Cloudflare Workers, CF Workers, Hono, wrangler, Vite, Static Assets, @cloudflare/vite-plugin, wrangler.jsonc, ES Module, run_worker_first, SPA fallback, API routes, serverless, edge computing, "Cannot read properties of undefined", "Static Assets 404", "A hanging Promise was canceled", "Handler does not export", deployment fails, routing not working, HMR crashes
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
Audit Azure Storage accounts for public blob containers, missing encryption, overly permissive SAS tokens, disabled logging, and network access violations using Azure CLI, PowerShell, and Microsoft Defender for Storage. Use for storage security audits across subscriptions, responding to Defender for Storage anonymous-access alerts, verifying compliance controls, or setting security baselines when onboarding a subscription.
Write a disaster recovery plan for a service or system — covering RPO/RTO targets, failure scenario runbooks, backup and restore procedures, DR testing cadence, and communication templates. Use when asked to write a DR plan, document failover procedures, create recovery runbooks, define RTO/RPO targets, or prepare for a disaster recovery game day. Produces a full DR document with per-scenario recovery runbooks, backup validation procedures, testing schedule, and communication templates.
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.