Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Diagnose and fix failing CircleCI builds quickly and safely. Use when users ask to investigate failed CircleCI jobs, triage flaky pipelines, identify root causes from logs, and implement minimal fixes in configuration, test setup, or build-related code paths.
Add headless Chrome automation with Puppeteer/Playwright on Cloudflare Workers. Use when: taking screenshots, generating PDFs, web scraping, crawling sites, browser automation, or troubleshooting XPath errors, browser timeouts, binding not passed errors, or session limits.
Use this skill when discovering and comparing cloud-native technologies from the CNCF Landscape for an architecture or engineering decision. Query the live public Landscape API, filter candidates by capability, category, maturity, license, and repository signals, then produce an evidence-backed shortlist with trade-offs, unknowns, and validation steps. Do not use it as a substitute for project documentation, production-readiness testing, legal review, or general architecture methodology.
Generate a Dynatrace Gen 3 **KPI dashboard** (15–20 business KPIs, required map tile, branded section dividers) and a matching 30‑minute BizEvents injector for a named company, then deploy both via `dtctl`. Use this skill ONLY when the user explicitly asks for a Dynatrace KPI dashboard, business-event KPI demo, BizEvents injector, or a "KPI dashboard for <company>" — do NOT use for generic Dynatrace dashboards (SRE, infra, k8s, services, RUM) or for editing existing non-KPI dashboards. Triggers include phrases like "generate a KPI dashboard", "build a BizEvents demo for <company>", "spin up a KPI dashboard + injector", "/generate-kpi-dashboard". Requires `dtctl` authenticated to a Dynatrace Gen 3 tenant.
Use files-sdk to add file storage to a TypeScript/JavaScript app with a unified API across 49 adapters (S3, R2, GCS, Azure, Vercel Blob, the local filesystem, and more). Triggers when the user wants to upload/download/list/search/move/delete/copy files, generate presigned URLs, do multipart or resumable uploads, range downloads, conditional (ETag) writes, bulk (array) operations, migrate or mirror between providers, list folders, scope to a prefix, observe activity with hooks, add plugins (encryption, validation, versioning, caching, …), react to files being created or deleted (bucket notifications from S3/SQS/EventBridge, MinIO, R2 Queues, GCS Pub/Sub, Storj via Pub/Sub, Azure Event Grid, B2/Box/Cloudinary/Appwrite/Supabase/Tigris webhooks), expose storage to the browser with `useFiles` and a server gateway, use the `files` CLI or its MCP server, expose storage to an AI agent (Vercel AI SDK, OpenAI Responses/Agents, Claude Agent SDK), or asks about "files-sdk", "Files SDK", `new Files(...)`, `createFiles(...)`, `files.upload`, `files.move`, `files.url`, `files.signedUploadUrl`, `files.search`, `transfer(...)`, `sync(...)`, `UploadControl`, or any `files-sdk/<adapter>` subpath import
Complete GitHub Pages deployment and management system. Static site hosting with Jekyll, custom domains, and GitHub Actions. USE WHEN user mentions 'github pages', 'deploy static site', 'host website on github', 'jekyll site', 'custom domain for github', OR wants to publish a website from a repository.
Manage CloudRobo workspaces — create, list, show, update, delete workspaces; manage workspace members (add, list, update role, delete); view workspace overview statistics (capacity, used, available, member count); switch active workspace context for use by other cloudrobo skills (dataset, train, eval, infer, etc.). Workspace is the foundational resource container — all other CloudRobo operations require a valid workspace_id. Triggers include: workspace management, workspace member management, workspace switching, workspace overview, workspace configuration, default workspace, 工作空间管理, 工作空间成员, 工作空间切换, 工作空间概览, 工作空间配置, 默认工作空间.
Query and manage Huawei Cloud HSS (Host Security Service) for daily security inspection and incident response. Covers host assets, vulnerabilities, security baselines, intrusion alerts (trojan/brute-force), login audit logs, risk scoring, and alert handling status updates. Read-only queries plus alert status marking — no isolation or antivirus actions. Use this skill when the user needs to inspect host security risks, investigate suspected intrusion, review vulnerability/baseline reports, or handle security alerts. Triggers include: 主机安全, HSS, Host Security Service, 安全巡检, 漏洞查询, 安全基线, 入侵告警, 木马检测, 暴力破解, 登录审计, 告警处置, 风险诊断, host security inspection, vulnerability scan, baseline check, intrusion alert, trojan detection, brute force, login audit, alert handling, risk diagnosis, security event response.
Write a structured incident postmortem or post-incident review. Use when asked to write a postmortem, incident report, P1/P2 review, outage report, or RCA (root cause analysis). Produces a blameless postmortem with timeline, root cause, contributing factors, impact summary, and action items.
Review Kafka producer and consumer performance configurations in both the live cluster (via Lenses MCP) and the codebase. Flags un-tuned defaults, anti-patterns and missing best practices. Use when user says "review Kafka performance", "check producer configs", "tune Kafka settings" or asks about throughput, batching or compression. Do NOT use for cluster sizing or capacity planning.
Stand up a personal Kanban board and wire this agent to it, end to end. Serve the board, publish it to a public URL, verify the connection, and hand the user their live link. Each user gets their OWN board at their OWN URL — self-contained, no shared server, no collisions. Use when the user wants to set up / publish / deploy their Kanban board, or connect their agent to it. For day-to-day task operations (create/move/list tasks) use the nested companion skill `kanban-agent` (in kanban_agent_skill/) instead — it is auto-discovered when this skill is installed.
Launch and manage batch jobs on Lightning AI - run commands on cloud CPUs/GPUs from a Docker image or a Studio snapshot, monitor status, show live progress with an ETA and setback tracking (status-line bar + Monitor events), fetch logs, SSH into a running job or multi-machine worker, collect artifacts, and run multi-machine (distributed) training. Use when the user wants to run training, data processing, or any batch workload on lightning.ai, or asks to SSH into a job / MMT. Also load it before launching or resuming any job, 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 progress.py.
Operate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure model lists and routing/reliability, virtual keys, teams, budgets, rate limits, caching, guardrails, observability, and spend, and diagnose request failures. Use when deploying or running a LiteLLM proxy or gateway (config.yaml, ghcr.io/berriai/litellm), wiring the Python SDK or OpenAI SDK through it, or hardening a public-facing deployment. Do not use for operating a single inference engine (vllm, llama-cpp), for engine-selection methodology (ml-engineering), or for building applications on top of an LLM API (backend/frontend engineering).
When distributing traffic across multiple servers or regions, use this skill to select and configure the appropriate load balancing solution (L4/L7, cloud-managed, self-managed, or Kubernetes ingress) with proper health checks and session management.
Guide users through creating, managing, and testing server configuration automation using Ansible. When automating server configurations, deploying applications with Ansible playbooks, managing dynamic inventories for cloud environments, or testing roles with Molecule, this skill provides idempotency patterns, secrets management with ansible-vault and HashiCorp Vault, and GitOps workflows for configuration as code.
Design and manage NetBox data models effectively. Covers site/location hierarchy, IPAM organization, device modeling, tenant assignment, custom fields vs tags vs config contexts, dependency ordering, and relationship patterns. Use when planning NetBox data structure, importing bulk data, or choosing between extensibility mechanisms.
Query and analyze OCI (Oracle Cloud Infrastructure) detail billing data from StarRocks via DuckDB. Handles large datasets by always exporting to CSV before analysis. Supports basic queries, aggregation, time-series, tenant, and currency analysis. Triggers on: OCI账单查询 / 云账单分析 / OCI billing / cloud cost analysis / 查询OCI费用 / OCI明细账单
Use when a project has NO okteto.yaml/okteto.yml and the user wants it on Okteto — e.g. "get this repo onto Okteto", "set up a dev environment for this", "create an Okteto manifest", "onboard this service". Also use when okteto deploy fails because no manifest exists. Do NOT use if okteto.yaml or okteto.yml already exists — that is the okteto skill's domain.
OpenClaw usage expert: helps you install, deploy, configure, and use the OpenClaw personal AI assistant. Can diagnose issues, create bots, execute automated tasks, etc. Use when users need to install OpenClaw, configure Gateway, set up Channels, create Agents, troubleshoot issues, or perform OpenClaw-related operations.
Operating production Kubernetes clusters effectively with resource management, advanced scheduling, networking, storage, security hardening, and autoscaling. Use when deploying workloads to Kubernetes, configuring cluster resources, implementing security policies, or troubleshooting operational issues.
Create Post Incident Records (PIRs) by discovering issues from PagerDuty, Datadog, Cloudflare, and Rollbar concurrently. Orchestrates pagerduty-oncall, datadog-analyser, cloudflare-traffic-investigator, and rollbar-reader skills, auto-determines severity, and outputs completed PIR forms. Use when asked to "create a PIR", "write a post incident record", "fill out PIR form", "incident report", "analyse incidents", or after on-call shifts need documentation.
Deploy and manage the self-hosted Tailscale/Headscale ecosystem: a Headscale control server, tailscale clients, ACL policies, node lifecycle, subnet routing, DERP relays, backup/migration, and Tailworm security exposure triage. Use when the user mentions Tailscale, Headscale, tailnet, mesh VPN, WireGuard mesh, or self-hosted VPN infrastructure. Do not use this skill for unrelated requests; route to the nearest named specialist.
CLI syntax reference for Tabular Editor 2 (TabularEditor.exe); deployment, scripting, BPA analysis, and CI/CD integration. Automatically invoke when the user mentions "TabularEditor.exe", TE2 CLI flags (-D, -S, -A, -B, -TMDL, -O, -C), or asks to "deploy a model via CLI", "set up CI/CD for Power BI", "automate model deployment", "run BPA from command line", "save model as TMDL".
Single-tenant GPU endpoints on Together AI with autoscaling and no rate limits. Deploy fine-tuned or uploaded models, size hardware, and manage endpoint lifecycle. Reach for it whenever the user needs predictable always-on hosting rather than serverless inference, custom containers, or raw clusters.
Integrate Vercel Blob object storage for file uploads, image management, and CDN-delivered assets in Next.js applications. Supports client-side uploads with presigned URLs and multipart transfers. Use when implementing file uploads (images, PDFs, videos), managing user-generated content, or troubleshooting missing tokens, size limit errors, or client upload failures.
Configure fastlane + GitHub Actions for iOS projects to automatically build and upload to TestFlight on pushes to the main branch. Reference implementation: the Cathier project. Triggers: "testflight", "fastlane", "auto build", "CI TestFlight", "/wjs-publishing-testflight".
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.