Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
A command guide for operating the ROCK platform with rockcli (rc): manage sandboxes, run and view agent evaluations, manage experiments, dump images, manage datasets, and more. Use when the user wants to look up rc command usage or use rockcli to start or stop sandboxes, run commands in sandboxes, transfer files, run agent evaluations, manage experiments, move images, or manage datasets.
Perform read-only troubleshooting on ROCK sandboxes with rockcli (rc): use logs, operation history, status, and replay to locate problems without modifying the sandbox. Use when a user's sandbox fails to start, is unresponsive, reports errors, or has an abnormal status and the cause needs to be diagnosed.
This skill should be used when managing Tailscale mesh VPN networks. Use when the user asks to "check tailscale status", "list tailscale devices", "ping a device", "send file via tailscale", "tailscale funnel", "tailscale serve", "create auth key", "check who's online", "tailscale exit node", "Magic DNS", or mentions Tailscale network management, tailnet operations, or VPN connectivity.
Vercel KV, the Redis-compatible key-value store powered by Upstash, in Next.js and other Vercel applications. Covers @vercel/kv setup and environment variables (KV_REST_API_URL, KV_REST_API_TOKEN), key and JSON value operations, TTL and expiration, caching patterns for pages, APIs, and data, session and auth token storage, rate limiting, TypeScript usage from the edge runtime, serverless functions, and Server Actions, plus migrating from Cloudflare KV. Use when adding Vercel KV to an app, building a cache or rate limiter, storing sessions or temporary data with a TTL, choosing strongly consistent Redis-compatible storage over eventually consistent alternatives, or debugging KV_REST_API_URL not set, rate limit exceeded, or JSON serialization errors.
Use when the user wants to transact on any Volcengine commercial product — purchase/provision it, ask what it costs, or unsubscribe from it. Covers three actions: buy (purchase, subscribe, provision, open, place an order; Chinese "开通 / 购买 / 下单 / 买 / 售卖 / 订购"), price (how much does it cost, quote, billing rules, estimated spend; Chinese "多少钱 / 价格 / 报价 / 费用 / 怎么收费 / 如何计费 / 预估费用"), and unsubscribe (cancel a subscription, refund a prepaid instance; Chinese "退订 / 退款 / 取消订阅"). Trigger even when the user does not mention "sale" but expresses a clear purchase, pricing, or cancellation intent toward a Volcengine product. Only handles these three transaction actions; anything outside them is out of scope.
Enterprise WLAN for mobile users—RF/site surveys, AP placement, 802.11 (Wi-Fi 5/6/6E/7), channel/power planning, SSID/VLAN segmentation, WPA3/802.1X/RADIUS, guest/captive portal, roaming (802.11k/r/v, band steering), high-density and mesh/outdoor, LAN/SD-WAN edge integration, troubleshooting (SNR, DFS, CCI). This skill should be used when the user asks about Wi-Fi, wireless mobility, WLAN design, wireless survey, AP placement, 802.11, Wi-Fi 6, Wi-Fi 6E, roaming, 802.11k, 802.11r, band steering, WPA3, 802.1X, enterprise wireless, high density Wi-Fi, channel planning, RF interference, wireless troubleshooting, Aruba, Meraki wireless, or Cisco wireless—not cellular RAN/5G core, MPLS/BGP backbone (network-backbone-architect), SD-WAN overlay (sd-wan-engineer), cloud VPC only (cloud-architect), MDM-only, or OT ISA wireless (scada-ics-cyber-security-specialist).
Deploys an agentic workflow as an internal FastAPI microservice on Coolify, accessible only from n8n via the internal Docker network (no public URL). Automatically creates the private repo on GitHub, uploads the code, creates the app in Coolify and verifies that the healthcheck is active. Use this skill whenever the user wants to "deploy", "push to production", "publish the agent", "have n8n call the microservice", "create the repo", or any variation of turning local code into a running service. It also applies when the user says things like "I finished the agent, now what" or "how do I integrate it with n8n".
Alibaba Cloud Cloud Firewall ACL rule read-only diagnostic assistant. **Trigger Scenarios**: Diagnose ACL rules not taking effect, troubleshoot Internet/NAT/VPC firewall traffic issues, query traffic logs, check matched rules, get configuration guidance (console manual operation). **Supported firewall types**: Internet Firewall, NAT Boundary Firewall, VPC Boundary Firewall **Keywords**: Cloud Firewall rules not taking effect, Internet Firewall ACL diagnosis, NAT Firewall policy not working, VPC Boundary Firewall rule diagnosis, firewall rule diagnosis ⚠️ **DO NOT use** for WAF issues - use alibabacloud-waf-rule-management skill instead. TEXT-ONLY console guidance. Queries and diagnosis only, no configuration changes.
Use this skill when users ask about SASE terminal device management, user account queries, inactive device analysis, or device locking on Alibaba Cloud SASE (product code: csas). Trigger scenarios: "查下哪些设备长期离线", "某部门有多少 终端设备", "锁定闲置设备", "查看用户被授权了哪些应用". Capabilities: flexible device querying with 20+ filters (department, device type, OS, SASE feature status, etc.), user listing, user application authorization queries, inactive device analysis, and locking inactive devices. Deletion or irreversible operations are NOT supported — users are guided to the SASE console. Note: user activity analysis is currently not supported (the API does not provide the user's last active time, and device bindings change).
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
CI/CD pipeline patterns with GitHub Actions, release automation, and testing strategies. Use for: github actions, workflow, CI, CD, pipeline, deploy, release, semantic release, changesets, goreleaser, matrix, cache, secrets, environment, artifact, reusable workflow, composite action.
Update clash-meta proxy configuration. Use when updating proxy nodes for clash-meta service, editing config.yaml with new proxies from .proxies.yaml, or maintaining proxy-groups consistency. Use the provided Python script with uv for automated backup, proxy update, and proxy-groups review.
Builds and deploys remote Model Context Protocol (MCP) servers on Cloudflare Workers in TypeScript with @modelcontextprotocol/sdk: McpAgent class patterns for tools, resources, and prompts, all four authentication patterns (token validation, remote OAuth with DCR, OAuth proxy via workers-oauth-provider, and a full OAuth provider), GitHub/Google/Azure OAuth, Durable Objects for per-session state, WebSocket hibernation for cost savings, and dual SSE plus Streamable HTTP transports. Ships templates for basic servers, OAuth proxy, stateful Durable Object servers, and wrangler.jsonc configs, and prevents 15+ errors including McpAgent export mistakes, OAuth redirect URI mismatches, WebSocket state loss, Durable Objects binding errors, and CORS misconfiguration. Use when creating, authenticating, debugging, or deploying an MCP server on Cloudflare Workers.
Complete knowledge domain for Cloudflare Workflows - durable execution framework for building multi-step applications on Workers that automatically retry, persist state, and run for hours or days. Use when: creating long-running workflows, implementing retry logic, building event-driven processes, scheduling multi-step tasks, coordinating between APIs, or encountering "NonRetryableError", "I/O context", "workflow execution failed", "serialization error", or "WorkflowEvent not found" errors. 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
Manage cloud development sandboxes with cloudrouter. Create, sync, and access remote VMs with GPU support, Docker, and browser automation. Use when asked to create a sandbox, spin up a dev environment, run code in the cloud, use GPUs, automate a browser, or interact with remote VMs.
Orchestrator for the DynamoDB single-table design pipeline. Use when the user wants to design a DynamoDB table end-to-end or is unsure which step to start with. Routes to the appropriate specialized skill: dynamodb-access-patterns, dynamodb-table-design, or dynamodb-query-interfaces.
Add Sentry v8 error tracking and performance monitoring to your project services. Use this skill when adding error handling, creating new controllers, instrumenting cron jobs, or tracking database performance. ALL ERRORS MUST BE CAPTURED TO SENTRY - no exceptions.
Run activity publishing tasks in a server / Feishu bot environment, wrapping `c pub`. In the dev (testing) environment it runs the publishing task fully automatically and returns the page URL; in the prod (production) environment it outputs the Jenkins release link plus the build configuration for manual execution. Triggered when the user mentions "发布", "发版", "上线", "发测试", "发正式", "pub", "c pub", "推到测试环境" or "发布活动", and also when `c pub` is not mentioned.
Guides FinOps analysis on AWS, GCP, and Azure—cost visibility and allocation, tagging and showback/chargeback models, rightsizing and waste removal, RI/Savings Plan/CUD recommendations, budgets and forecasts, anomaly detection, unit economics (cost per service/customer), and FinOps cadence with engineering accountability. Use when optimizing cloud spend, analyzing CUR/billing exports, building cost dashboards, explaining bill spikes, or improving allocation—not for GL mapping, capex, depreciation, or month-end ledger close (compute-accounting-manager), enterprise EA negotiation (enterprise-cloud-architect), hands-on resource provisioning (cloud-engineer), or hardware supply efficiency (data-center-compute-supply-efficiency).
Provides full-stack development architecture design, tech stack selection, frontend development, backend development, and ops deployment guidance; use when the user needs architecture design, tech selection, frontend development, backend development, ops deployment, or best-practice consulting
Set up a persistent AI agent gateway on macOS with Redis event bridge, heartbeat monitoring, and multi-session routing. Interactive Q&A to match your intent — from minimal (Redis + extension) to full (embedded daemon + Telegram + watchdog). Use when: 'set up a gateway', 'I want my agent always on', 'event bridge', 'heartbeat monitoring', 'agent notifications', or any request to make an AI agent persistent and reachable.
Create and maintain GitHub Agentic Workflows (gh-aw) for Prowler. Trigger: When creating agentic workflows, modifying gh-aw frontmatter, configuring safe-outputs, setting up MCP servers in workflows, importing Copilot Custom Agents, or debugging gh-aw compilation.
glab CLI documentation — GitLab's official command-line tool. Covers merge requests, issues, CI/CD pipelines, repositories, runners, releases, clusters, stacks, variables, schedules, labels, milestones, auth, config, snippets, deploy keys, SSH/GPG keys, Duo AI, MCP, and OpenTofu. USE THIS SKILL WHEN the user asks about glab commands, glab CLI reference, glab mr, glab ci, glab issue, glab repo, glab runner, or GitLab CLI docs.
Google Cloud Pub/Sub messaging service. Covers topics, subscriptions, push/pull delivery, and dead-letter handling. Use for GCP-native event-driven architectures and real-time analytics. USE WHEN: user mentions "google pub/sub", "pubsub", "gcp messaging", "push subscription", "pull subscription", asks about "cloud pub/sub", "ordering keys", "bigquery subscription" DO NOT USE FOR: AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; event streaming - use `kafka` or Dataflow; on-premise - use `rabbitmq` or `activemq`; multi-cloud - use `kafka` or `pulsar`
Ship Home Assistant OS (HAOS) backups off the SD card to cloud storage (Google Drive or any rclone remote) with an upload bandwidth cap and a GFS-style retention policy (daily/weekly/monthly thinning), using the Rclone Backup add-on. Use when the user wants HA backups uploaded to Google Drive / Dropbox / cloud, complains the SD card is filling up with backups, needs 異地備份 for Home Assistant, or asks to rate-limit / throttle backup uploads because home upstream bandwidth is scarce. Also consult before suggesting the native google_drive backup agent or the sabeechen add-on — neither can throttle upload speed.
Guides information security engineering—implementing and operating security controls, identity and access systems, encryption and secrets management, security tool integrations (SIEM, EDR, SOAR), cloud guardrails, hardening baselines, and remediation engineering for vulnerabilities. Use when building SSO/RBAC/PAM patterns, configuring KMS or certificate lifecycle, deploying WAF/DLP or EDR connectors, writing security-as-code policies (OPA, SCPs, CIS benchmarks), integrating logging to SIEM, automating security workflows, or validating control fixes—not for SOC triage (soc-analyst), pentesting (penetration-tester, network-pentester, web-pentester), red team (red-team-specialist), CI gates only (devsecops), platform provisioning without security ownership (infrastructure-engineer), CISO/exec program (chief-information-security-officer), security program strategy (cybersecurity), GRC program and audit prep (compliance-specialist), or product tenancy isolation (product-infrastructure-security-engineer).
Write an infrastructure-as-code review checklist and conduct a structured review of Terraform, CloudFormation, Pulumi, or Ansible code. Use when asked to review IaC code, audit infrastructure configurations, check cloud security posture, or produce a reusable IaC review checklist. Produces a structured review report with severity-categorized findings, remediation guidance, and a reusable checklist.
LLM gateway and routing configuration using OpenRouter and LiteLLM. Invoke when: - Setting up multi-model access (OpenRouter, LiteLLM) - Configuring model fallbacks and reliability - Implementing cost-based or latency-based routing - A/B testing different models - Self-hosting an LLM proxy Keywords: openrouter, litellm, llm gateway, model routing, fallback, A/B testing
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.