Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model control or LoRA hot-loading. Triggers on 'llama.cpp', 'GGUF', 'LoRA adapter', 'benchmark inference', 'llama-server'.
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer wants to run "mirrord preview" ad hoc, share a preview via a link (mirrord-share-ingress), or wire preview environments into CI with the metalbear-co/mirrord-preview GitHub Action (e.g. per-PR previews, least-privilege cluster access).
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.
This skill should be used when user asks to "query OpenObserve", "create OpenObserve dashboard", "edit OpenObserve panel", "fetch OpenObserve logs", "run OpenObserve search", "list OpenObserve streams", "ingest into OpenObserve", or works with OpenObserve Cloud / self-hosted via REST API. Covers auth, search/SQL, streams, dashboards (CRUD + per-panel ops), the v8 panel JSON schema, and known pitfalls (re-aggregation, hash concurrency, microsecond timestamps).
Authors GitHub Actions quality-gate workflows for a Python repo — lint/type/test jobs, version matrices, uv caching, an all-checks-passed aggregator, required checks, rulesets, merge queues, SHA pinning, zizmor hardening. Use for 'set up continuous integration quality gates', 'make checks required', 'move branch protection to rulesets', 'harden the workflows'. Not for release pipelines or commit hooks.
Qdrant vector database: collections, points, payload filtering, indexing, quantization, snapshots, and Docker/Kubernetes deployment. Use when managing Qdrant collections, performing vector searches with payload filters, configuring HNSW indexes or quantization, or deploying Qdrant clusters. Keywords: Qdrant, vector database, HNSW, quantization, semantic search.
QMEDR read-only devops diagnostics: after confirming the current server metadata's describe result, query devops gray-task for gray-release tasks/reporting statistics/failure information, and devops crash-monitor for crash and dump status. Does not cover policy configuration, security alerts or threat incident investigation, Endpoint response, telemetry SQL, and does not perform general release deployment.
Use the official Remix CLI for authentication, config inspection, game creation, uploads, and analytics. Trigger this skill when a task involves `remix login`, `remix whoami`, `.remix-cli.json`, `REMIX_API_KEY`, or terminal-based game management on Remix.
Guide for connecting to remote servers via SSH, managing containers, and executing commands remotely. Covers SSH connection setup with multiple authentication methods (SSH key, sshpass, Paramiko, Fabric, tmux interactive), Docker container connection and command execution, file transfer, and troubleshooting. Use this skill whenever users need to: (1) Connect to a remote server or VPS via SSH, (2) Execute commands on remote machines, (3) Transfer files to/from remote servers, (4) Connect to Docker containers on remote hosts, (5) Set up SSH password authentication tools. Even if the user just says 'help me run something on my server' or 'connect to my machine', this skill applies.
Use when working on BK-CI repository integration, repository authorization, Webhooks, SCM integration, PAC switches, and differences between repository types. Prefer this when the user mentions Git/SVN/GitHub/TGit, Webhooks, repository authentication, PAC repositories, or commit records.
Turns a Backstage plugin you are developing into a deployable Red Hat Developer Hub dynamic plugin artifact: run @red-hat-developer-hub/cli plugin export to produce dist-dynamic and dist-scalprum, choose shared, embedded and bundled dependencies, package as an OCI image, tgz archive or npm package, push to quay.io or another registry, and generate the SHA-512 or sha256 digest integrity values a deployment needs. Use for "export my plugin", "package the plugin as OCI", "push the plugin to a registry", --shared-package, --embed-package, plugin-manifest.json, or integrity hashes. For a failing export in the rhdh-plugin-export-overlays repository, use /rhdh-overlay instead.
Propagates an rhdh-plugins workspace change through overlays and rhdh-plugin-catalog (midstream): changeset + npm publish, overlays source.json to the Version Packages SHA, then a surgical catalog MR (overlay-repo/, workspaces/, plugin_builds/, .tekton PLR tags like 2.0.0--0.0.3) without a full sync-midstream --force-clone. Use when promoting plugin versions, waiting on npm @red-hat-developer-hub packages, bumping overlays repo-ref, or midstream Hermeto/lock/PLR updates for one workspace. For an overlays workspace edit outside this promotion chain, use /rhdh-overlay.
Commissions or decommissions the openshift/release Prow configuration for a single RHDH release branch: the ci-operator config `redhat-developer-rhdh-release-{version}.yaml`, the jobs `make update` generates from it, the `release-{version}` branch-protection block in `_prowconfig.yaml`, and the `#rhdh-e2e-alerts-X-Y` Slack channel and `rhdh-send-alert` Vault webhook. Use for "set up CI for release 1.11", "commission the 1.12 branch jobs", or "decommission 1.8". Prow configuration for a release branch only — the release itself is rhdh-release-status, rhdh-release-schedule, and rhdh-release-announce.
Comprehensive senhasegura PAM platform skill for secrets management, credential vaulting, SSH key rotation, and DevOps secrets integration. Use when working with senhasegura A2A APIs, DSM CLI, MySafe, credential management, password rotation, External Secrets Operator integration, or any senhasegura PAM operations.
Share a local iOS build with a registered iPhone that is not connected to this Mac. Cuts a cloud-signed build, uploads it to Speedflight (speedflight.dev), and posts a link in the chat that installs from Safari. Use it proactively, without being asked, whenever the user wants a build on their device and the device is not plugged in or reachable (run-on-device fails, "send me the build", "I'm away from my desk", "put this on my phone"). Also use on "/speedflight" or "share a build", to set up Speedflight for a repo, and when the user asks to add a device or a teammate's phone to Speedflight (mints an enroll link, pulls the UDIDs down, registers them with Apple).
UiPath Insights historical monitoring via `uip insights`: job metrics, failure analysis, and process performance; queue totals, SLA risk, timelines, and failure drill-down; machine availability, fault ranking, and runtime minutes; filter discovery of scope; alert definition, history, delivery, and entitlement reads; Insights user, role, and group reads; Maestro process dashboard reads and writes; export destination checks; Looker dashboard lists and embed URLs. For live Orchestrator records or job start/stop/logs→uipath-platform, root-cause analysis→uipath-troubleshoot, workflow authoring→uipath-rpa, org identity→uipath-admin.
Install, configure, and use the Unity Command Line Interface (CLI) for automated production workflows, project management, and cloud integration. Use when setting up CLI-based build automation, CI/CD pipelines, Editor/module management, authentication, or localhost API calls via the experimental Unity Pipeline package. Designed for verifiable, machine-readable game production workflows where the build machine must be describable and tests must return evidence. Triggers on: Unity CLI, unity command line, unity automation, unity ci/cd, unity build script, unity pipeline, unity production workflows.
Managing Walrus blob lifecycles: epochs, lifetimes, extending blobs, deleting blobs, burning blob objects, sharing blobs, setting blob attributes, and handling large uploads. Use when the user needs to extend a blob's lifetime, delete or burn blobs, create shared blobs, set/get/remove blob attributes, plan large data uploads (>1 GiB), estimate storage costs, manage concurrent upload memory, or understand epoch-based expiration. For basic store/read, see `walrus-cli`. For quilts, see `walrus-quilts`.
Common Walrus error messages, their causes, and fixes. Use when the user encounters an error while using Walrus CLI, TypeScript SDK, HTTP API, or Move integration. Covers VMVerificationOrDeserializationError, ChainNotSupportedError, tip exceeded, RetryableWalrusClientError, file.bytes is not a function, 413 Payload Too Large, BlobNotCertifiedError, spawn walrus ENOENT, Cannot find gas coin, EWrongVersion, and other errors the documentation and the SDK source describe.
Deploy tRPC on AWS Lambda with awsLambdaRequestHandler() from @trpc/server/adapters/aws-lambda for API Gateway v1 (REST, APIGatewayProxyEvent) and v2 (HTTP, APIGatewayProxyEventV2), and Lambda Function URLs. Enable response streaming with awsLambdaStreamingRequestHandler() wrapped in awslambda.streamifyResponse(). CreateAWSLambdaContextOptions provides event and context for context creation.
Use when working on an AI GO Custom App (ai-go.app): developing the frontend (React + TypeScript) or a Server-Side Action (Python), deployment and verification, planning a new App from scratch (requirements inventory, deciding between the Custom App / Hosted App product lines), planning user authorization architecture (roles, app role allowlists, batch-inviting internal and external people), planning data architecture (self-built tables in the data center / Data Reference), hooking up Webhooks or setting App schedules, and moving/migrating an existing system or an entire project (frontend + backend + DB; Supabase / Google Sheet / MySQL, etc.) into AI GO.
Read-only diagnostics for Alibaba Cloud CDN refresh and preload issues. Use when a URL/file/directory refresh or preload looks ineffective - refresh failed, preload failed, cache not cleared, or the task failed. Verifies task records and edge cache status, and produces a diagnosis report; never submits refresh/preload jobs. Triggers: "refresh failed", "preload failed", "cache not cleared", "purge not working", "prefetch not cached", "warm up ineffective", "invalidation unsuccessful", "pre-warming failure", "pre-fetching".
Set up Conventional Commits with semantic-release for automated semantic versioning. Use this skill whenever the user mentions conventional commits, semantic versioning, semver, release automation, auto version bumping, changelog generation, commit message standards, semantic-release, or wants to configure automated releases. Also trigger when the user asks about commit message formats like "feat:", "fix:", or "BREAKING CHANGE", or wants to replace an existing versioning system (standard-version, changesets, lerna, release-please) with semantic-release. Even if the user just says "set up versioning" or "add release automation", this skill applies.
This skill should be used when users need to query AWS cost and usage details for a specific date. It supports querying costs at service level (e.g., EC2, S3, RDS) and drilling down to usage type level (e.g., instance types, storage classes, data transfer). Triggers on requests mentioning AWS costs, billing, spending, cost breakdown, or fee analysis.
Deploy any full-stack app (Next.js + FastAPI or similar) to AWS production with Docker, ECR, ECS Fargate, ALB, ElastiCache, CloudWatch, and Grafana. Use when deploying to AWS, setting up CI/CD, configuring production infrastructure, or shipping any app to production.
Overall methodology for penetration testing Azure cloud environments. Use when the target uses Azure/Microsoft 365/Entra ID, when Azure-related assets are discovered (Blob Storage/App Service/Azure VM/Azure Functions), when Azure credentials are obtained (Service Principal/Managed Identity/Access Token), or when a security assessment of an Azure environment is required. Provides a full decision tree from unauthenticated enumeration to Entra ID attacks, service privilege escalation, and Cloud-to-OnPrem lateral movement. Covers the attack surface of 35+ Azure services
Use when creating cloud sandboxes (microVMs) to run code, start dev servers, and generate live preview URLs. Also covers deploying AI agents, MCP servers, batch jobs, and Agent Drives (shared filesystems) on Blaxel's serverless infrastructure. Reach for this skill when you need isolated compute environments, real-time app previews, shared file storage across sandboxes, or to deploy agentic workloads.
Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment".
OpenClaw system diagnostics and performance analysis tool. Analyzes agent reasoning time, Token usage, tool call statistics, Run timelines, and Gateway restart history. Supports multiple modes: batch analysis (default), real-time tracking (-f), summary statistics (-s), advanced diagnostics (--advanced). Supports multi-Agent filtering. Use cases: triggered when users ask about OpenClaw running status, performance bottlenecks, reasoning latency, Token consumption, tool execution statistics, error troubleshooting, or agent activity analysis. Trigger words: diagnostics, performance analysis, reasoning time, token statistics, running status, agent analysis, tool call statistics, Run details, Gateway restart. Command trigger: /diag — runs diagnostics directly, supports parameter passthrough.
Use CDK for container environment penetration and escape. Use when you have entered a container environment (Docker/K8s Pod) and need to assess escape possibilities, exploit container vulnerabilities, or perform information gathering inside the container. CDK integrates container environment assessment, multiple escape techniques (privileged/mount/cgroup/lxcfs/runc/kernel vulnerabilities) and in-container lateral movement. Running the CDK assessment should be the first step after obtaining a container shell. Use this skill in scenarios involving container escape, Docker penetration, K8s security or container privilege escalation
Methodology for CI/CD pipeline and supply chain attacks. Use when the target uses CI/CD systems such as GitHub Actions/Jenkins/GitLab CI/CircleCI/Terraform Cloud/Atlantis, when pipeline security needs to be tested, or when configuration files such as .github/workflows/Jenkinsfile/.gitlab-ci.yml are discovered. Covers the three PPE (Poisoned Pipeline Execution) attack patterns (D-PPE/I-PPE/3PE), the VCS repository attack surface (code leakage/Webhook abuse/branch protection bypass), Pipeline Secrets theft and lateral movement, and paths from CI/CD into cloud environments
Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.
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.