Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Wire Strix security scanning into CI/CD — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code. Covers both the self-hosted open-source CLI (runs in your runner) and the managed app.strix.ai platform (GitHub/GitLab app or API, no runner infra). Use when the user asks to add security scanning, pentesting, or Strix to their CI pipeline or PR workflow.
Set up and manage Twilio Organizations for centralized account and user governance. Covers the Organization > Account > Subaccount hierarchy, roles (Owner/Admin/Standard), managed vs independent accounts, domain registration, SSO enforcement, SCIM provisioning, and Organization merging. Use this skill when managing multiple Twilio accounts or users across teams.
Hardening-audit module for reverse-proxy edges and TLS termination (nginx primary; Caddy, HAProxy, Apache secondary) covering inventory, protocol/cipher posture, HSTS and edge headers, request limits, admin-path shielding, proxy-to-app hop trust, and ACME renewal hygiene.
Diagnostics and profile management for Clash Verge and mihomo. Use when the user hits proxy failures, needs to configure AI tool routing, local Hub topology, multi-machine alignment, TUN bypass, cloning or switching subscriptions, or when configuration does not take effect after syncing. For process routes use clash-routes; for egress IP quality use ip-check. Not for ordinary network speed tests.
Cloudflare platform knowledge — Workers, Pages, R2, D1, KV, Durable Objects, AI, and Zero Trust. PROACTIVELY activate for: (1) Cloudflare Workers (handlers, bindings, wrangler), (2) Cloudflare Pages and Pages Functions, (3) R2 object storage, (4) D1 SQL database, (5) Workers KV and Durable Objects, (6) Workers AI inference (LLMs, embeddings, image gen), (7) Vectorize (vector database), (8) Queues and Email Workers, (9) Zero Trust (Access, Tunnel/cloudflared, Gateway), (10) DNS, WAF, Rate Limiting, Page Rules. Provides: wrangler.toml templates, binding patterns, R2/D1/KV usage, Workers AI examples, and Zero Trust config.
Configures and runs Depot remote container builds using `depot build` and `depot bake`. Use when building Docker images, creating Dockerfiles with Depot, pushing images to registries, building multi-platform/multi-arch images (linux/amd64, linux/arm64), debugging container build failures, optimizing Dockerfile layer caching, using docker-bake.hcl or docker-compose builds, or migrating from `docker build` / `docker buildx build` to Depot. Also use when the user mentions depot build, depot bake, container builds, image builds, or asks about Depot's build cache, build parallelism, or ephemeral registry.
Use this skill when operating the DOCA Firefly Service container on BlueField: choosing the four PTP configuration axes (role / profile / domain / interface), connecting the BlueField PHC, host follower, and consumer workload, deciding whether PTP-grade time is needed (vs. chrony / NTP), or debugging a Firefly deployment where PTP is not syncing or the host clock is not following. Trigger even when the user does not explicitly mention “DOCA Firefly” or “PTP.” Typical implicit requests include “container green but PTP never advances past LISTENING,” “Firefly says synced but the host clock still drifts,” “sync acquired but offset is tens of microseconds,” “my Rivermax SMPTE workload needs PTP,” or “is chrony good enough.” Refuse and route elsewhere for installing DOCA, host-side chrony / ptp4l configuration, PTP topology / boundary-clock design, building DOCA apps that read the disciplined PHC, or other DOCA services (DMS, Flow-Inspector, HBN); those belong to other skills.
Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system—writing an mlxconfig firmware parameter, burning NIC firmware, reflashing BFB, flipping NIC ↔ DPU mode, enabling SR-IOV or a device-emulation slot, changing a kernel boot parameter (IOMMU, hugepages, VFIO), PCIe rebinding / rescanning / link-state changes, a BlueField cold reboot, or remediation of a BlueField thermal shutdown. Wrap the change in a pre-flight inventory, OOB reachability, a maintenance window, replica rehearsal, and rollback. Trigger on implicit phrasing: “flip BlueField mode over SSH,” “enable SR-IOV and reboot,” “burned firmware but mlxconfig shows old value,” “BlueField thermal shutdown.” Not for read-only inventory or version queries (doca-version, doca-caps). Refuse and route elsewhere for orientation (doca-public-knowledge-map), installation or environment debugging (doca-setup), and program-side debugging (doca-debug, doca-programming-guide)
Docker containerization for development and production. Covers Dockerfiles, multi-stage builds, layer caching, Compose services, networking, volumes, health checks, security hardening, and production deployment patterns. Use when writing Dockerfiles, optimizing image size, configuring Compose services, debugging container networking, setting up health checks, hardening containers for production, or troubleshooting build cache issues.
Set up and validate Splunk HTTP Event Collector (HEC), explain indexer acknowledgment and distributed HEC behavior, diagnose HEC no-data and HTTP delivery failures from sanitized evidence, and prepare bounded escalation handoffs. Use for Splunk Cloud Platform or Splunk Enterprise HEC tokens, endpoints, event or raw payloads, TLS, channels, ACK, health, authorization, queues, and delivery verification; do not use for non-HEC ingestion, broad architecture, allowlist changes, or service-side remediation.
Use when parsing agent log files to identify error patterns, rate limit hits, timeout clusters, tool failures, and component-level error counts. Produces a structured anomaly report. Cron-compatible — silent if no issues, alert digest if anomalies found.
Research current public Splunk sources and use optional existing-auth read-only stack evidence to diagnose SAML, LDAP, roles, capabilities, group mappings, login failures, and access readiness without changing identity configuration or handling credentials.
Installs and deploys Ascend NPU drivers and firmware. Supports regex-based package matching and extraction, adding executable permissions as needed, dual Python and Shell package verification, checking system dependencies before installation, and CentOS/RHEL/Ubuntu/Debian.
This skill should be used when users need to interact with AWS services via CLI. It covers all AWS services including EC2, ECS, EKS, Lambda, S3, RDS, DynamoDB, VPC, Route53, CloudFront, Bedrock, Support, Billing, and more. Supports querying, creating, modifying, deleting resources, monitoring, debugging, and cost analysis. Triggers on requests mentioning AWS, cloud resources, or specific AWS service names.
Build a distributable macOS DMG from an Xcode project via the bundled local helper — archive → export → package into one signed artifact. Resolves the project/workspace, scheme, team ID, and export options, regenerates the project first when `xcodegen` is detected, then runs `helpers/build-dmg.sh` from the project root instead of inlining xcodebuild. User-only workflow that touches code signing and provisioning: it never GUESSES the signing identity, never overwrites `ExportOptions.plist` without approval, and reports the built DMG path, version, and signing status. Use only when the user explicitly asks to build or package a DMG.
Senior DevOps Engineer with expertise in CI/CD automation, infrastructure as code, monitoring, and SRE practices. Proficient in cloud platforms, containerization, configuration management, and building scalable DevOps pipelines with focus on automation and operational excellence
AWS EC2 virtual machine management — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation. Trigger on ANY of these, even when EC2 isn't named explicitly: - Launching or provisioning: "spin up a server", "create a VM", "new instance", "run-instances", mention of instance types (t3, m5, c5, r6, g5, p4d, t4g, c7g, etc.) - SSH / connectivity problems: "connection refused", "connection timed out", "permission denied publickey", "can't connect to my instance", "SSH not working" - Instance management: resize, stop, start, terminate, reboot, change instance type - Cost optimization: stop dev instances overnight, save money on EC2, spot vs on-demand, reserved instances - Auto Scaling: ASG, launch template, mixed instances policy, scale to zero, scheduled scaling - Spot Instances: spot fleet, spot interruption, capacity-optimized, price-capacity-optimized - AMIs and backups: create image, custom AMI, EBS snapshot, DLM lifecycle policy, copy AMI - Monitoring: EC2 CPU utilization, CloudWatch metrics for instance, instance status checks, console output - Access methods: Session Manager, EC2 Instance Connect, bastion host, port forwarding - Security: IMDSv2, instance metadata, IAM role on instance, security group rules - User data and bootstrap scripts, cloud-init
Create and manage GitLab projects, merge requests, pipelines, issues, branches, and more using the orbit CLI. Use this skill whenever the user asks about GitLab repositories, MRs (merge requests), CI/CD pipelines, branches, tags, commits, issues, groups, or project members. Trigger on phrases like 'list MRs', 'check the pipeline', 'create a branch', 'open a merge request', 'view the latest commits', 'list projects in group X', 'retry the CI', 'close the issue', 'who are the members', or any GitLab-related task — even casual references like 'what's running in CI', 'show me the MRs', 'tag a release', 'check if it merged', or 'list repos'. Also trigger when the user mentions PR/pull request in a GitLab context (GitLab calls them merge requests). The orbit CLI alias is `gl`.
Query specific Kubernetes resources in Huawei Cloud CCE clusters through kubectl cce. Trigger when users ask to get, describe, inspect, or view a Pod, workload, Service, ConfigMap, node, namespace, or other CCE Kubernetes resource, or when they ask to install or repair the local kubectl-cce prerequisites. Install kubectl and kubectl-cce only when they are missing locally.
Proxmox VE (PVE) 9.2. KVM/QEMU VMs (virtiofs), LXC (OCI images), clusters, HA (CRS load balancing), SDN, Ceph, ZFS, pmxcfs, ACME certificates, proxmox-boot-tool, Secure Boot certificate renewal (enroll-efi-keys), NIC name pinning. qm, pct, pvecm, pvesm, pveceph, pvesh, pveum, vzdump, pveam, pvesr, ha-manager CLI, REST API, qm.conf, pct.conf, datacenter.cfg
Install, deploy, or bootstrap a new Coder (coder/coder) deployment end-to-end. Use for first-time setup on Docker, Kubernetes/Helm, a VM, cloud, HTTPS/domain setup, creating the first admin, pushing a starter template, or building the first workspace. Do not use for upgrades, debugging an existing deployment, editing an existing template, or configuring OAuth/OIDC on a running deployment.
Create and manage Volcengine cloud resources using the Volcengine CLI (`ve` command). Supports all Volcengine services including ECS, VPC, CLB, RDS, Redis, and more. Trigger this skill whenever the user asks to create, query, modify, or delete cloud resources on Volcengine, mentions the `ve` command, says "volcengine CLI", or describes infrastructure tasks such as "create an ECS instance", "set up a VPC", "list security groups", "allocate an EIP". Also trigger on Chinese prompts mentioning "火山引擎" or "火山" (e.g., "火山引擎上有哪些 ECS"、"查一下我火山的云服务器"、 "火山引擎创建一个 VPC"、"火山的 Redis 实例列一下"). Also trigger when the user encounters errors from `ve` commands and needs troubleshooting help. Also use for TOS bucket/object operations, tosutil (sometimes written tosutils), Ark CLI / arkcli model discovery, inference, generation, endpoints, fine-tuning, plans, or usage, and TLS (日志服务) / volclog log search, analysis, ingest, export, or LogCollector collection, through `ve tosutil`, `ve arkcli` and `ve volclog`.
Expert on CI/CD pipelines, GitHub Actions first but the principles port to any forge. GENERATE mode builds a repo's pipelines through an interactive analyze-then-confirm conversation (never batch the questions). ADVISE mode reviews, hardens, debugs, and speeds up existing CI and answers best-practice and security questions. Use when setting up or generating CI/CD, adding a workflow, reviewing or hardening a pipeline, auditing supply-chain risk (pinned actions, cache poisoning, pull_request_target, token scope), speeding up CI (caching, path filters, job DAG, pinned tool binaries), or wiring Renovate to bump CI tool pins. Triggers include set up CI, generate a workflow, harden my pipeline, secure my Actions, is my CI safe, speed up CI, pin my actions
Operate NVIDIA DOCA Management Service on a BlueField, Arm/x86 host, or Kubernetes pod: from DOCA 3.5, use the local `dms-cli` (one command per YANG path, no server) or the `dmsd` + `dmspe` service; choose deployment and authentication, configure `-allowed_users` and `dmsgroup`, use gNMI Get/Set/Subscribe, run supported gNOI workflows, and debug frontend/backend failures. Trigger even without “DMS” for “manage a remote BlueField over gRPC,” “gNOI reboot from orchestrator,” or fleet-management requests. SAFETY: reboot, OS installation, factory reset, and managed-file deletion are destructive and require explicit confirmation tied to the target; never invoke them speculatively. Route installation and library/API build questions elsewhere, and turnkey aggregation to the externally productized DOCA Telemetry Service
Expert guidance for Docker Compose — writing production-grade compose.yml files for multi-container applications. Covers complete Compose file syntax (services, networks, volumes, secrets, configs, profiles, extends, include), service configuration (image/build, ports, environment, env_file, depends_on with health checks, deploy resources, restart policies), networking in Compose (default networks, custom networks, internal networks), volume management, environment variable strategies (.env vs environment vs env_file), override files for multi-environment, profiles for optional services, and migration to Kubernetes with kompose. Use when the user asks about docker compose, docker-compose.yml, compose file, multi-container, service orchestration, compose configuration, or needs to write/modify a compose file. Use cases: docker compose, docker-compose.yml, compose file, multi-container, service orchestration, compose configuration, depends_on, profiles.
Hostinger Domains API for domain portfolio management, availability checks, forwarding, WHOIS profiles, nameservers, domain lock, privacy protection, and domain access verifications. Use when registering domains, checking availability, managing DNS delegation, configuring redirects, handling WHOIS contact information, or checking domain verification status.
HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distributed communication bandwidth, verifying HCCL functionality, and benchmarking collective operations like AllReduce and AllGather. Covers MPI installation, multi-node pre-flight checks (SSH/CANN version/NPU health), and production testing workflows.
Implement OpenTelemetry (OTEL) observability — Collector configuration, Kubernetes deployment, traces/metrics/logs pipelines, instrumentation, and troubleshooting. Use when working with OTEL Collector, telemetry pipelines, observability infrastructure, or Kubernetes monitoring.
Use when managing Oracle Autonomous Database on OCI, troubleshooting performance issues, optimizing costs, or implementing HA/DR. Covers ADB-specific gotchas, cost traps, SQL_ID debugging workflows, auto-scaling behavior, and version differences (19c/21c/23ai/26ai).
OpenTelemetry in Go — SDK setup, API surface, breaking changes, contrib instrumentation libraries (otelhttp, otelgrpc, otelmongo), compile-time zero-code instrumentation (otelc), and performance tuning. Use when adding, reviewing, or configuring OpenTelemetry in a Go service. Triggers on "setup otel in go", "go telemetry", "go tracing", "otelconf go", "otelhttp", "otelgrpc", "TracerProvider go", "MeterProvider go", "otelc", "compile-time instrumentation go", "zero-code go instrumentation", "go build instrumentation", or any Go-related OTel question.
Turn a thesis, proposition, trend, question, or explainer topic into a citation-backed, image-rich, interactive website and deploy it with Vercel CLI. Use when the user asks to research a claim deeply, generate visuals, build a shareable web experience, publish a microsite, create an interactive story/report, or deploy a researched site to Vercel.
Best-practice authoring guidance AND a read-only policy gate for AWS Terraform generated by a migration skill. Load during any phase that writes a terraform/ directory — first as the "what to emit" posture rules + security-baseline spec, then after writing as the deterministic policy verdict. Read-only: it reports whether the generated Terraform passes; it never edits .tf files, never touches .phase-status.json, and never decides phase completion. Complements (does not replace) terraform fmt/init/validate
Use when adding or editing a GitHub Actions workflow that pushes a container image to a registry (ECR/ghcr/Docker Hub via build-push-action) or dispatches a production deploy (a `commit_state_update` repository_dispatch to PostHog/charts). Those run from a single canonical deploy repo, gated by the CD_DEPLOY_ENABLED variable. Does NOT apply to workflows that publish GitHub releases, npm, crates, or Homebrew — those stay on the public repo.
Chaos engineering principles, controlled failure injection, resilience testing, and system recovery validation. Use when testing distributed systems, building confidence in fault tolerance, or validating disaster recovery.
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.