Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Expert guidance for Dockerfile authoring — the complete reference for writing production-grade Dockerfiles. Covers every instruction (FROM/RUN/COPY/ADD/ENV/ARG/WORKDIR/EXPOSE/CMD/ENTRYPOINT/USER/HEALTHCHECK/SHELL) with syntax, best practices, and common mistakes. Includes multi-stage build patterns (build+scratch, build+alpine, builder pattern), layer caching optimization strategies, .dockerignore rules, and language-specific production templates (Go/Rust/Java Spring Boot/Python FastAPI/Node.js Express/TypeScript). Use when the user asks about Dockerfile, how to write a Dockerfile, multi-stage build, layer optimization, or needs Dockerfile examples for a specific language. 使用场景：Dockerfile 编写、怎么写 Dockerfile、Dockerfile 指令、多阶段构建、multi-stage、层优化、layer cache、Dockerfile 模板.
Configures .NET CI/CD pipelines (GitHub Actions with setup-dotnet, NuGet cache, reusable workflows; Azure DevOps with DotNetCoreCLI, templates, multi-stage), containerization (multi-stage Dockerfiles, Compose, rootless), packaging (NuGet authoring, source generators, MSIX signing), release management (NBGV, SemVer, changelogs, GitHub Releases), and observability (OpenTelemetry, health checks, structured logging, PII). Spans 18 topic areas. Do not use for application-layer API or UI implementation patterns.
Orchestrator for the Hostinger Headless build flow — build and deploy a real website on the user's Hostinger account from a single prompt that names a domain. Holds the stage flow and the state contract, and drives each stage in sequence: connect, check state, refine, provision, content model, design, frontend, validate, deploy, done. Triggers: build a headless site for <domain>, build me a site, create a website, make me a website, deploy this to Hostinger, host this on Hostinger, connect this project to Hostinger.
Manages TLS certificates for CockroachDB clusters including CA certificate configuration, client certificate authentication, certificate rotation, and troubleshooting SSL/TLS connection errors. Use when setting up client certificate auth, resolving SSL connection failures, rotating certificates, or configuring mTLS for CDC changefeeds.
Guided entry point for using Sentry through your agent. Orients you to your current setup and, for a new project, sets up Sentry end to end with sane defaults — provision a project, install the SDK (errors, tracing, and whatever it enables by default), and confirm real telemetry reaches Sentry. Routes other intents (adding more signals, fixing issues) to the right skill.
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
Query FeatureDB read/write usage data from PAI-FeatureStore. Use for analyzing consumption, usage trends, and cost estimation by official pricing. Supports date range queries with breakdowns. Triggers: "FeatureDB read/write volume", "PAI-FeatureStore usage", "FeatureDB usage", "FeatureDB statistics", "Feature View usage", "PAI-FeatureStore billing"
Audits the security posture of a CockroachDB cluster (Cloud or self-hosted) across network, authentication, authorization, encryption, audit logging, and backup dimensions. Use when assessing cluster security readiness, preparing for compliance reviews, or investigating security configuration gaps.
Autonomous PR monitor — polls every 2 minutes for merge conflicts, CI/CD failures across GitHub Actions, Buildkite, Vercel, and Fly.io, review comments, and merge readiness. Auto-detects PR from current branch, fixes what it can, notifies on state changes. No setup questions. Use when asked to babysit a PR, watch a PR, monitor CI, keep a PR green, handle merge conflicts, or poll PR status
Changing DOCA versions safely: upgrading or downgrading the host DOCA packages, refreshing the BlueField BFB, bumping the NGC DOCA container tag, or rolling back, with the discipline detect -> report -> ASK -> only then a guided upgrade. Trigger on "is there a newer DOCA", "I want the newest DOCA features, can I just apt upgrade in place", "should I move to the next release", "the upgrade stopped midway and dpkg is in a broken state", "my component is being deprecated, what now", or "roll me back", even without the word upgrade. Detect what is installed, find the newer release, report the gap, then STOP and ask for explicit confirmation; never upgrade automatically. Do not use it for a runtime error on an unchanged install (doca-debug). Version detection alone belongs to doca-version, first-time install to doca-setup, any hardware / firmware / reboot step to doca-hardware-safety, and public-docs or sunset routing to doca-public-knowledge-map.
Set up and orchestrate multi-container Docker applications using docker-compose, including service configuration, networking, volumes, and environment management. Use when the user requests docker compose setup or provides relevant inputs for this workflow.
Use this skill to set up a CI gate that fails the build when Compose stability silently regresses, using the `skydoves/compose-stability-analyzer` Gradle plugin (primary) or the `j-roskopf/ComposeGuard` plugin (alternative for non-Android multiplatform). Covers applying `com.github.skydoves.compose.stability.analyzer`, configuring the `composeStabilityAnalyzer { stabilityValidation { ... } }` DSL, generating a `.stability` baseline with `:stabilityDump`, committing it to version control, and wiring `:stabilityCheck` into a GitHub Actions or other CI job. Use when the team wants a stability SLO, when an unstable parameter slipped into a shared data class and went unnoticed until jank was reported, when migrating a large app to strong skipping, or when the user mentions stabilityCheck, stabilityDump, baseline drift, ComposeGuard, or "fail the build on stability regression".
Reviews, audits, and modifies CockroachDB cluster settings. Self-Hosted has full control over all settings and start flags. Advanced/BYOC can modify most SQL-level settings but infrastructure settings are managed by CRL. Standard has limited settings access — session variables are the primary tuning mechanism. Basic has minimal settings — use session variables and Cloud Console. Use when auditing configuration, tuning performance, or troubleshooting settings-related issues.
Midnight RPC interface — JSON-RPC methods for contract state, ZSwap chain state, ledger version, Polkadot SDK defaults, and Partnerchain RPCs. Use when building dApps, wallets, explorers, or configuring node RPC exposure for validators vs observers.
Catch the deterministic CI failures reachable from your diff before pushing, with `hogli ci:preflight`. Use when the pre-push hook blocks a push, before reporting a task done, or after editing Python, serializers, migrations, workflows, or dependency manifests — to avoid burning a CI matrix on a failure you could catch locally (formatting, lint, broken lockfiles, OpenAPI drift, migration conflict, stale branch). Trigger terms: ci:preflight, preflight, pre-push checks, pre-push hook failed, "will this break CI".
Set up Sentry releases and deploy tracking — tag events with a version and environment, create the release in CI with its commits, and wire up suspect commits and code mappings, so Sentry can show which release introduced an issue, which commit is responsible, and release health. Use when asked to set up releases, track deploys, see what changed, or when issues show an unknown release or no suspect commit.
Azure AD OAuth2/OIDC SSO integration for Kubernetes applications. Use when implementing Single Sign-On, configuring Azure AD App Registrations, restricting access by groups, or integrating tools (DefectDojo, Grafana, ArgoCD, Harbor, SonarQube) with Azure AD authentication.
Use this skill when the user is building or interpreting the doca/tools/gpunetio_ib_write_bw tool pair—a CUDA kernel posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE BW on a GPU+IB-device pair. Trigger even without the tool name—typical phrasings: "measure WRITE BW when the GPU posts the WRs", "BW swings run to run on the same flags", "is the NIC saturated or am I bound on the CUDA kernel", "meson compile fails for the GPUNetIO bw tool", "nvidia_peermem isn't picking up my GPU buffer", or "GPU-posted WRITE BW vs the CPU path". Refuse and route elsewhere for general doca-gpunetio library work, DOCA setup, the GPU-posted WRITE latency analog, CPU-posted RDMA benchmarking (doca-perftest), and app-level end-to-end rates.
Use this skill when the user characterizes RDMA WRITE round-trip time posted from a CUDA kernel via GPUNetIO—compiling `gpunetio_ib_write_lat` under `doca/tools/`, verifying GPU–NIC affinity, and interpreting the half-iteration / full-iteration / nanosecond columns for median / p99 / tail-jitter analysis of a real-time control loop. Also load it for implied asks like "p99 WRITE time on H100 + ConnectX", "tail delay versus batching", or "device-originated versus upstream ib_write_lat". Refuse and route to the proper owner for throughput runs (doca-gpunetio-ib-write-bw), the GPI channel API (doca-gpi), GPUNetIO API work (doca-gpunetio), or SDK setup.
Use this skill when the user is doing hands-on DOCA Management programming against BlueField / ConnectX devices — standing up a management or representor context (doca_mgmt_dev_ctx / doca_mgmt_dev_rep_ctx), querying device caps (data-direct, caps-general), toggling congestion-control global status, modifying diagnostics-data, setting ICM quotas, or issuing a raw firmware command via doca_mgmt_raw_cmd with the right scope (CONFIGURATION / DEBUG_READ_ONLY / DEBUG_WRITE / DEBUG_WRITE_FULL). Trigger even when the user does not say "DOCA Management" — typical implicit phrasings include "fleet tool that walks every BlueField and reads device state", "toggle data-direct on a VF", "set an ICM quota per representor", "send a raw firmware command from C", "DOCA_ERROR_IO_FAILED from raw_cmd", or "fwctl ioctl is failing". Refuse and route elsewhere for mlxconfig direct operation, BFB / firmware reflash, streaming telemetry, doca_caps CLI snapshots, or DOCA install itself — those belong to other skills.
Use this skill when the user is invoking the DOCA PCC Counters tool — the `pcc_counters.sh` bash script under the DOCA tools directory — to arm and read the fixed firmware/hardware PCC (Programmable Congestion Control) diagnostic counters (CNP, RTT, WRED-drop, etc.) on a ConnectX / BlueField device via mst + the mlx5 debugfs `diag_cnt` interface. The script takes two positional args — `set | query` and an mst device path — with no `--help` or subcommands. Trigger even without "pcc_counters.sh" or "PCC counters": "how do I read the CNP / RTT / WRED-drop counters", "PCC counter stuck at zero", "the script says Bad Device", or "is congestion control dropping packets on this port?". Route elsewhere for writing a custom PCC algorithm (doca-pcc), factory firmware PCC config, DOCA install, or fleet-wide CC tuning.
Use this skill when the user is doing hands-on DOCA Telemetry Exporter programming on a host where DOCA is installed — defining a doca_telemetry_exporter_schema and event types, creating sources, picking a publish surface (typed events / opaque events / the metrics counter-gauge-histogram API / OTLP logs / NetFlow), walking the schema-then-source lifecycle, or debugging DOCA_ERROR_* failures from the exporter API. Trigger even when the user does not explicitly mention "DOCA Telemetry Exporter" or "doca_telemetry_exporter_*" — typical implicit phrasings include "publishing counters from my DOCA app", "BAD_STATE when I report an event", "consumer/DTS sees nothing but my report succeeded", "how do I export NetFlow/IPFIX records", or "should I link the exporter or the telemetry service". Refuse and route elsewhere for the receiving DOCA Telemetry Service (DTS), plain stdout logging via doca_log, or real-time event subscription back into the app via doca-comch — those belong to other skills.
Detect infrastructure drift between Terraform state and actual cloud resources. Identifies unmanaged resources, manual changes, and configuration drift. Use when: - User asks to check for infrastructure drift - User wants to find unmanaged cloud resources - User mentions "drift detection" or "Terraform drift" - User asks to compare cloud state to IaC - User wants to audit infrastructure changes
Huawei Cloud ModelArts training job fault diagnosis skill. Uses hcloud CLI to call ModelArts training job log/event APIs, analyzes training job failures/timeouts/stuck jobs, locates customer training code issues, and provides diagnosis conclusions with fix suggestions and confidence levels. Scenarios: training job failure (status.phase=Failed), timeout (Timeout), abnormal (Abnormal), stuck jobs. Triggers: training job failure, training job timeout, training job stuck, ModelArts training diagnosis, 训练任务失败排查, 训练作业异常分析.
Midnight P2P networking — Polkadot SDK libp2p, peer discovery (bootstrap, mDNS, Kademlia DHT), transport (TCP/WebSocket/DNS), Noise encryption, Yamux multiplexing, and substream protocols. Use when configuring nodes, debugging connectivity, or explaining how validators exchange blocks and gossip.
Use when designing OCI networks, troubleshooting connectivity, optimizing egress costs, or configuring VCN security. Covers Service Gateway cost savings, VCN CIDR immutability, Security List vs NSG tradeoffs, VCN peering limitations, and Load Balancer subnet requirements.
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.