Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Manage cycles and canister lifecycle. Covers cycle balance checks, top-ups, freezing thresholds, canister creation, and ICP-to-cycles conversion via the CMC. Use when working with cycles, canister funding, freezing threshold, frozen canister, out of cycles, top-up, canister creation, or cycle balance. Do NOT use for wallet-to-dApp integration or ICRC signer flows — use wallet-integration instead.
Full Sentry SDK setup for Ruby. Use when asked to add Sentry to Ruby, install sentry-ruby, setup Sentry in Rails/Sinatra/Rack, or configure error monitoring, tracing, logging, metrics, profiling, or crons for Ruby applications. Also handles migration from AppSignal, Honeybadger, Bugsnag, Rollbar, or Airbrake. Supports Rails, Sinatra, Rack, Sidekiq, and Resque.
Use when you need to implement or improve Java logging and observability — including selecting SLF4J with Logback/Log4j2, applying proper log levels (ERROR, WARN, INFO, DEBUG, TRACE), parameterized logging, correlation context, secure logging without sensitive data exposure, environment-specific configuration, log aggregation, monitoring, and alerting. This should trigger for requests such as Improve logging; Apply logging; Refactor logging; Add logging support; Review SLF4J structured logging in Java code. Part of Plinth Toolkit
Build ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI). Use when: developing ChatGPT extensions, implementing MCP servers, or troubleshooting CORS, widget 404s, MIME types, ASSETS binding errors, Next.js integration issues, or edge platform limitations.
Lead complex software implementation, architecture decisions, and reliable delivery across any modern technology stack. Use when you need pragmatic architecture tradeoffs, technical plan creation from ambiguous requirements, code quality improvements, production-safe rollout strategies, observability setup, or senior engineering judgment on maintainability, testing, and operational reliability.
Expert blueprint for HTML5/web export on Compatibility (WebGL 2.0): JavaScriptBridge, localStorage wrapper, custom loading shells, COOP/COEP hosts, relative paths, beforeunload, visibility pause, and size optimization. WebGPU is out of scope. Keywords: web, HTML5, WebGL, Compatibility, JavaScriptBridge, localStorage, COOP, COEP, canvas, browser API.
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing applications, managing infrastructure as code, deploying to Kubernetes clusters, configuring cloud platforms, automating releases, or responding to production incidents. Invoke for pipelines, Docker, Kubernetes, GitOps, Terraform, GitHub Actions, on-call, or platform engineering.
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework. Use when writing or editing sst.config.ts, building infra/ modules (sst.aws.Function/Bucket/Dynamo/Cron/Service/Router, sst.Secret, sst.Linkable, raw aws.* Pulumi resources), wiring resource links, scoping IAM, or running sst deploy/dev/diff/remove. Essential when the user mentions SST, sst.config.ts, $config, $transform, $interpolate, sst.aws.*, sst.Secret, Pulumi/Ion, "sst deploy", a failed SST deploy (ConflictException on a resource-type change, "Identifier '__filename' has already been declared", MalformedPolicyDocument on an Output<T>), or wants to scaffold/troubleshoot AWS infrastructure with SST. Also use when a request to "deploy my AWS stack" or "add a Lambda/bucket/table" is made in a repo that already contains an sst.config.ts (using $config) or an sst dependency. Do NOT use when the task is primarily AWS CDK, Terraform, raw CloudFormation, or SAM with no SST present — those have their own tooling.
Guides developers through Enonic CLI commands for sandbox management, project scaffolding, local development, app deployment, and CI/CD pipeline generation. Use when creating Enonic XP sandboxes, starting or stopping local instances, scaffolding projects from starters, running dev mode with hot-reload, deploying apps, or generating CI/CD workflows for Enonic apps. Don't use for writing XP application code (controllers, content types), querying via Guillotine or lib-content APIs, configuring non-Enonic environments, or Docker/Kubernetes deployment of XP.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Safe-change playbook for the darkmatter/gitops repo—pre-commit validation (kubeconform with CI-identical flags, yq for YAML manifests, jq for SOPS JSON, git diff --check), SHA-pinned images, KSOPS/SOPS secret-editing rules, rollback via revert, and how ArgoCD reconciles. Use for any change to darkmatter/gitops (manifests, Helm values, apps/*.yaml, secrets), when asked to bump an image tag, wire a secret, or roll back a deploy. Also use when tempted to kubectl apply/edit/patch anything—the answer is no.
Convert per-page styled HTML prototypes (stardust under stardust/prototypes/**, or claude-design / Mobirise / Relume / Lovable / v0 / Figma-derived pages, or JSX prototypes pre-rendered to HTML, often under samples/) into Edge Delivery Services (EDS / AEM) blocks and content pages, then deploy via DA. Each prototype section becomes one EDS block; the prototype's per-section CSS becomes that block's CSS scoped under the block class. Use when the user wants to lift styled per-page HTML prototypes into a working EDS site under blocks/ and content/
Create Huawei Cloud Flexus L Instance (Lightweight Server), deploy OpenClaw application platform on it, and support installation and configuration of models and channels for deployed OpenClaw instances. Web UI access needs to be manually enabled in Huawei Cloud console. Trigger words: "Deploy OpenClaw", "Deploy Flexus L Instance", "Deploy Huawei Cloud Lightweight Server", "Model setting", "Channel Setting", "部署OpenClaw", "部署Flexus L实例", "部署华为云轻量服务器", "设置模型", "设置通道"
Build with Firebase Cloud Storage — file uploads, downloads, and secure access. Use when: uploading images/files, generating download URLs, implementing file pickers, setting up storage security rules, or troubleshooting storage/unauthorized, cors errors, quota exceeded, or upload failed errors. Prevents 9 documented errors.
Design and deploy multi-canister dapps. Covers inter-canister calls, canister factory pattern, async messaging pitfalls, bounded vs unbounded wait, and 2MB payload limits. Use when splitting an app across canisters, making inter-canister or cross-canister calls, or designing canister-to-canister communication. Do NOT use for single-canister apps.
Configure the OpenTelemetry Collector with Sentry Exporter for multi-project routing and automatic project creation. Use when setting up OTel with Sentry, configuring collector pipelines for traces and logs, or routing telemetry from multiple services to Sentry projects.
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, and GCP.
Architect scalable backend systems, database schemas, APIs, and cloud infrastructure for robust server-side applications. Use when you need microservice vs monolith decisions, database indexing strategies, API versioning, event-driven architecture, ETL pipelines, WebSocket streaming, data modeling, query optimization, or cloud-native service design with high reliability and sub-20ms query performance.
Turn messy Unity or Unreal build/release automation into one bounded game-pipeline packet after naming the signal tier first: fast branch-gate CI, nightly/package- candidate builds, or release/certification candidates. Use when a game team needs to design or repair GitHub Actions, Unity Build Automation, Jenkins, TeamCity, or similar CI for engine builds — especially when they mention flaky packaging, cache superstition, giant build-job blobs, slow cook / package cycles, artifact confusion, SDK/signing drift, or manual candidate promotion that should become reproducible. Route one red log first-pass diagnosis to `game-build-log-triage`.
Use when the user asks to manage Make platform resources with makecli — create/deploy apps, promote beta to production, check build/deploy progress or app URLs, read build/deployment logs, entities, relations, records, inspect resources, switch backend context, log in to Make, or run makecli CLI commands. Also triggered by requests like \"部署\", \"发布到 production\", \"promote\", \"部署进度\", \"构建状态\", \"构建日志\", \"部署日志\", \"apply\", \"查看应用\", \"创建记录\", \"登录 Make\", \"切换环境\", or \"/makecli\". Does not own DSL schema design (use makedsl), frontend UI (makeui), auth (make-app-auth), Service/API code (make-app-service), runtime packaging (make-app-runtime), OCR integration (make-integration), or canvas-table behavior.
Expert knowledge for Azure Role-based access control development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, integrations, and coding patterns. Use when defining custom roles, ABAC conditions, deny assignments, PIM-eligible roles, ARM/Bicep-based role assignments, or other Azure Role-based access control development tasks. Not for Azure Policy (use azure-policy), Azure Resource Manager (use azure-resource-manager), Azure Security (use azure-security), or Azure Lighthouse (use azure-lighthouse)
Audits Cloud Logging costs for a Google Cloud project: charges for log entries written to log buckets, the services, log streams, and severities that drive them, and the log sinks that route them. Reconciles Cloud Billing export costs with Cloud Monitoring volume metrics, and generates a FinOps report with charts and copy-paste exclusion filters. Use when auditing Cloud Logging spend, finding logging waste, identifying top logging contributors, generating log cost reduction reports, or creating log sink exclusion filters. Don't use for querying log entries (use cloud-logging-query-generation), configuring Cloud Monitoring alerts, or querying metrics/traces.
Linux container internals skill covering namespaces, cgroups, and OCI. Use when understanding clone/unshare namespaces, cgroups v2 limits, overlayfs, runc, seccomp profiles, capabilities, or escape mitigations. Activates on queries about namespaces, cgroups, overlayfs, runc, seccomp-bpf, the OCI spec, or container escape
Neon + Vercel serverless Postgres for edge and serverless environments. Use for Cloudflare Workers, Vercel Edge, Next.js apps with HTTP/WebSocket connections, database branching (git-like), Drizzle/Prisma ORM integration, migrations, PITR backups, or encountering connection pool exhausted errors, TCP connection issues, SSL config problems.
Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools—pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow is the slow or flaky long pole, how long PRs take from open to merge, how an author's merge time compares to the cohort, which open PRs have failing or pending CI, or where a specific pull request is stuck. Triggers on “engineering analytics,” “is CI getting slower,” “slow workflow,” “flaky CI,” “time to merge,” “cycle time,” “PR throughput,” “failing checks,” “where is PR <n> stuck,” “CI long pole,” “what's holding up this PR.” For a verdict on one specific CI failure (whose fault, which commit) use investigating-ci-failures; to save these numbers as insights use turning-engineering-analytics-into-insights.
Generates service-specific configuration files for GitLab stack projects in the ./config directory, using .env as the primary configuration source. Creates nginx, PostgreSQL, Redis, and custom service configs with strict validation for secrets, paths, and Docker best practices. Use when setting up service configurations, creating config templates, or ensuring configs follow stack patterns.
Expert blueprint for dedicated / headless multiplayer hosts: ENet/DTLS, authority validation, safe packet decode, matchmaker handoff, and health telemetry. Use when building authoritative servers, --headless hosts, or hardening host networking. Keywords: dedicated server, headless, ENet, DTLS, authority, safe_packet_decoder, multiplayer host, WebSocketMultiplayerPeer.
Add OAuth authentication to MCP servers on Cloudflare Workers. Uses @cloudflare/workers-oauth-provider with Google OAuth for Claude.ai-compatible authentication. Prevents 9 documented errors including RFC 8707 audience bugs, Claude.ai connection failures, and CSRF vulnerabilities. Use when building MCP servers that need user authentication, implementing Dynamic Client Registration (DCR) for Claude.ai, or replacing static auth tokens with OAuth flows. Includes workarounds for production redirect URI mismatches and re-auth loop issues.
Full Sentry SDK setup for .NET. Use when asked to "add Sentry to .NET", "install Sentry for C#", or configure error monitoring, tracing, profiling, logging, or crons for ASP.NET Core, MAUI, WPF, WinForms, Blazor, Azure Functions, or any other .NET application.
Alibaba Cloud MaxCompute Project Management Skill. Use for creating, querying, and listing MaxCompute projects. Triggers: "maxcompute project", "odps project", "create maxcompute project", "manage maxcompute project", "list maxcompute project".
Migrate vision, detection, and segmentation small models to Ascend NPU, covering the full workflow: model structure analysis, migration verification, performance profiling, and optimization. Based on torch_npu and msprof. Use this skill when the user wants to: (1) migrate encoder-only models like ResNet, YOLO, and UNet to Ascend NPU; (2) analyze model structure for migration feasibility; (3) verify model inference on NPU; (4) identify performance bottlenecks and get optimization suggestions. Trigger: user mentions “migrate,” “migration,” “Ascend,” “NPU,” “YOLO,” “ResNet,” “encoder-only,” “detection,” “segmentation,” “adaptation,” “adapt,” “迁移,” “昇腾迁移,” “小模型,” “适配,” “昇腾适配,” “GPU迁移,” “NPU适配,” “适配NPU,” or “适配昇腾”
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.