Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Design HTTP APIs for Bun + Hono backends using Clean Architecture, Zod contracts in a shared package, OpenAPI generation from Zod, and thin controllers. Supports two selectable conventions — standard REST (resource paths with GET/POST/PATCH/PUT/DELETE) and POST-only action-based paths — picking one per project. Use when defining new endpoints, auditing or refactoring existing routes, shaping request/response contracts and envelopes, establishing API standards, or mapping typed application errors to HTTP status codes. Do not use for GraphQL, tRPC, non-Hono runtimes, or frontend-only concerns.
Audit an existing repository or multi-module subsystem for evidence-backed architecture improvements, rank bounded candidates, and present them in a visual HTML report with before-and-after diagrams and a top recommendation. Use when the user asks where architecture investment would pay off across a codebase, wants multiple architecture candidates ranked, or needs systemic coupling, shotgun-change, testability, or AI-navigability problems diagnosed. For one named module's responsibility, deepening, splitting, or contract use codebase-design; for a source-tree or package audit use structure-codebase; for an already-selected path whose success is an evidence-backed net-mechanism-reduction claim use reduce-system-complexity. This is audit-and-selection by default.
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under `src/vs/platform/browserView` and `src/vs/workbench/contrib/browserView`.
Java language (17+). Covers modern features, patterns, and best practices. Use when writing Java applications, Spring Boot backends, or enterprise systems. USE WHEN: user mentions "java", "records", "sealed classes", "streams", asks about "pattern matching", "switch expressions", "Optional", "collections", "generics" DO NOT USE FOR: reviewing existing Java code - use `review/java`, which covers the defects javac and an unconfigured build do not report DO NOT USE FOR: Spring Boot specifics - use `backend-spring-boot` skill instead DO NOT USE FOR: Lombok annotations - use `lombok` skill instead DO NOT USE FOR: MapStruct - use `mapstruct` skill instead
Senior Java & Spring Boot 4 / Spring Framework 7 architect skill for 2026-standard development. Use when the user asks to build, scaffold, design, review, or explain Java applications using Spring Boot 4.x, Spring Framework 7.x, Spring Modulith, or any related Spring ecosystem project. Triggers include: creating REST APIs, designing microservices, configuring data access (JdbcClient, JPA 3.2, R2DBC), reactive programming (WebFlux), security (Spring Security 7), observability, GraalVM native images, Gradle/Maven build configuration, Jakarta EE 11 migration, and any task requiring idiomatic modern Java (Java 25: records, sealed classes, structured concurrency, scoped values, pattern matching, JSpecify null safety).
Implementation guide for building and modifying UIs and pages with Lism CSS. Depending on the size of the change, it covers Primitive selection, token matching, use of Property Class/Lism Props, responsive design, and anti-pattern checks. Also useful for reverse lookups of classes and tokens in the b--*, c--*, l--*, a--*, is--*, has--*, set--*, u--*, and -prop:value formats.
Expertise in LLVM optimization passes, performance tuning, and code transformation techniques. Use this skill when implementing custom optimizations, analyzing pass behavior, improving generated code quality, or understanding LLVM's optimization pipeline.
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this code", "tests pass but prod fails". SCOPE HARD RULE: one file or one function only. For a directory or whole module use logic-health; for a confirmed failure (stack trace, failing test, specific wrong value) use logic-locate; for two versions use logic-diff; for repo-wide autonomous fixing use logic-fix-all. Do NOT trigger for: style/formatting, security scanning, performance, test generation, architecture or design questions.
Design, explain or redesign code at the level of modules, classes, files and folders, through the low-level design delivery framework. Use when designing a new project or feature from a spec, explaining how an existing codebase is structured, restructuring one, or deciding where code should live
Build maps in React with mapcn, themeable shadcn-style map components built on MapLibre GL and Tailwind CSS. Use when the user wants to add, customize, or theme a map: markers, popups, tooltips, routes, arcs, GeoJSON or choropleth layers, clusters, a globe, custom basemap styles or light/dark theming, or a full map page (analytics dashboard, delivery tracker, store locator) in a React, Next.js, or Vite project using shadcn/ui or Tailwind. Also use when they ask where a map would fit in their app.
Speed up local parfor, parfeval, or spmd by switching to a thread-based parallel pool. Trigger when a user describes slow or disappointing local parallel performance, even if they don't mention threads. Symptoms: parfor on a laptop/workstation is slower than expected or "only slightly faster than for"; parfor scales poorly with the number of workers; ticBytes/tocBytes, the Parallel Pool dashboard, mpiprofile, or system tools show large per-worker data transfer; large broadcast variables or sliced inputs make iterations slow; opening a process pool dominates a short workload; user mentions serialisation or data transfer overhead. Also trigger on any question about whether code or a function works on a thread pool. For non-pool MATLAB performance work (vectorisation, preallocation, profiling), defer to matlab-optimize-performance.
Configures mise as the sole runtime and CLI tool manager for a project. Every mise.toml carries [settings] disable_backends = ["ubi", "asdf"] and lockfile = true, pins every version fully, commits mise.lock and .mise/locks/, routes Python CLIs through pypi (each on its own private Python, in its own venv, from a locked wheel-only graph) and Node CLIs through npm, and rejects competing managers (brew/nvm/asdf/volta/fnm/pyenv/ubi/pip/pipx/uv tool).
Guidelines for creating responsive email templates using MJML framework with .NET Razor syntax integration. Use when building responsive email templates in .NET applications, integrating MJML with Razor views, or creating email layouts that work across email clients.
This skill should be used when the user asks to optimize, export, serve, compress, or accelerate ML inference. PROACTIVELY activate for: (1) latency, throughput, p95/p99, batching, concurrency, KV cache, memory, or cost issues, (2) quantization INT8/INT4, GPTQ, AWQ, bitsandbytes, pruning, sparsity, distillation, (3) ONNX export, ONNX Runtime, TensorRT, TorchScript, torch.compile, XLA, OpenVINO, Core ML, TFLite, (4) Triton, TorchServe, TF Serving, BentoML, Seldon, KServe configuration, (5) edge deployment, CPU/GPU/TPU/Inferentia serving. Provides: hardware-aware inference optimization and safe benchmarking.
Guide for writing, refactoring, and testing MoonBit projects, including exclusive use of `.mbtx` for agent-authored automation. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/run/test/doc/ide etc.), or following MoonBit-specific layout, scripting, documentation, and testing conventions.
Integrate compiled NixieFX particle effects into PixiJS or Three.js applications using the public nixie-fx package. Use when an agent needs to install the runtime, load an out/vfx export bundle, implement texture or material providers, mount a renderer, drive effects from a game loop, inspect runtime diagnostics, or clean up NixieFX resources.
NocoBase 2 only; never use in a NocoBase 3 project. Use when users need to configure, inspect, test, or troubleshoot NocoBase notification management, including in-app message channels, email SMTP channels, workflow notification nodes, and notification send logs.
NocoBase 2 only; never use in a NocoBase 3 project. Use when a task provides a prototype to reproduce — an HTML file, an image, or a link, INCLUDING the published form "Build a NocoBase app — X … Match the layout and signature visuals of this reference prototype: <url>" — or when someone says a built page "doesn't match the prototype / looks monotone / is ugly". A prototype/URL being present is what triggers this skill, EVEN WHEN the same prompt also says "build an app" — the verb "build" does not cancel the prototype. Skip it only when there is NO prototype at all: a bare "build me a CRM/app" → nocobase-app-discipline; a one-field edit / rename → nocobase-ui-builder. It turns "here is the prototype, build it" into a faithful app — analyze prototype, native CRUD, the right native block per region, then a screenshot-vs-prototype visual loop. Native-first; JS only inside a native container; never a full-page JS block. Mechanics live in nocobase-ui-builder, nocobase-data-modeling, nocobase-app-discipline.
(NS) Autonomous execution engine — plans depth, resolves doubts from docs/specs, multi-agent work in an isolated worktree. Use for a local/pasted plan or "run this autonomously" without GitLab. Also Phase 2 under ns-execution-gitlab-issue (do not run standalone then). Not for single-step edits (ns-code-coder) or GitLab issues directly (ns-execution-gitlab-issue).
(NS) Orchestrate partitioned version implementation slice-by-slice — one subagent per slice, commit, auto-advance until done or stop. Use when version-roadmap.md has pending slices and the user asks to orchestrate/execute all slices. Do NOT use for non-partitioned versions, ad-hoc coding (ns-code-coder), or partitioning itself (ns-sdd-version-partitioner).
(NS) Generate or refresh lean architecture-rules.md for AI agents — stack, layout, patterns, constraints. Use when the user asks for architecture rules, .nextstage-harness/rules/architecture-rules.md, agent conventions, or "document how this repo works for the AI". Do NOT use for business specs (ns-harness-codebase-reverse-spec), brownfield maps (ns-harness-bootstrap-brownfield), or one-off Cursor rules without a full architecture pass.
(NS) Onboard an existing codebase into spec-driven planning — map stack, modules, rule adherence, and gaps without modifying code. Use when the user says analyze existing project, brownfield bootstrap, or before first requirements on a repo with code but no requirements. Outputs brownfield-map.md for ns-sdd-requirements-generator. Read-only on source code. Do NOT use for greenfield with no app code, architecture-rules generation, or writing requirements.md.
(NS) Full post-harness-init bootstrap in one session — architecture rules, sync, brownfield map, reverse business spec, project AGENTS.md. Use for "harness prepare", post-install setup, onboard brownfield, or running all prepare skills without separate slash commands. Do NOT use for greenfield with no app code, single-skill runs, or CLI-only baseline AGENTS.md.
C++ and Qt integration patterns for OBS Studio plugins. Covers Qt6 Widgets for settings dialogs, CMAKE_AUTOMOC, OBS frontend API, optional Qt builds with C fallbacks, and modal dialog patterns. Use when adding UI components or C++ features to OBS plugins.
Complete Odoo server lifecycle manager — run, deploy, initialize, and manage Odoo across local venv, Docker, and any IDE. Handles server startup/shutdown, environment initialization, database management, Docker orchestration, and IDE configuration for Odoo 14-19. <example> Context: User wants to start the Odoo server user: "Start the Odoo 17 server for my TAQAT project" assistant: "I will activate the virtual environment, locate the TAQAT17.conf config, and start the server with the correct addons path." <commentary>Server start trigger.</commentary> </example> <example> Context: User wants to stop the server user: "Stop the Odoo server" assistant: "I will find and kill the process on port 8069/8072." <commentary>Server stop trigger.</commentary> </example> <example> Context: User wants database backup user: "Backup the taqat17 database" assistant: "I will use pg_dump to create a backup of the taqat17 database with custom format." <commentary>Database operation trigger.</commentary> </example> <example> Context: User wants IDE configuration user: "Set up VSCode for my Odoo 17 project with debug configs" assistant: "I will generate .vscode/launch.json, tasks.json, settings.json, and extensions.json with Odoo-specific configurations." <commentary>IDE config trigger - generates full VSCode workspace setup.</commentary> </example> <example> Context: User wants to initialize a new environment user: "Initialize a new Odoo 17 environment with database" assistant: "I will create a venv, install requirements, configure PostgreSQL, generate .conf, and create the database." <commentary>Environment init trigger.</commentary> </example> <example> Context: User wants to create a new module user: "Create a new module called hr_overtime in the TAQAT project" assistant: "I will scaffold a complete module with models, views, security, and tests." <commentary>Module scaffold trigger.</commentary> </example> <example> Context: User wants to check if module is production-ready user: "Is my module ready for production?" assistant: "I will run tests, security audit, translation validation, and template checks to generate a GO/NO-GO verdict." <commentary>Quality gate trigger.</commentary> </example>
Diagnose and fix how slow a frontend feels and measures: optimistic UI for mutations, latency masking (skeletons, blur-up, preloading, staggering), request batching/deduplication, and Core Web Vitals (LCP/INP/CLS) remediation. Use when the user says 'the app feels slow', 'clicks feel laggy', 'improve performance', 'my Lighthouse score is bad', 'fix my Core Web Vitals / LCP / CLS', 'make saves feel instant', or when interactions visibly wait on the network. Produces a performance audit (findings ranked by user impact, with measured or user-reported evidence) plus the implemented fixes — optimistic mutation code, masking treatments, and network-layer improvements.
Creates and updates GitHub pull requests for cloudflare-docs changes. Load when asked to open, create, submit, update, or edit a PR, or write a PR title or description. Covers title conventions, branch naming, PR body structure, and the documentation checklist template.
Transform PRD (Product Requirements Document) into actionable engineering specifications. Creates detailed technical specs that developers can implement step-by-step without ambiguity. Covers data modeling, API design, business logic, security architecture, deployment, and agent system design. Use when: converting product requirements to technical specs, validating PRD completeness, planning technical implementation, creating task breakdowns, or defining test specifications. Triggers: 'PRD to spec', 'convert requirements', 'technical spec from PRD', 'engineering doc from requirements', 'validate PRD'.
Write production-ready print stylesheets. Covers @page rules, page breaks, visibility, color management, typography, images, links, tables, and framework-specific gotchas for Next.js/React/Tailwind. Use when the user asks to add print styles, make a page printable, or create a print-friendly layout.
Integrates Privy authentication, embedded wallets, and agent payment protocols into web and agentic apps. Covers React SDK (PrivyProvider, hooks, wagmi), Node.js SDK, smart wallets (ERC-4337), x402 and MPP machine payments, Tempo chain, and agentic wallets with policies. Use when setting up Privy auth, creating embedded or agentic wallets, adding x402 or MPP payments, integrating with Tempo, configuring wallet policies, or connecting Privy to MCP/Agent Auth flows.
Execute a comprehensive Python project health audit. Analyze the tech stack, architecture, API/interface design, data layer, testing, code quality, CI/CD, and documentation. Produce a shareable Markdown report with section scores and a weighted overall score. Use when the user asks to audit a Python project, run a health check, evaluate backend quality, or assess technical debt. Triggers on: 'python audit', 'python health audit', 'fastapi audit', 'django audit', 'flask audit', 'tech debt assessment', 'python health', 'python project quality', 'python quality check', 'python code review'.
Three.js materials in R3F, built-in materials (Standard, Physical, Basic, etc.), ShaderMaterial with custom GLSL, uniforms binding and animation, and material properties. Use when choosing materials, creating custom shaders, or binding dynamic uniforms.
Use when the user asks for new work such as a feature, component, integration, service or dependency, especially when the request names a solution instead of a problem, the scope looks larger than the user may expect, or the motivation is that other products have it
Game reverse engineering: Unity/Unreal, Cheat Engine, Lua script engines, graphics shaders. Triggers: game reverse engineering, Unity, Unreal, Cheat Engine, memory modification, anti-cheat, Lua, LuaJIT, .luac, .jsc, script engine, Shader, shader, SPIR-V, DXIL, DXBC, GLSL.
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.