Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Standardizes development environment setup across machines by generating tool version configs (Node, Python, Ruby), package manager configs (pnpm, Volta, asdf, mise), environment variable templates, and setup scripts with onboarding documentation. Use when users need to "setup dev environment", "standardize tooling", "configure version managers", or "create onboarding scripts".
Identifies domain modules, ownership boundaries, dependencies, and interfaces using Domain-Driven Design principles. Provides domain maps, bounded contexts, refactor recommendations. Use for "DDD", "domain modeling", "bounded contexts", or "service boundaries".
This skill guides building AI agent endpoints on EdgeOne Makers — five framework routes (DeepAgents, LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK), platform-injected `context.store` / `context.tools` / `context.sandbox`, conversation_id dual-channel routing, SSE streaming, and `agents/` vs `cloud-functions/` separation. It should be used when the user wants to create or review an AI agent endpoint on EdgeOne Makers — e.g. "build an agent on EdgeOne Makers", "create a Claude agent endpoint", "wire LangGraph into Makers", "stream LLM responses with SSE", "review my agent template", "use context.store / context.sandbox / context.tools". Do NOT trigger for plain Edge Functions, Cloud Functions, or middleware (those don't run AI logic — use edgeone-pages-dev instead). Do NOT trigger for deployment workflows (use edgeone-pages-deploy). Do NOT trigger for generic AI framework development outside an EdgeOne Makers project.
Call use_skill as your first and only action when the user asks to run, start, or debug a Mule application. This includes executing applications in run or debug mode. Trigger phrases include “run my project,” “run all projects,” “debug my project,” “debug all my projects,” “start the app,” “run <project-name>,” and “debug <project-name>.” When you call use_skill, it must be the only tool call in that response.
Establishes git workflow guardrails including conventional commits, commit message hooks, branch naming conventions, PR templates, and code review processes. Provides hook configurations, workflow templates, and emergency bypass instructions. Use when users request "setup git hooks", "enforce commit conventions", "add PR templates", or "standardize git workflow".
Automated factory for converting GitHub repositories into specialized AI skills. Use this skill when the user provides a GitHub URL and wants to "package", "wrap", or "create a skill" from it. It automatically fetches repository details, latest commit hashes, and generates a standardized skill structure with enhanced metadata suitable for lifecycle management.
Data-driven resource harvesting (mining, logging, foraging) for Godot 4: apply_hit tool/tier validation via HarvestToolData enums, HarvestResourceData yields, harvestable_node shake/deplete, respawn_manager world persistence, UNIX offline progress, autosave, and noise vein proc-gen. Trigger keywords: apply_hit, HarvestResourceData, HarvestToolData, offline UNIX, respawn_manager, tool tier, harvestable_node, FastNoiseLite veins.
Expert blueprint for party games including minigame resource system (define via .tres files), local multiplayer input (4-player controller management), asymmetric gameplay (1v3 balance), scene management (clean minigame loading/unloading), persistent scoring (track wins across rounds), and split-screen rendering (SubViewport per player). Use for Mario Party-style games or WarioWare collections. Trigger keywords: party_game, minigame_collection, local_multiplayer, asymmetric_gameplay, split_screen, dynamic_input_mapping.
Use when planning legacy system migrations, codebase modernization, monolith decomposition, microservices consolidation, cross-language rewrites, or framework upgrades. Invoke for strangler fig pattern, incremental migration strategy, or refactoring roadmaps. Do NOT use for domain analysis (use domain-analysis), component sizing (use component-identification-sizing), or step-by-step decomposition plans (use decomposition-planning-roadmap).
Systematically investigates, diagnoses, and resolves complex Magento 2 technical problems. Use when debugging issues, investigating bugs, analyzing performance problems, resolving errors, or troubleshooting system failures. Masters log analysis, performance profiling, and root cause analysis.
Implement or debug JavaScript language behavior, including promise completion, async iteration, mutation, and runtime compatibility. Use for ECMAScript semantics or polyfill/transform choices; not for unrelated framework or TypeScript type design.
For frontend engineers authoring UI — how to make components reliably locatable by tests and AI agents. Covers the official Playwright locator priority, semantic/accessible markup first, and how to add valid, unique, stable `data-testid` attributes (naming convention, uniqueness in lists, stability rules) for React, Vue, Angular, and Svelte. Use when writing or reviewing components, or when an agent needs durable locators.
Creates GitHub pull request templates, issue templates, and discussion templates with proper YAML configuration. Use when users request "PR template", "issue template", "GitHub templates", "pull request template", or "contribution guidelines".
Install and configure Prelude (darkmatter/prelude) in any repository — run the setup wizard, wire it into an existing or new flake (the flake-parts module, or prelude.lib.evalModule for blueprint and other flakes), activate packages.prelude-shell in the devshell, and verify with real smoke checks. Use for adding devshell UI (MOTD, x command picker, docs viewer, themed prompt), integrating the generated prelude.nix sidecar, or activation questions (nix develop, direnv, lorri).
Use when authoring or editing Justfile recipes in a repository wired to Prelude, when the user asks to add just recipes or make them discoverable in the x menu, or when a recipe needs descriptions, typed arguments, groups, aliases, or module namespacing. Covers recipe authoring for Prelude's runtime Justfile import and verification through x.
React performance optimization guidelines. Use when writing, reviewing, or refactoring React components, hooks, effects, data fetching, or bundle optimization. Includes useEffect best practices — when NOT to use effects and better alternatives. Triggers: "when writing React code", "reviewing a React PR", "why is this component re-rendering", "reviewing code for performance issues", "optimizing bundle size".
Use when structuring Godot 4.7 game code: folders, scenes and nodes, signals or an event bus autoload, custom Resources for item data, components (health, hitbox, hurtbox), an inventory, save and load, InputMap and key rebinding for keyboard, mouse and gamepad, GDScript static typing and style, or GDScript vs C#; or when code is spaghetti, a folder scan breaks in the export, a save loads wrong, the gamepad does nothing, or @onready is null.
Enforces consistent structured logging with request correlation IDs, standardized log schema, middleware integration, and best practices. Use for "structured logging", "log standardization", "request tracing", or "log correlation".
Use when implementing iOS 17+ SwiftUI patterns: @Observable/@Bindable, MVVM architecture, NavigationStack, lazy loading, UIKit interop, accessibility (VoiceOver/Dynamic Type), async operations (.task/.refreshable), or migrating from ObservableObject/@StateObject.
Advanced Vite 8 patterns including Rolldown-powered builds, advancedChunks, Environment API, plugin development, SSR configuration, library mode, and build optimization. Use when customizing build pipelines, creating plugins, or configuring multi-environment builds.
Generate and maintain a project's reader-facing documentation in-repo (getting-started, how-to guides, architecture overview, runbooks), every command verified against the code, in four modes: init, update, audit, and an opt-in publish that mirrors the set to the GitHub wiki. Use when the user says "write docs for this project", "update the docs", "our docs are stale", or "sync the docs to the GitHub wiki". Not an agent handoff, and not the glossary or ADRs.
Test-driven development for behavior that a unit test cannot reach: write the expectation against the running app before writing the code. Declare the consequence first, watch it fail, implement, then watch it pass. Use when building a user-facing feature, when the user asks for TDD on UI or full-stack work, when a unit test cannot express the outcome that matters, or when you want a red-green loop that runs against the real app instead of mocks.
Production-tested setup for Base UI (@base-ui-components/react), MUI's unstyled, accessible React component library that uses a render prop API instead of Radix's asChild pattern, with Floating UI positioning. Covers installation, component patterns (Dialog, Select, Popover, Tooltip, NumberField, Accordion), Radix UI migration, Tailwind v4 and shadcn/ui styling, Cloudflare Workers deployment, and workarounds for known v1.0.0-beta issues. Use when setting up Base UI in a Vite + React project, migrating from Radix UI, building accessible headless components with full styling control, debugging popup or positioner placement issues, or judging Base UI beta API stability before adopting it
Superseded by the web CLI: attach to an already-running Chrome with `web browser attach <cdp-url>`, then drive it with `web browser eval|run|cdp|screenshot`. Use when the user asks to attach to, connect to, or control an existing Chrome running with --remote-debugging-port
Optimize Core Web Vitals (LCP, INP, CLS) for a better page experience and search ranking. Use when asked to “improve Core Web Vitals,” “fix LCP,” “reduce CLS,” “optimize INP,” “optimize page experience,” or “fix layout shifts.” Focuses specifically on the three Core Web Vitals metrics. Do NOT use for general web performance (use perf-web-optimization), Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).
Helps implement coss UI components correctly. Use when building UIs with coss primitives and patterns (buttons, dialogs, selects, forms, menus, tabs, segmented controls, inputs, toasts, etc.), migrating from shadcn/Radix to coss/Base UI, composing trigger-based overlays, or troubleshooting coss component behavior. Covers imports, accessibility, Tailwind styling, and common pitfalls.
Creates Architecture Decision Records (ADRs) to document significant architectural choices and their rationale for future team members. Use when the user says "write an ADR", "document this decision", "record why we chose X", "add an architecture decision record", "create an ADR for", or wants to capture the reasoning behind a technical choice so the team understands it later. Do NOT use when the decision hasn't been made yet (use create-rfc instead), for implementation planning (use technical-design-doc-creator), or for general documentation.
Find out why something in a running web app does not work, when the console is empty and the code looks correct. Reads the click, the request, the store and the console together and returns the file:line to open. Use when a button does nothing, a form will not submit, data will not load, a page renders blank or stale, a modal will not close, or the user says "it's broken" and the code review says it is fine.
Manages Drupal contributed modules via Composer: module updates and major-version upgrades, cweagans/composer-patches v2 (patches.lock.json, composer patches-relock, verifying patches are applied), mglaman/composer-drupal-lenient, Drupal 11 compatibility checks with upgrade_status, committing an optimized vendor/ autoloader, and contributing fixes back to drupal.org via issue forks and merge requests. Use when updating or upgrading contrib modules, applying, finding, or creating patches, a patch fails or keeps regressing after composer install, resolving Composer dependency or drupal/core version conflicts, checking Drupal 11 readiness or deprecations, or contributing to a drupal.org issue queue.
Creates consistent error handling with custom error classes, HTTP status mapping, structured logging, safe client messages, and error taxonomy. Use when standardizing "error handling", "logging", "error responses", or "exception management".
Best practices for building Gadget apps. Use for Gadget-specific models, fields, actions, routes, access control, Shopify/BigCommerce integrations, frontend patterns, API client usage, internal API usage, webhooks, background jobs, testing, deployment, ggt CLI workflows, environment sync, logs, problems, and parallel agent development loops.
Expert blueprint for open world games including chunk-based streaming (load/unload regions dynamically), floating origin (prevent precision jitter beyond 5000 units), HLOD (hierarchical LOD for distant meshes), persistent state (track entity changes across unloaded chunks), POI discovery systems (compass, markers), and threaded loading (prevent stutters). Use for RPGs, sandboxes, or exploration games. Trigger keywords: open_world, chunk_streaming, floating_origin, HLOD, persistent_state, POI_discovery, threaded_loading.
Full GSAP v3 mastery for interactive websites: core tweens/timelines, eases, staggers, keyframes, modifiers, utilities, plus complete plugin coverage (ScrollTrigger, ScrollTo, ScrollSmoother, Flip, Draggable, Inertia, Observer, MotionPath, DrawSVG, MorphSVG, SplitText, ScrambleText, TextPlugin, Physics2D/PhysicsProps, CustomEase/Wiggle/Bounce, GSDevTools). Includes Next.js/React patterns (useGSAP, gsap.context cleanup), responsive matchMedia, reduced-motion accessibility, performance best practices, and debugging playbooks.
nginx C module performance optimization and reliability guidelines based on the official nginx development guide. This skill should be used when optimizing nginx C modules for throughput, latency, memory efficiency, and operational resilience. Triggers on tasks involving buffer optimization, connection tuning, shared memory contention, error recovery, timeout strategy, caching implementation, worker process tuning, or logging performance in nginx C modules.
Systematic planning for medium-to-large tasks. Gathers context, identifies domain skills, and writes phased plans to brain/plans/. Does NOT implement. Use for new features, multi-file refactors, or architectural changes—not small fixes. Triggers: “plan this”, “break this down”.
Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Generates 4 interconnected docs — SPECIFICATION.md, IMPLEMENTATION.md, TASKS.md, BRANDING.md — plus a self-contained PROMPT.md for autonomous execution by any coding agent. Includes interactive tech stack selection, design pattern recommendations, and architecture decisions with trade-off analysis. Trigger when user wants to: plan a project, create specs, architect a system, break work into tasks, choose a tech stack, get design pattern advice, generate a coding agent prompt, or do documentation-first development. Phrases: "plan my project", "spec this out", "architect", "help me plan", "what stack should I use", "generate a prompt", "break this into tasks", "project docs", "I want to build X".
Rebuild an existing site's pages with byte-faithful content on a separately-defined donor design system — another live site, or local static HTML prototypes (Figma donors are contract-defined, not yet implemented). Content fidelity is gated byte-level (text, ordered images, SEO metadata); design application is flexible (content re-laid-out onto donor modules). Use when the user says “reskin my site with this design”, “apply this design system to my content”, “restyle my site to look like <other site>”, “new design, same content”, “rebrand my site using these prototypes”, or names a content site plus a design donor. NOT for redesigning from intent (that's the stardust core extract/direct/prototype chain) and NOT for keeping the current design while migrating (that's the replica flow)
Use when building gameplay systems in Godot 4.7: enemy AI that patrols, chases and attacks, state machines, behavior trees (LimboAI), NavigationAgent3D pathfinding and avoidance for 100 to 1000 enemies, 'agents stack up' or 'path is empty', hitbox and hurtbox combat, fast bullets going through walls, save and load, inventory, quests, dialogue (Dialogue Manager), input remapping, procedural dungeons, or measuring agent counts and frame time headless.
Use when you need MongoDB persistence in Micronaut — including @MongoRepository design, document modeling, indexes, query patterns, and error handling. This should trigger for requests such as Add MongoDB in Micronaut; Review Micronaut Data Mongo design; Improve error handling for Micronaut Mongo operations; Model MongoDB documents for a Micronaut service; Configure Micronaut MongoDB codecs indexes or transactions. Part of Plinth Toolkit
Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic engineering books. Triggers when: user wants an overall quality assessment, asks "how healthy is this codebase?", "run all the checks", "I need a health score before the release", or wants to onboard a new team with a quality overview. Do NOT trigger for: server health checks, HTTP health endpoints, Kubernetes liveness/readiness probes, database health, or application uptime. Also do not trigger when the user specifically requests only one dimension — use the corresponding focused skill instead (brooks-review / brooks-audit / brooks-debt / brooks-test).
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up the whole project", or asks for a single command that both diagnoses and remediates quality problems. Do NOT trigger for: read-only audits or health reports where the user only wants findings without code changes; single-dimension reviews (use the focused skill instead: brooks-review / brooks-audit / brooks-debt / brooks-test); server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Not an accessibility surveyor's opinion and not legal advice. Implement Israeli web accessibility compliance per IS 5568 standard, which is WCAG 2.0 AA plus Israeli national changes, for Hebrew RTL applications. Use when the user asks about Israeli accessibility law, "negishot" (accessibility), IS 5568, "teken negishot" (accessibility standard), "nachim" (disabilities), Hebrew screen reader support, RTL ARIA patterns, or accessibility audits for Israeli websites. Covers mandatory legal requirements under the Equal Rights for Persons with Disabilities Act, who is exempt, enforcement and penalties, the accessibility coordinator role, Hebrew screen reader compatibility (NVDA, JAWS, VoiceOver), native mobile apps, and RTL-specific ARIA patterns. Do NOT use for general WCAG guidance without Israeli context (use standard a11y resources instead), or for building a self-hosted accessibility preferences widget (use wcag-accessibility-widget).
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.