Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
sprint.migration module — Version classes (up/down), HelperManager helpers, builders, migrate.php CLI, migrations.*.php configs. Use when writing or applying schema/content migrations, exporting iblocks/HL/options, or checking migration status.
Carbon language skill for C++ interop and toolchain. Use when evaluating Carbon syntax, bidirectional C++ interop, building carbon-toolchain, or comparing Carbon vs C++. Activates on queries about Carbon language, Carbon.h, carbon-toolchain, checked borrows, or C++ successor.
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers, implementing Sanctum auth flows, building Livewire components, optimising Eloquent queries, or writing Pest/PHPUnit tests for Laravel features.
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
Keep the Orca desktop app's workspace list honest about the git worktrees your workflow actually creates: link each one to its issue, keep its status current, and clean out the ones whose work already merged. Use when the user says "orcakit", "clean up my orca workspaces", "my Orca sidebar is full of finished work", "which workspaces are stale", "link my worktrees to their issues", "remove the workspaces for merged issues", or "where should Orca put new worktrees"
Use the `redmine` CLI to interact with Redmine. Activate when the user asks to create, list, update, close, or search issues, epics, or subtasks; log or view time entries; read or edit Redmine wiki pages; manage versions or memberships; query projects, users, or groups; or perform any Redmine project management task. Also activate when the user says “redmine,” “issue,” “ticket,” or “time entry,” pastes a Redmine URL (e.g. `.../issues/123`), or references Redmine workflows.
Find and explain official Tempo documentation for stablecoin accounts and payments, passkeys, fee sponsorship, TIP-20 issuance, the Stablecoin DEX, Earn, Routes, Zones, Machine Payments (MPP), Tempo EVM contracts, nodes and network upgrades, the Tempo API and indexer, SDKs, CLI tools, and partner integrations. Use when building on Tempo, integrating or reviewing Tempo code, or answering Tempo developer and protocol questions.
Use when configuring QueryClient, implementing mutations, debugging performance, or adding optimistic updates with @tanstack/react-query in Next.js App Router. Covers factory patterns, query keys, cache invalidation, observer debugging, HydrationBoundary, multi-layer caching. Keywords TanStack Query, useSuspenseQuery, useQuery, useMutation, invalidateQueries, staleTime, gcTime, refetch, hydration
Makes a Unity game look and feel finished: art style, lighting, juice, sound, menus, saves and look scoring. Use when building a new game's first playable version, or when a game looks like programmer art, feels flat or silent, or needs polish.
Create well-structured RFCs and technical proposals for software projects. Use this skill whenever the user wants to write an RFC, technical proposal, design doc, architecture doc, or system design overview. Also trigger when the user says things like "write an RFC", "I need to propose a new system", "create a technical proposal", "document the architecture", "write up the design", "I need a design doc", or "explain the system architecture in a doc". Even if they just say "RFC", "design doc", or "arch doc", use this skill. Covers both RFCs (proposing what to build) and architecture docs (documenting an existing codebase).
A workflow for synchronizing documentation, the website, and public skills for the weapp-vite monorepo. Use after source capabilities change to synchronize configuration, CLI, React/Wevu/Vue SFC, multi-platform support, mpcore, README, packaged docs, scaffold `AGENTS.md`, AI skills metadata, and regression trigger entry points.
Develop a new ESLint rule for @sap-ux/eslint-plugin-fiori-tools. Always use this skill when adding any rule to the plugin, implementing manifest.json/XML/CDS/flex-change validation, writing rule tests with project context, or creating rule documentation — even if the request sounds simple or the user doesn't mention 'ESLint' explicitly. Guides through the complete workflow: diagnostics constant, rule implementation, unit tests, docs, and registration.
Expert blueprint for fighting games including frame data (startup/active/recovery frames, advantage on hit/block), hitbox/hurtbox systems, input buffering (5-10 frames), motion input detection (QCF, DP), combo systems (damage scaling, cancel hierarchy), character states (idle/attacking/hitstun/blockstun), and rollback netcode. Based on FGC competitive design. Trigger keywords: fighting_game, frame_data, hitbox_hurtbox, input_buffer, motion_inputs, combo_system, rollback_netcode, cancel_system, advantage_frames.
Expert blueprint for puzzle games including undo systems (Command pattern for state reversal), grid-based logic (Sokoban-style mechanics), non-verbal tutorials (teach through level design), win condition checking, state management, and visual feedback (instant confirmation of valid moves). Use for logic puzzles, physics puzzles, or match-3 games. Trigger keywords: puzzle_game, undo_system, command_pattern, grid_logic, non_verbal_tutorial, state_management.
Expert blueprint for tower defense games (Bloons TD, Kingdom Rush, Fieldrunners) covering wave management, tower targeting logic, path algorithms, economy balance, and mazing mechanics. Use when building TD, lane defense, or tower placement strategy games. Keywords tower defense, wave spawner, pathfinding, targeting priority, mazing, NavigationServer baking.
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.
Implements comprehensive observability with OpenTelemetry tracing, Prometheus metrics, and structured logging. Includes instrumentation plans, sample dashboards, and alert candidates. Use for "observability", "monitoring", "tracing", or "metrics".
Create a release from dev branch. Generates changelog entries from commits, bumps version, and creates a PR to main. TRIGGERS - Use this skill when user says: - "/release" - create a patch release (default) - "/release minor" - create a minor release - "/release major" - create a major release - "make a release", "cut a release", "ship it", "release to main"
Research credible options for a technical decision and recommend one (a tool, library, framework, architecture, or service), grounded in primary sources with cited, dated evidence. Use when the user asks “which should I use, A or B,” “compare X and Y,” “evaluate options for Z,” “what’s the best tool/library/service for …,” “should we use X or Y,” “research X before we build,” or runs “/researchkit”—decision research that comes before a plan.
Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.
Use when you need to design or implement Kafka messaging in Spring Boot — including topic design, producer/consumer implementation, JSON serialization with Boot factory customizers, Testcontainers `@ServiceConnection` integration tests, retries and dead-letter topics, idempotency, and error handling. This should trigger for requests such as Add Kafka in Spring Boot; Review Spring Kafka consumers; Improve retries and DLT in Spring Kafka; Configure Spring Kafka topics serializers or listener containers; Add Spring Kafka dead-letter topic handling. Part of Plinth Toolkit
Build ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK. Use when creating ChatGPT apps, building MCP servers with widgets, defining React widgets, working with Apps SDK, or when the user mentions ChatGPT widgets, mcp-use widgets, or Apps SDK development
Accept, send, and manage ckBTC (chain-key Bitcoin). Covers BTC deposit flow via minter, ckBTC transfers, withdrawal to BTC, subaccount derivation, and UTXO management. Use when integrating Bitcoin, ckBTC, BTC deposits, or BTC withdrawals in a canister. Do NOT use for plain token transfers without BTC minting/withdrawal—use icrc-ledger instead.
Database sharding for PostgreSQL/MySQL with hash/range/directory strategies. Use for horizontal scaling, multi-tenant isolation, billions of records, or encountering wrong shard keys, hotspots, cross-shard transactions, rebalancing issues.
Maintain a project's domain model as a consented record of settled understanding: the CONTEXT.md overview and glossary of the ubiquitous language, and docs/adr/ decision records. Use when a domain term needs pinning down, when a hard-to-reverse trade-off decision gets settled, when the user says "update the glossary" or "write an ADR", or when another skill needs the domain model kept current; when the user says "set up CONTEXT.md" or "write the project overview"; or when the user asks "is CONTEXT.md still accurate" or says "audit the glossary".
Write and revise queries with the published HelixDB TypeScript SDK (`@helix-db/[email protected]`, Node.js 20+). Use for `readBatch`, `writeBatch`, traversal builders, direct `toQueryRequest`/`toQueryJson` payloads, projections, indexes, vector and BM25 search with traversal-scoped prefiltering, structured remote errors, and `Client.query`. Stored routes, registration, and query bundles are not v3 SDK APIs. When the target is Helix Cloud, always use helix-mcp first.
Use when migrating a Meteor 2.x application to Meteor 3.x. Triggers include callAsync, *Async Mongo, removed Fibers, implicit-global ReferenceError, lost Blaze reactivity, a publish function returning a Promise, a scheduler dropping a Promise, a read API receiving update modifiers, async allow/deny, an Iron Router controller not running, “Method stub took too long”, Atmosphere resolution, Express 5 WebApp handlers, lost async context, rawCollection callbacks, TypeScript declaration failures during upgrades, useTracker, and useSubscribe. Use this skill when the user asks about upgrading Meteor, async caller propagation, iterators with await, or replacing and forking packages. Standalone declarations and type-checking belong to meteor-typescript.
Use when migrating an existing Meteor app to Rspack (Meteor 3.4+), or upgrading Rspack 1 to 2 on Meteor 3.6 beta. Triggers on nested imports, mainModule entry points, server-only apps, replacing fourseven:scss / meteor/less / coffeescript / jorgenvatle:vite / zodern:melte with loaders, Svelte/TypeScript preprocessing or Lingui SWC plugin failures after upgrade, CommonJS default-import interop, module.exports in client graphs, Node built-ins in browser code, _build / build-assets / build-chunks, .meteorignore hiding handoff files, dynamic chunks under ROOT_URL, meteor.modules for CSS/HTML, resolve.symlinks or resolve.alias migration, automatic dependency updates and immutable CI/Docker builds. Use this skill when the user asks about migration compatibility or a build plugin's Rspack replacement. For new-app setup and rspack.config.js helpers, use meteor-modern-build-stack instead.
Generates complete starter repositories for various tech stacks (Next.js, Vite, Nest, FastAPI, etc.) with best-practice conventions, folder structure, baseline code, configs, scripts, and setup documentation. Use when users request to "scaffold a project", "create a starter repo", "initialize a new project", or specify a tech stack to begin with.
Implements React Server Components (RSC) patterns with Next.js App Router including data fetching, streaming, selective hydration, and server/client composition. Use when users request "server components", "RSC", "Next.js app router", "server-side rendering", or "streaming".
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
Sveltia CMS, a Git-backed content management system and successor to Decap/Netlify CMS. 5x smaller bundle (300 KB), GraphQL performance, and 260+ issues solved. Use for static sites (Hugo, Jekyll, 11ty, Gatsby, Astro, Next.js), blogs, docs, i18n, or when encountering OAuth errors, TOML/YAML issues, CORS problems, or content listing errors
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.