Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Automatic graph layout using dagre with React Flow (@xyflow/react). Use when implementing auto-layout, hierarchical layouts, tree structures, or arranging nodes programmatically. Triggers on dagre, auto-layout, automatic layout, getLayoutedElements, rankdir, hierarchical graph.
Django migration patterns and safety workflow for PostHog. Use when creating, adjusting, or reviewing Django/Postgres migrations, including non-blocking index/constraint changes, multi-phase schema changes, data backfills, migration conflict rebasing, and product model moves that require SeparateDatabaseAndState. Also use for any deletion or removal of a model, table, column, product, or app — including deleting migration files or retiring a feature — even when no migration is written.
Drizzle ORM for type-safe SQL with PostgreSQL, MySQL, and SQLite. Use when defining schemas, writing queries, managing relations, running migrations, or using drizzle-kit. Use for drizzle, orm, schema, query, migration, pgTable, relations, drizzle-kit, drizzle-zod.
Publish files or Obsidian notes as GitHub Gists. Use when user wants to share code/notes publicly, create quick shareable snippets, or publish markdown to GitHub. Triggers include "publish as gist", "create gist", "share on github", "make a gist from this".
Profiles Meta VR and Horizon OS application CPU performance using simpleperf — workload classification, CPU hotspot recording, kernel overhead measurement. Use when diagnosing whether an app is CPU-bound, memory-bound, or I/O-bound on Meta VR devices. Build paths: all Meta VR app stacks; use hz-quest-verify-first if the build path is unclear.
Use when integrating, generating, refactoring, reviewing, or debugging Make App record-list grouping with @qfei-design/make-app-group and @qfei-design/canvas-table GroupTableComponent. Triggered by 分组, 高级分组, 多级分组, 分组条件, 拖拽分组, 表头分组, 表头分组 openWithField, capabilities.groupable, Entity Preset group save/load/echo, record-groups, groupFilter, grouped leaf pagination, or grouping tests. Covers one integrated toolbar, CanvasTable grouped rendering, Entity Preset, Service group contracts, Make Data ListResources grouping mode, groupFilter expression composition, and leaf-record pagination. When make-app-actions is present, a successfully applied group must clear its selection and invalidate pending action work; draft edits and failures preserve selection. Does not own page shell/layout, CanvasTable internals, package internals, permission policy, auth, runtime packaging, DSL modeling, Make CLI execution, filtering, sorting, or cell editing.
A structured workflow for progressively migrating native WeChat, Alipay, Douyin, and other mini programs to `weapp-vite + 原生` or further upgrading to `weapp-vite + wevu + Vue SFC`. Covers six-platform single-target builds, preserving native file extensions, Web integration boundaries, migration path selection, tooling integration, SFC pilots, responsive upgrades, and rollback-capable validation.
NocoBase 2 only; never use in a NocoBase 3 project. **Opt-in DSL path** for NocoBase app building. Use ONLY when the user explicitly asks for YAML / DSL / committed-to-git / `cli push` / spec files — e.g. "use the DSL reconciler", "I want YAML I can commit", "build this as a workspaces/ project". For any other UI authoring request (new page, new block, tweak an existing screen), default to `nocobase-ui-builder` instead — this reconciler is still in active development and has rough edges that the live-UI path avoids. When the user opts in: produces/changes files under `workspaces/<project>/`, supports new pages, menus, modules, whole systems, collections, tables, sub-tables, popups, dashboards, approval workflows, recordActions, and deploys them via `cli push`.
Creates or updates a GitHub pull request for the current branch. Use when the user asks to publish committed branch changes as a PR or refresh the body of an existing PR. Do not use for draft-only PR copy, PR review, CI repair, review-comment fixes, or a push that does not include creating or updating a PR.
Brad Frost's Atomic Design methodology for UI component hierarchies: atoms (indivisible elements), molecules (small groups of atoms), organisms (complex sections of molecules), and templates (page layouts). Enforces bottom-up composition (never skip levels), presentational components (data via props, events via callbacks, no data fetching), design tokens for all visual properties, and composition over inheritance. Use when building user interfaces, creating component libraries, organizing frontend code, designing form systems, or structuring any UI. Triggers on: “build a component,” “component hierarchy,” “design tokens,” “presentational components,” “composition over inheritance,” “React/Vue/SwiftUI components,” “atomic design.” Applies to any UI framework.
Colyseus 0.18 multiplayer game servers and clients: rooms, Schema state synchronization, state callbacks, reconnection, matchmaking, client SDKs, and client-side prediction. Use when colyseus, @colyseus/schema, @colyseus/sdk, or colyseus.js appears in the task or package.json, before writing any Room or Schema code, and when a project contains pre-0.17 code such as getStateCallbacks(), Room<State> generics, onLeave(client, consented), @filter(), or new Server().
Provides comprehensive guidance for draw.io architecture diagrams including diagram creation, shapes, templates, and collaboration. Use when the user asks about draw.io architecture, needs to create architecture diagrams, design system diagrams, or collaborate on diagrams.
Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with /egm-draft.
Build RAG pipelines with Exa.ai for real-time web retrieval. Use when building retrieval-augmented generation, integrating Exa with LangChain, LlamaIndex, Vercel AI SDK, or implementing AI agents with web search capabilities. Triggers on: RAG pipeline, retrieval augmented generation, Exa LangChain, Exa LlamaIndex, ExaSearchRetriever, ExaSearchResults, Exa MCP, Exa tool calling, Claude tool use, AI agent web search, grounded generation, citation generation, fact checking, hallucination detection, OpenAI compatibility, chat completions.
Exa.ai search API integration for neural and keyword web search with content retrieval. Use when implementing web search features, integrating Exa SDK (exa_py, exa-js), or retrieving web content. Triggers on: Exa, exa_py, exa-js, neural search, web search API, search_and_contents, searchAndContents, find_similar, findSimilar, domain filtering, date filtering, text extraction, page summaries, highlights, search auto mode, fast search, search categories, livecrawl, excluding domains, include text, exclude text, EXA_API_KEY.
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.
Use when creating, extending, debugging, or publishing a Lightweight Charts™ plugin—a custom series, a series primitive, or a pane primitive—or when turning a chart idea (“I want the chart to show/draw X”) into a working plugin. Covers choosing the plugin type, scaffolding with create-lwc-plugin, building on @tradingview/lwc-toolkit instead of hand-rolled helpers, which official plugin packages to use as references, where the docs are, and the autoscale, whitespace, visible-range, hit-test, and conflation mistakes every plugin author makes once. Use whenever the user mentions a custom series, primitive, renderer, drawing on the chart canvas, lwc-plugin, plugin-examples, the toolkit, or the plugin catalog—even if they never say the word “plugin”.
Next.js 16 App Router performance, caching, server components, server actions, routing, and codebase-hygiene best practices — plus a category-major review/refactor algorithm with codebase-level (remove/dedup/reuse) findings. This skill should be used when writing Next.js 16 App Router code, configuring caching with 'use cache' or the previous fetch-cache model, building Server Components, setting up parallel/intercepting routes, configuring next.config OR proxy.ts, OR auditing/refactoring a Next.js codebase (single file or whole repo). This skill does NOT cover generic React 19 patterns (use vercel-react) or non-Next.js server rendering.
Guide for implementing Obsidian knowledge management - vault operations, plugin development, URI scheme automation, markdown extensions, and Local REST API integration. Use when working with Obsidian vaults, creating plugins, automating note workflows, querying notes via API, or implementing knowledge graph features.
Use when setting up or troubleshooting Rojo for Roblox: project.json configuration, Studio sync issues, file naming conventions (init.luau, *.server.luau), rojo serve/build/sourcemap commands, multi-environment setups (dev/staging/prod), or Wally/Aftman integration. Triggers include "rojo", "project.json", "sync", and "sourcemap".
Run existing ShinkaEvolve tasks with the `shinka_run` CLI from a task directory (`evaluate.py` + `initial.<ext>`). Use when an agent needs to launch async evolution runs quickly with required `--results_dir`, generation count, and strict namespaced keyword overrides.
Use when drafting or revising internal technical design docs, review notes, architecture writeups, or sharing posts in Chinese, especially when the tone should stay evidence-backed, calm, and suitable for peers or leaders rather than marketing or literary writing.
Generate viewable HTML or a complete spec for host consumption with VChart, modify and diagnose chart configurations, recreate styles from screenshots, and support React-VChart and chart interactions. Use for VChart chart generation, configuration, troubleshooting, and application integration.
Use when building widgets that extend Wix dashboard pages for first-party business apps. Triggers include dashboard plugin, dashboard slot, extend dashboard page, Wix Stores plugin, Wix Bookings plugin, Wix Blog plugin, observeState, dashboard widget. Do NOT use for standalone dashboard pages (use wix-cli-dashboard-page) or site-facing UI (use site widgets/site plugins).
Handle Wix Stores Catalog V1 and V3 SDK compatibility. Use when building any integration that interacts with Wix Stores products, inventory, orders, or collections. Triggers include Wix Stores, products API, inventory API, catalog version, productsV3, V1 vs V3, store products, queryProducts, getProduct.
Build reliable third-party API integrations, including OAuth, webhooks, rate limiting, error handling, and data sync. Use when integrating external services (Slack, Stripe, Gmail, etc.), building API connections, handling webhooks, or implementing OAuth flows.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components—not for simple single-file HTML/JSX artifacts.
Browser debugging, performance profiling, and automation via Chrome DevTools MCP. Use when user says "debug this page", "take a screenshot", "check network requests", "profile performance", "inspect console errors", or "analyze page load". Do NOT use for full E2E test suites (use playwright-skill) or non-browser debugging.
Auto-generates code flow diagrams from Python module analysis. Detects when architecture diagrams become stale (code changed, diagram didn't). Use when: creating new modules, reviewing PRs for architecture impact, or checking diagram freshness. Generates mermaid diagrams showing imports, dependencies, and module relationships.
Project planning and management with CodeSpring. Use when the user wants to work with CodeSpring projects, tasks, PRDs, mindmaps, or analyze a codebase for project planning. Handles workspace selection, project linking, task management, and syncing findings to CodeSpring.
Designs and builds ETL/ELT data pipelines. Takes data sources, destination, transformation requirements. Generates pipeline code (Python/SQL), scheduling config, error handling, monitoring setup, and data quality checks. Outputs data-pipeline-spec.md + implementation files.
Discovers business domains in a Swift codebase by tracing what users can DO — not by reading folder names or architecture docs. Maps each domain's vertical slice (Types → Config → Repo → Service → Runtime → UI), identifies providers (external SDK bridges), and separates cross-cutting concerns. Produces a domain map that drives all downstream decisions: folder structure, SPM targets, enforcement specs, migration plans. Use this skill whenever the user wants to understand their codebase domains, find what's cross-cutting vs domain-specific, restructure a Swift project, figure out where code belongs, or map a product's capabilities to architectural boundaries. Triggers on "what are my domains", "where does this belong", "map this codebase", "what's cross-cutting", "organize this project", "is this a domain or infra", "restructure this", "architecture review", or any request to understand the business domain structure of a Swift codebase.
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which experimentation platform, choose Statsig vs PostHog, evaluate experimentation tools, switch experimentation platform, migrate from Optimizely, consolidate experimentation tools, multi-platform experimentation, experimentation platform decision, ab test platform selection, feature flag platform vs experiment platform, warehouse-native experiments, vendor lock-in experimentation. Also triggers when a team is asking about cost, governance, or migration cost across experimentation tools, or when an evaluation is starting.
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.
Convert natural language questions into safe executable SQL to query Ascend PyTorch Profiler / msprof database for operator time consumption, communication, dispatch, and other performance data. Supports table schema extraction from official documentation. Use this skill when the user wants to: (1) analyze Ascend profiling database, (2) query operator performance data, (3) analyze communication and dispatch bottlenecks, (4) check table schema for profiling data. Trigger: user mentions "profiler db", "sqlite", "sql", "table", "schema", "ascend-pytorch-profiler", "msprof", "operator time", "communication time", "dispatch analysis", "性能分析", "算子耗时", "数据库查询", "性能数据", "性能瓶颈"
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.