Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Diagnose and fix 3+ genuinely independent failures concurrently on Claude Code’s real parallel agent runtime, without splitting one root cause into conflicting investigations. Proves failures do not share a root cause (same dependency/config/migration/deploy across traces) before launching, matches each lane to the best specialized agent, briefs it with real evidence (failing output, stack traces, test names), launches all lanes in one message with background execution and worktree isolation, then reruns each original failure and checks for conflicts. Refuses to parallelize fewer than 3 lanes or symptoms that may share a cause, consolidates lanes that converge on one root cause instead of claiming independent wins, and reports partial success honestly. Use when the user gives 3+ clearly independent failures to fix in parallel.
Diagnostica, sem alterar nada, se este computador e este repositório estão prontos para trabalhar com SDD: repositório git, agente de código, identidade do git, acesso ao remoto (credencial, rede, repositório ainda vazio), worktrees órfãs, dependências, editor e dado exposto (senha, certificado A1 ou chave privada já salvos no git; .env fora do .gitignore; npm sem ignore-scripts; repositório público). Responde em uma linha quando está tudo certo e, quando não está, lista o que impede primeiro, cada item com o comando exato que resolve. Use quando o usuário pedir para checar o ambiente, antes de abrir a primeira frente de trabalho num projeto, ou quando algo estranho acontecer (commit que falha, comando não encontrado, worktree que sumiu).
Opens an isolated work front in this repository: creates a git worktree outside the project folder, with a new branch based on the remote's UPDATED production branch, prepares the folder (dependencies, local files), and opens it in the editor. On first run, investigates the repository and writes its findings to sdd/ambiente.md. Use when the user says 'open a work front', 'new session', 'new isolated task', 'create a worktree for X', or wants to start a feature/fix without mixing it with another in progress.
Close a workstream and ship it to production with ONE approval point: it independently checks what will ship (syntax, tests, secrets in the diff, outdated base), shows once exactly what goes to production and whether the push publishes on its own, and only after the user's OK does it commit, integrate, publish and verify. Use from inside the workstream folder when the user says 'release', 'publicar', 'subir para produção', 'fechar a frente' or 'integrar'. It is the other end of the sdd-new-session skill.
Guide for building, auditing, and refactoring Swift code using modern concurrency patterns (Swift 6+). This skill should be used when working with async/await, Tasks, actors, MainActor, Sendable types, isolation domains, or when migrating legacy callback/Combine code to structured concurrency. Covers Approachable Concurrency settings, isolated parameters, and common pitfalls
Full-stack React framework built on TanStack Router. Type-safe routing, server functions, SSR/streaming, middleware, and multi-platform deployment. Use when building full-stack React apps with SSR, server functions, middleware, or authentication. Use for createServerFn, createMiddleware, beforeLoad, API routes, Cloudflare Workers, Vercel, Netlify deployment.
Sculpt reference-image objects into procedural Three.js models. Use for reconstruction feasibility, procedural build planning, code-native implementation, or animation-, collider-, and destruction-ready structure from one or more object views.
Comprehensive quality verification: spec compliance, linting, type-checking, tests, cross-layer data flow, code reuse, and consistency checks. Use after code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.
Build web3 applications, scripts, CLIs, bots, mobile apps, and desktop apps that need blockchain data via the Blockscout PRO API — a single HTTP API spanning 100+ EVM chains. Invoke this skill whenever the user wants to read blockchain data over HTTP (transactions, blocks, addresses, tokens, NFTs, logs, contract context, internal txs, account abstraction, etc.) and is building software that calls an API directly. Trigger on direct mentions of `Blockscout PRO API`, `pro-api`, `proapi_`, `Blockscout API`, `block explorer API`, `api.blockscout.com`, or on broader phrasing like "build a web3 app", "index/query on-chain data", "wallet history", "NFT inventory", "transaction logs across chains", "how much does the Blockscout API cost", "chain IDs supported by Blockscout". Use this skill for direct HTTP integrations; the sibling `blockscout-analysis` skill covers the Blockscout MCP Server.
Answer questions about the AI SDK and help build AI-powered features. Use when developers ask about Vercel AI SDK, generateText, streamText, ToolLoopAgent, useChat, providers, tools, structured output, embeddings, streaming, or adding AI to an app. First identify the installed major version and route version-specific work: use ai-sdk-7 for AI SDK 7 features/migrations such as WorkflowAgent, HarnessAgent, reasoning, runtime/tools context, toolApproval, telemetry, realtime, or v6-to-v7 upgrades; use ai-sdk-6 for v6 code.
Make Alpaca API clients resilient — rate-limit header handling, HTTP 429 backoff, exponential retry, bounded concurrency/worker pools, pagination loops, batch sizing, and timeouts. Use when building robust REST clients, bulk/cron jobs, or reconciliation sweeps against Alpaca in any language.
Ban `as` type assertions in a package via the `@typescript-eslint/consistent-type-assertions` lint rule, replacing them with compiler-verified type-safe alternatives. Use when enabling the assertion ban in a new package or fixing violations in an existing one.
Lean facilitator for creating, updating, and validating a product brief — the Analysis-phase foundation of the BMAD Method. Captures problem statement, target users, core features, goals, constraints, and success metrics. Use when the user says: "create a product brief", "I need a product brief", "let's do discovery", "help me define my product", "what problem are we solving", "capture our product vision", "update the product brief", "validate the brief", "check if the brief is complete", "run discovery", "start a product brief", "brainstorm the product", or "I want to plan a product". Supports three intents: - Create — guided discovery conversation that fills and writes the brief - Update — amends one or more sections in an existing brief - Validate — completeness check against all required sections Output is a planning artifact only — no code is written or run.
Use when making single-property CSS or Tailwind visual changes in Next.js App Router projects. Presents a floating control widget on the page so the user can tweak the value before it is persisted. Covers atomic style changes, live preview, and cleanup. Triggers on single CSS value or single Tailwind utility class modifications.
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Use this skill when the user wants to investigate a bug, defect, incident, or quality issue and find its root cause — including requests to run a "5 whys" analysis, write a postmortem, do a root-cause analysis (RCA), figure out why a bug reached production or slipped past code review/QA, set up a recurring defect-analysis routine, or run a daily/weekly quality-improvement (Kaizen) triage. Also known as the Dantotsu method (Sadao Nomura's Toyota-derived defect-analysis approach, adapted for software). Trigger even if the user doesn't name the method explicitly — e.g. "why did this bug get through code review", "a client reported a bug, help me analyze it", "I want to understand why this keeps happening", "write up a root cause report for this defect", or "help me prioritize which fixes to actually ship this week".
Use when persisting key-value preferences or small typed settings on Android or KMP with Jetpack DataStore — Preferences vs Typed (Proto/JSON) vs Room selection, the IOException and corruption-recovery error traps, serializers with corruption handlers, and the KMP factory with per-platform file paths. Triggers on DataStore, Preferences, PreferenceDataStoreFactory, DataStoreFactory, preferencesDataStore, Serializer, SharedPreferences-to-DataStore migration, or persistent settings work.
Domain-driven design complete workflow — event-storming-driven 6-step domain modeling process, aggregate design 5-principles + 6-rules, bounded context identification, entity/value object design patterns, domain event catalog, and code mapping. Use when user asks about domain modeling, 领域建模, aggregate design, 聚合设计, bounded context, 限界上下文, or needs to design DDD domain model.
Routes .NET/C# requests to the correct domain skill and loads coding standards as baseline for all code paths. Determines whether the task needs API, UI, testing, devops, tooling, or debugging guidance based on prompt analysis and project signals, then invokes skills in the right order. Always invoked after `using-dotnet` detects .NET intent. Do not use for deep API, UI, testing, devops, tooling, or debugging implementation guidance.
Explanation documentation patterns for understanding-oriented content — conceptual guides that explain why things work the way they do. Use when writing an explanation doc, conceptual guide, understanding/background doc, design rationale, or architecture explanation, or when asked how/why something works. Builds on the docs-style core writing principles.
Design system engineering aligned with Airbnb-DLS for Expo / React Native apps targeting web and native iOS, built on Unistyles v3, Reanimated, Skia, and FlashList. Use when building, reviewing, or refactoring shared UI, including design tokens, theming, variant-driven component APIs, typography, spacing, cross-platform web/iOS parity, native-feel performance, and complex surfaces such as calendars and drawing canvases (examples use a clinic app). Covers token architecture, theming, component API contracts (variants over style props), web/iOS parity (Unistyles `_web` hover/focus/cursor, Platform splits, one shared theme), the Unistyles styling engine, and governance. Trigger even when the user does not say “design system” but is creating or changing reusable React Native components, tokens, or theme code, or making a component behave natively on both web and iOS. Teaches how to build the design system; pair with expo-react-native-coder for features and expo-ios-hig for iOS native-feel decisions
Create distinctive, production-grade frontend interfaces with high design quality. Use when building or refining web components, pages, or apps (HTML/CSS/JS/React) with bold aesthetics, purposeful layouts, motion, and accessibility. Avoid generic AI-looking output.
Creates custom Magento 2 themes, child themes, and theme modifications. Use when developing themes, customizing frontend, implementing responsive design, or working with Luma/Blank themes. Masters frontend architecture, layout XML, templates, and performance optimization.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Design UIs in Pencil (.pen files) and generate production code from them. Use when working with .pen files, designing screens or components in Pencil, or generating code from Pencil designs. Triggers on tasks involving Pencil, .pen files, design-to-code workflows, or UI design with the Pencil MCP tools.
Develops resources for FiveM using the Qbox Project (qbx_core). Covers the exports-based API, bridge compatibility, Ox integration (ox_lib, ox_inventory), and best practices. Use when the user works with FiveM, Qbox, qbx_core, or mentions `exports.qbx_core`, `QBX.PlayerData`, or `ox_lib`.
Detect React and TypeScript maintainability smells across the whole component, hook, and module, explain the cost of each, and propose a fix with a source link. Covers prop and API design (naming, booleans, callbacks, variants, controlled state, generics, refs, styling, JSDoc), state and data flow (redundant state, stale closures, context and ref misuse), effects and lifecycle, component structure and hooks, rendering correctness (keys, mutation, impure renders, hydration, the leaked 0 from &&), accessibility and focus management, async handlers, error boundaries, unsafe HTML, TypeScript discipline (any, casts, untyped catch, exhaustiveness), and a cross-file duplication pass. Defers memoization and re-render performance to react-compiler and color literals to theme-colors. Use when reviewing or writing React components or hooks, auditing for maintainability, or asked to sniff, smell-check, lint, or clean up a codebase, folder, file, or pasted snippet. Respects native HTML attributes and library conventions.
Simplification audit or authorized codebase simplification whose stated objective is to remove accidental complexity. Use for evidence-backed deletion or consolidation of dead code, duplicate state, redundant APIs or layers, ownerless abstractions, obsolete compatibility or design records, and over-engineering in any language; also use for 代码简化 or 熵回收. Do not use for general code review, onboarding, style-only refactoring, or performance tuning.
Complete Java Spring Boot skill set for building enterprise applications. Includes modular architecture with optional components: PostgreSQL database with JPA/Hibernate + Flyway migration; Redis caching (optional); Kafka/RabbitMQ messaging (optional, choose one); JWT + OAuth2 authentication (OAuth2 optional); RBAC authorization (optional); TDD with Mockito; Spec-First Development with OpenSpec.
Expert SQL query writing, optimization, and database schema design with support for PostgreSQL, MySQL, SQLite, and SQL Server. Use when working with databases for: (1) Writing complex SQL queries with joins, subqueries, and window functions, (2) Optimizing slow queries and analyzing execution plans, (3) Designing database schemas with proper normalization, (4) Creating indexes and improving query performance, (5) Writing migrations and handling schema changes, (6) Debugging SQL errors and query issues
Diagnose unexpected Three.js WebGPU/TSL runtime, rendering, API, asset, or version behavior. Use for a concrete failure, a suspected upstream regression or known issue, or a choice among an application fix, released upgrade, bounded workaround, upstream report, and blocker.
Compile procedural buildings, cities, and semantic site assemblies in Three.js r185 WebGPU/TSL. Use for building massing and facades, city-scale architectural batching and LOD, or deterministic placement of heterogeneous site assets around architecture.
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.