Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
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).
Guide to creating and managing Model Context Protocol (MCP) servers. How to add custom tools. When to use: (1) when you want to add custom tools to Claude Code, (2) when integrating external services, (3) when you want to build project-specific automation tools, (4) when you want to know how to configure an MCP server. Trigger examples: "create an MCP server", "add a custom tool", "MCP config", "turn an external API into a tool", "test runner MCP".
Turn an app idea or an existing React Native app into a Nav Read - tab structure, route tree, push/modal/sheet decisions, deep links, Android back plan - without building any screens. Use when planning navigation for a new app, restructuring an existing app's navigation, or deciding whether something is a tab, a push, a modal, or a bottom sheet. For building the screens afterward use mobile-taste; for full-app visual redesign use mobile-redesign-app.
Detects and modernizes outdated Move V1 syntax, patterns, and APIs to Move V2+. Use when upgrading legacy contracts, migrating to modern syntax, or converting old patterns to current best practices. NOT for writing new contracts (use write-contracts) or fixing bugs.
Style adaptation development guide for Mpx cross-platform output to RN (referred to as Mpx2RN or Mpx2DRN). Must be invoked when the user's question or context contains all three key elements of Mpx, RN, and styles, e.g. Mpx2RN style adaptation, Mpx2RN style errors. Should not be invoked when the user's question does not involve Mpx cross-platform output to RN or is unrelated to styles, e.g. Mpx mini program output issues, RN-related issues.
(NS) Diagnose a product bug report (screen, expected vs actual, ticket, screenshot description) by tracing the reported flow across every layer the consumer stack has. Chat-only eight-section report, then auto-dispatch ns-execution-gitlab-issue (ISSUE_URL) or ns-coder unless the user opted out (diagnose-only / do not fix). This skill does not write the patch. Use whenever the user pastes a relato, issue, ticket, screenshot description, "what is happening", "diagnose this", expected vs actual on a screen, or /ns-bug-report-diagnosis — even if they never name this skill. Do NOT use if they asked to implement/fix now without a screen story (ns-coder), to execute a GitLab ISSUE_URL as the first skill (ns-execution-gitlab-issue), for stack/CI/log with no screen story (ns-investigator), or for DB-only inspection when the consumer has a DB skill
(NS) Reverse-engineer a brownfield/legacy codebase into a technology-agnostic business description — rules, actors, permissions, lifecycles, integrations (no implementation detail). Use whenever the user mentions brownfield, legacy, modernization, reverse engineering, engenharia reversa, or extracting business rules from code. Do NOT use for code review, bug fixes, or technical architecture docs.
Invoke OpenCode CLI as a sub-agent to leverage alternative AI models (GPT-5.x, Codex, local models) for code implementation, review, debugging, research, and second opinions. Use when the user asks to "use opencode", "get a second opinion from GPT/Codex", "implement with opencode", "review with opencode", "let opencode handle this", "use a different model", or wants cross-model validation. Also triggers when the user explicitly names an OpenCode model (e.g., "use gpt-5.4", "use codex") or wants to delegate a task to a non-Claude AI system. Supports all providers configured in the user's OpenCode installation (OpenAI, GitHub Copilot, local models via Ollama/LM Studio, and OpenCode's own free-tier models).
Autonomous multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tasks, dispatches parallel agents (subagents or Agent Teams), audits completions, and ships PRs. Registry-driven — works for any user with a configured project registry.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Internal machine-result contract for headless agentic-workflow drivers. The executable source is @gtrabanco/agentic-workflow-schema: strict Envelope v2 for workflow-status, compact SkillOutcome v1 for driven work, compatibility parsing, and deterministic document snapshots. Not a menu entry.
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml, pr-check-changelog.yml, pr-conflict-checker.yml, labeler.yml, or CODEOWNERS.
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.
Keep README files in sync with the repo using symbolic HTML comments. Use this skill whenever making a repo change that could affect documentation — code (exported APIs, configuration, examples, CLI commands, dependencies), repo structure (adding/removing/renaming files, directories, packages, or other sibling entries referenced by a listing comment), or metadata (package.json, manifests). Also use when authoring or editing README files to add or update symbolic comments. Trigger on any change — code or structural — that touches a construct referenced by an HTML comment in a markdown file.
Guides Redis usage including data structures (strings, hashes, lists, sets, sorted sets), caching patterns, pub/sub, persistence (RDB/AOF), clustering, and Lua scripting. Use when the user needs to implement caching, session storage, rate limiting, queues, or any Redis-based data layer.
Refactor Flutter/Dart code to improve maintainability, readability, and performance. This skill applies Dart 3 features like records, patterns, and sealed classes, implements proper state management with Riverpod or BLoC, and uses Freezed for immutable models. It addresses monolithic widgets, missing const constructors, improper BuildContext usage, and deep nesting. Apply when you notice widgets doing too much, performance issues from unnecessary rebuilds, or legacy Dart 2 patterns.
Reverse engineer Unity games and apps built with IL2CPP or Mono, using Il2CppDumper, Il2CppInspector, and dnSpy. Use when an APK or IPA contains global-metadata.dat, libil2cpp.so, UnityFramework, or Assembly-CSharp.dll, when jadx shows only UnityPlayerActivity, or when the target is described as a Unity build.
Analyzes a codebase's modularity imbalances using the Balanced Coupling model and produces a review of design issues. Use when reviewing existing code for coupling problems, assessing architecture quality, identifying distributed monolith risks, or finding areas where changes are unexpectedly expensive.
High level overview of Space Engineers (version 1) related development. Start here to understand the ecosystem (game client, dedicated server, Pulsar, Magnetar, Torch, PluginHub, MagnetarHub, Quasar) and to route to the right se-dev-* skill for in-game scripts, mods, plugins, the Magnetar PluginSdk, and decompiled code/handbook reference.
Make Sentry stack traces readable—upload source maps for JavaScript/TypeScript, or debug files for native and mobile (dSYM, ProGuard/R8, NDK symbols, Dart obfuscation maps, .NET PDBs). Use when frames in Sentry show minified names, bundled paths, hex addresses, “unknown”, or method names with no file/line, instead of your original source.
Set up Husky pre-commit hooks in the current repository, integrating lint-staged (Prettier), type checking, and tests. Use when users want to add pre-commit hooks, set up Husky, configure lint-staged, or add formatting/type checking/tests on commit.
Build, review, migrate, and deploy Salesforce Multi-Framework React or Angular apps as UIBundle metadata. Use for uiBundles, ui-bundle.json, Data SDK and GraphQL integration, internal apps, Experience Cloud app containers, microfrontend embedding, ACC, localization, or UIBundle packaging. Also use when choosing Multi-Framework versus LWC. Pure LWC or generic Apex work does not require this skill.
How to correctly insert overlay elements when the host is slotted inside a shadow DOM. Covers the parentElement trap, assignedSlot pattern, and the connectedCallback timing hazard. Use when inserting overlays, portals, or absolutely-positioned siblings of slotted elements.
Maintain and author Editframe's skills-as-docs system. Covers file structure, frontmatter schemas, rendering conventions (html live demos, callouts, API metadata), the generation pipeline, and build/push workflow. Use when creating or editing skill files, reference documentation, frontmatter, html live blocks, API metadata, or working on the skills web renderer.
Use this skill first for any SpacetimeDB task; it routes to focused skills for modules, tables, reducers, procedures, views, clients, subscriptions, CLI commands, auth, RLS, HTTP APIs, SQL, deployment, serialization, tutorials, quickstarts, and upgrades. Triggers on: spacetime, spacetimedb, SpacetimeDB, stdb, module, reducer, table, procedure, view, subscription, DbConnection, spacetime generate, spacetime publish, spacetime sql, BSATN, SATS, row-level security, RLS, Maincloud, standalone, Unity, Unreal.
Spring Modulith for modular architecture in Spring Boot 3.x. Covers module structure, API vs internal packages, inter-module events, module testing, documentation generation, and observability. USE WHEN: user mentions "spring modulith", "modular monolith", "@ApplicationModule", "module boundaries", "inter-module events", "@ApplicationModuleTest", "modular architecture" DO NOT USE FOR: simple applications - unnecessary complexity, microservices - use proper service boundaries, existing tightly coupled monoliths - requires significant refactoring
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
Guided, jargon-free starting point for people with no schema and no database yet — a short 7-question wizard that turns "I want to build an app" into a concrete engine recommendation and a first data model. Zero artifacts required. Use when the user has nothing to audit, asks how to begin, says they're not technical, or doesn't know what database or schema they need.
Load PROACTIVELY when task involves application state, data fetching, or form handling. Use when user says "manage state", "add data fetching", "set up Zustand", "handle form validation", or "add React Query". Covers server state (TanStack Query with caching, optimistic updates), client state (Zustand stores), form state (React Hook Form with Zod validation), URL state (search params, routing), and choosing between state solutions.
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.