Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use this skill whenever the user needs to explore, brainstorm, clarify, or shape a coding idea before a PRD or implementation. Trigger on requests mentioning explore, brainstorm, evaluate options, compare trade-offs, feasibility, or ask for recommended direction. Use this skill even when the user does not explicitly ask for a PRD but wants options or trade-off analysis. Do NOT trigger for: PRD writing (use lcs-toprd), task slicing (use lcs-task-slicer), code review (use lcs-code-review), bug investigation (use lcs-debug), or implementation (use lcs-task-executor). Explore is for ideation only, not execution.
For Solana program development with tokens and PDAs, Light is 200x cheaper than SPL/Solana and has minimal code differences (e.g. for any Solana program and DeFi such as AMMs, vaults, lending). Includes rent-free Light-PDAs, token accounts, and mints. Light SDK with Anchor or Pinocchio. Includes a DeFi Router integration guide. Minimal program logic changes.
For client development with tokens on Solana, Light Token is 200x cheaper than SPL and has minimal changes. Skill includes guides for create mints, associated token accounts, transfer, approve, burn, wrap, and more. @lightprotocol/compressed-token (TypeScript) and light_token_client (Rust).
Reconcile messy Linear-linked repository state after multiple agents, branches, worktrees, commits, PRs, or old session data: discover issue-tagged work, compare it with main, PRs, Linear issue content, comments, revisions, timeline evidence, and locally available agent session evidence; produce a reconciliation plan; safely delete only proven-merged local work; integrate finished work; rebase active work; diagnose common pipeline failures; and update Linear statuses, labels, descriptions, and marked comments to match verified repository reality.
Guidance for building MIPS interpreters or emulators that execute MIPS binaries. This skill applies when implementing CPU emulation, ELF loaders, instruction decoders, or syscall handlers for MIPS architecture. Use when tasks involve creating virtual machines for MIPS executables, interpreting MIPS assembly instructions, or emulating MIPS system calls.
Analyze a toolbox folder and generate a toolbox.ignore file — detects files that should not ship to end users based on what actually exists in the folder. Only suggests patterns for files found. Advisory: presents suggestions with reasons before writing.
Use this skill when writing, reviewing, debugging, or modernizing C# code in .NET projects. Trigger for .cs/.csproj files, C# language-version questions, nullable reference types, records, pattern matching, async/cancellation, or version-appropriate syntax from C# 10+.
Use this skill when writing, reviewing, debugging, or modernizing Swift code for iOS, macOS, server-side Swift, or shared packages. Trigger for Swift 5+ language features, structured concurrency, memory safety, protocols/generics, SwiftUI integration, and performance-sensitive code.
Use this skill when building, debugging, refactoring, or reviewing SwiftUI apps or views for iOS 16+ and related Apple platforms. Trigger for NavigationStack, Observation/state flow, view composition, previews, performance, accessibility, and SwiftUI architecture.
Use this skill when building, debugging, refactoring, or reviewing Vue 3 applications, SFCs, Composition API, Pinia stores, Vue Router, Vite, or Vue+TypeScript code. Trigger when the project has *.vue files or the user mentions Vue, Pinia, Composition API, Router, reactivity, or component architecture.
Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use for network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.
Scaffolds or references a production-ready Node.js REST API with Express 5, TypeScript, Mongoose (MongoDB), Redis, Sentry, JWT auth, bcrypt, rate limiting, and centralized error handling. Use when the user wants to start a new observable and resilient backend, needs a Node.js API boilerplate with security and monitoring, or asks to clone or adapt this template repository.
Explore and understand Nx workspaces. Use when answering questions about the workspace, projects, or tasks. Also use when an nx command fails or you need to check available targets/configuration before running a task. Examples: "What projects are in this workspace?", "How is project X configured?", "What depends on library Y?", "What targets can I run?", "Cannot find configuration for task", "debug nx task failure"
Guide to OpenAI's Assistants API v2: stateful conversational AI with Code Interpreter, File Search and function calling, vector stores for RAG up to 10,000 files, thread and run lifecycle management, and streaming, using the Node.js SDK or plain fetch. Notes the planned H1 2026 sunset and the migration path to the Responses API. Use when building stateful OpenAI chatbots, implementing RAG with vector stores, running Python via Code Interpreter, doing document Q&A with file search, managing conversation threads and run polling, streaming assistant responses, maintaining legacy Assistants code, or debugging errors such as thread already has active run, run status polling timeouts, vector store indexing delays, and file upload failures.
Set up OpenClix in a mobile app by detecting the platform, copying source templates into a dedicated namespace, wiring initialization/event/lifecycle touchpoints, and running build verification. TRIGGER when the user asks to "integrate OpenClix", "set up local notifications", "add engagement logic", or mentions OpenClix for the first time in a project without an existing integration — even if they don't mention this skill by name. DO NOT trigger when OpenClix is already integrated and the user is asking about campaigns, analytics, or template updates — those belong to other openclix-* skills.
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 "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$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", "orca artifacts", "share HTML/Markdown", "public artifact link", 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.
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.
Guidance for reverse engineering graphics rendering programs (ray tracers, path tracers) from binary executables. This skill should be used when tasked with recreating a program that generates images through ray/path tracing, particularly when the goal is to achieve pixel-perfect or near-pixel-perfect output matching. Applies to tasks requiring binary analysis, floating-point constant extraction, and systematic algorithm reconstruction.
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.
Automate GitHub pull request review resolution by processing ALL review comments and fixing ALL failing CI checks. Use when: (1) A PR has review comments that need to be addressed and resolved, (2) CI/CD checks are failing and need fixes, (3) You want to process all PR feedback and mark conversations as resolved, (4) You need to iterate on PR feedback quickly. IMPORTANT: This skill processes EVERY comment - no skipping allowed. Always fetches fresh data from GitHub. The only acceptable end state is zero unresolved threads. COMMIT CADENCE: Each thread gets its own commit (fix → commit → resolve → next). Never batch commits at the end.
Build throwaway prototypes to flesh out a design before committing. Routes between two branches — a runnable terminal app for state/business-logic questions, or several distinct UI variants switchable via one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
Use this skill for reinforcement learning tasks, including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use it to implement PPO training, create PufferEnv environments, optimize RL performance, or develop policies with CNNs/LSTMs.
Push notifications for web and mobile. Firebase Cloud Messaging (FCM), Apple Push Notification Service (APNs), Web Push API, Expo Notifications, and notification service architecture. USE WHEN: user mentions "push notification", "FCM", "Firebase messaging", "APNs", "web push", "service worker notification", "Expo notifications" DO NOT USE FOR: email notifications - use `email-sending`; in-app real-time updates - use `socket-io` or `sse`
Configures CI/CD pipelines for automated Python package publishing to PyPI or GitLab Package Registry. Use when creating GitHub Actions or GitLab CI release workflows, setting up trusted publishing or API token-based PyPI authentication, configuring version management with git tags and hatch-vcs, writing pyproject.toml publishing metadata, testing packages against TestPyPI, or documenting the release process for a Python project.
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.
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Core React 19 patterns including hooks, Suspense, lazy loading, component structure, TypeScript best practices, and performance optimization. Use when working with React components, hooks, lazy loading, Suspense boundaries, or React-specific TypeScript patterns.
Enforces a disciplined refactoring process for Ruby code: ONE atomic transformation at a time, characterization tests MUST exist and be Green BEFORE any edit, run tests after EVERY single step, rollback immediately on Red (no debugging in broken state), no behavior changes mixed with refactoring. Covers extract methods, rename symbols, split classes, inline variables, remove duplication. Use when: refactor, clean up code, rewrite class, structure changes, simplify.
Safely refactors dbt models with downstream impact analysis. Use when restructuring dbt models for: (1) Task mentions "refactor", "restructure", "extract", "split", "break into", or "reorganize" (2) Extracting CTEs to intermediate models or creating macros (3) Modifying model logic that has downstream consumers (4) Renaming columns, changing types, or reorganizing model dependencies Analyzes all downstream dependencies BEFORE making changes.
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.